School of Engineering and Technology, Department of Computer Science, Pondicherry University Pondicherry-India.

Size: px
Start display at page:

Download "School of Engineering and Technology, Department of Computer Science, Pondicherry University Pondicherry-India."

Transcription

1 IEEE-Internatonal Conference on Recent Trends n Informaton Technology, ICRTIT 2 MIT, Anna Unversty, Chenna. June 3-5, 2 Performance Evaluaton of Multlngual Informaton Retreval (MLIR) System over Informaton Retreval (IR) System Raju Korra #, Pothula Sujatha *2, Sdge Chetana *3, Madarapu Naresh Kumar #4 School of Engneerng and Technology, Department of Computer Scence, Pondcherry Unversty Pondcherry-Inda rajuu99@gmal.com 2 spothula@gmal.com 3 sdgechetana@gmal.com 4 madarapu.naresh@gmal.com Abstract Multlngual Informaton Retreval (MLIR) System deals wth the use of queres n one language and retreves the documents n varous languages. Here the Query translaton plays a central role n MLIR research. In ths paper, the language-ndependent ndexng technology s used to process the text collectons of Englsh, Telugu and Hnd languages. We have used multlngual dctonary based word-by-word query translaton. The expermental results are evaluated to analyze and compare the performance of Average Precson (AP IR ) and Mean Average Precson (MAP IR ) metrcs of IR system wth esteem to the Average Precson (AP MLIR ) and Mean Average Precson (MAP MLIR ) metrcs n MLIR system. Expermental result shows that the effectve retreval and performance of MLIR system has mproved by 3.4% over IR system. Index Terms Query translaton, MLIR, Recall, Precson, Average Precson, Mean Average Precson. I. INTRODUCTION Many nformaton worers collect nformaton from the global resources, whch mght be n dfferent languages. MLIR system s consdered as an mportant applcaton n IR. The am of MLIR system s to provde users a way to search documents wrtten n varous languages for a gven query. Several dfferences between monolngual IR and MLIR [3] arse f the user s well-versed wth more than one language. In order to reflect dfferng profcency levels of user language, the user nterface must provde dfferental dsplay capabltes. Translaton nto several languages s needed when more than one user receves the results. Dependng on the user's level of complexty, translaton of dfferent elements at dfferent stages can be provded to users for a range of nformaton access needs, ncludng eyword translaton, term translaton, ttle translaton, abstract translaton, specfc paragraph translaton, capton translaton, full document translaton, etc. Fnally, monolngual IR users can also tae advantage of the results of MLIR, where a query gven by user can retreve a set of valuable documents n other languages wthout any translatons. MLIR system uses a query n one language to retreve documents n varous languages. There exst language translaton ssues n MLIR. In addton to language translaton ssues, producng raned lst that nvolves documents n varous languages from several text collectons s crtcal process. In order to solve ths crtcal ssue there are two possble archtectures n MLIR. They are centralzed and dstrbuted. In the former archtecture, a huge collecton that contans documents n dfferent languages s used. In the later archtecture, documents are n varous languages are ndexed and retreved separately and then all the results are merged nto a multlngual raned lst [8]. For evaluatng the Centralzed MLIR system performance we are comparng some standard metrcs such as Recall, Precson, Average Precson and Mean Average Precson metrcs wth the IR system. MLIR system can help the users to query n ther natve language and retreve nformaton n varous languages. At a basc level, there are two approaches that can be taen when t comes to the desgn of a MLIR system. They are: translaton of query language [3] or translaton of the document language. Snce n MLIR the query language and document language dffer, a query representaton must be compared wth each document representaton n order to determne the degree of smlarty: In MLIR, ether the query must be translated nto the document language, or the document n the query language. Former way s a better way because translatng a query one s much more effcent than translatng each and every document n the collecton nto the query language. The advantage of query translaton [4] rather than document translaton s that a query translaton module may be added to an exstng IR system s easy, when compared wth the cost of modfyng the entre document base and redesgnng the system for multlngual retreval. The remander of ths paper s organzed as follows. Secton 2 dscusses related wor to ths study. Secton 3 Tradtonal measures for evaluatng the performance of IR system, secton 4 descrbes the proposed performance evaluaton method for MLIR system, and secton 5 presents the Expermental Results. Fnally secton 6 concludes the paper. II. RELATED WORK Three dfferent strateges [9] for query translaton were used namely, dctonary-based, thesaurus-based, and corpusbased methods [, 5, 4]. For dctonary-based approaches, //$26. 2 IEEE 722

2 IEEE-ICRTIT 2 Hull and Grefenstette [3] performed experments usng dctonary-based approach wthout ambguty analyss. Informaton Retreval models are weghtng and ndexng process: the three IR models are () Boolean model: In ths model the documents and query are represented as sets of ndex terms; t s set theoretc, () Probablstc model: The framewor for modellng documents and query representaton s based on probablty theory; ths s probablstc, () Vector space model: The query and documents are represents vectors n t-dmensonal space; t s algebrac. They translate nonnames; they used a probablstc word translaton derved from bdrectonal word algnments extracted from GIZA++ [Och and Ney ] [29] by the Machne Translaton members of Defence Advanced Research Projects Agency Global Autonomous Language Explotaton (DARPA GALE) team. Ths teams s provded wth a multlngual corpus, ncludng text and speech, consstng of Englsh, Arabc and Chnese documents. They mplemented a straghtforward probablstc structured query approach [Darwsh and Oard, 3], and translated all word usng ths model. Document Translaton (DT) does sgnfcantly better than Query Translaton (QT). Salton et.al [8] also suggested that the performance of MLIR systems could resemble those monolngual ones provded a correct multlngual thesaurus s establshed. For poor performance of QT havng two problems :() Prevalence of rare names n the queres, t was not covered by the translaton dctonary, () translaton of non-name phrases. A QT module nclude translteraton mght mprove performance of QT for names. For non-name arguments usng full SMT than the typcal approach of word by word translaton mght lead to better QT. Sa and Saa [2] are proposed IR metrcs for the tas of retrevng one hghly relevant documents and opposed to the fndng as many relevant documents as possble. Bucley and Voorhees [22], Voorhees [23] used the stablty and swap method consdered bnary IR metrcs. Sanderson and Zobel [24] and Saa [25] explored a few varatons of the swap method. Saa [26] proposed a method for comparng the senstvty of IR metrcs based on Bootstrap Hypothess Tests. Saa [27] nvestgated the ran correlatons among Ave P, R- Prec, Q-measure and R-measure usng NTCIR data. Vu and Gallnnar [28] generalzed AveP for handlng graded relevance. To promote research and development n the area of IR n Inda, the followng Evaluaton campagns are conducted. ILIR-29 Inda Language IR IRSI-24 IR Socety of Inda FIRE-2 Forum for IR Evaluaton MIRACLE-Maryland Interactve Retreval Advanced Cross-Language Engne NIST- Natonal Insttute of Standards and Technology Evaluaton campagns n other countres ncludes Cranfeld-958 UK TREC-992 Text Retreval Conference USA NTCIR NII-999 Test Collecton for IR Systems Japan CLEF-2Cross-Language Evaluaton Forum Europe The new applcaton of MLIR draws on achevements and technques n several related areas [3] ) Informaton Access: document ndexng (multlngual); retrevng, flterng, clusterng; presentaton and summarzaton of nformaton; multlngual metadata; crosslanguage nformaton retreval. 2) Machne Translaton: comparable and parallel text algnment; language generaton. 3) Computatonal Lngustcs: morphologcal analyss, syntactc parsng, technques for dsambguaton, document segmentaton, corpus analyss, creaton of dervatve lexcons, term recognton and term expanson. 4) Resources: dctonares, thesaur, ndex terms, test collectons, speech data bases. III. TRADITIONAL MEASURES FOR EVALUATING THE PERFORMANCE OF IR SYSTEM To measure s to now, f we cannot measure t, we cannot mprove t, for that purpose we mprove the characterstcs of IR/MLIR systems usng the metrcs. In relevance judgment [4], human evaluators wll read the content of each returned document and judge f t satsfes the nformaton need of that partcular topc. Gradng on returned document s gven as follows. L2 (Relevant): contans nformaton that satsfes the nformaton need. L (Partally relevant): contans nformaton that partally satsfes the nformaton need. L (Not relevant): does not contan nformaton relevant to the nformaton need. Based on relevance judgment the evaluatons nclude: A. Set based evaluaton B. Ran based evaluaton wth explct absolute judgments C. Ran based evaluaton wth explct preference judgments D. Ran based evaluaton wth mplct judgments A. Set based evaluaton ) Precson: Precson [5] [6] s the fracton of the documents retreved that are relevant to the user's nformaton need. () Where t p =relevant tems retreved, t p + f p = relevant retreved tems and t p =true postve, f p =false postve 2) Recall: Recall [5] s the fracton of the documents that are relevant to the query that are successfully retreved. R (2) 723

3 Performance Evaluaton of Multlngual Informaton Retreval (MLIR) System over Informaton Retreval (IR) System Where t p =relevant retreved tems, t p +f n =total number of relevant retreved tems n the database, t p =true postve, f n =false negatve B. Ran based evaluaton wth explct absolute judgments ) Average precson (AP): AP [6] emphaszes ranng relevant documents hgher. It s the average of precsons computed at the pont of each of the relevant documents n the raned sequence. Dscounted gan at Ran r, precson at Ran r = P(r), AP = r Pr j (3) j D j + Where D + denotes the number of relevant documents wth respect to the query. 2) (Voorhees et al. 25) [6] s a measure for evaluatng top postons of a raned lst usng two levels (relevant and rrelevant) of relevance judgment: = r (4) j j = Where = the truncaton poston, r j = f the document n the j th poston s relevant and zero otherwse. C. Ran based evaluaton wth explct preference judgments ) Kendall s ran correlaton: Kendall s ran correlaton [6] s a monotonc functon of the probablty that a randomly chosen par of raned systems s ordered dentcally n the two ranngs. Hence a swap near the top of a raned lst and that near the bottom of the same lst has equal mpact. However, for the purpose of ranng retreval systems, for example, n a competton-style worshop such as NTCIR and TREC [9], the rans near the top of the lst are arguably more mportant than those near the bottom. C D endall = (5) L ( L ) / 2 C = number of system pars that are raned n the same order n both ranngs, and let D= number of system pars that are raned n opposte order n the two ranngs, the sze of the raned lsts be L. D. Ran based evaluaton wth mplct judgments ) Mean Average Precson (MAP): Most standard among the TREC communty s MAP [5] [6], whch provdes a sngle-fgure measure of qualty across recall levels. Among valuaton measures, MAP has been shown to have especally good dscrmnaton and stablty. For a sngle nformaton need, AP s the average of the precson value obtaned for the set of top documents exstng after each relevant document s retreved, and ths value s then averaged over nformaton needs. MAPQ / Q Q PrecsonRj (6) Where Q=set of relevant documents, R=recall IV. PERFORMANCE EVALUATION FOR PROPOSED MLIR METRICS For the MLIR system evaluaton only basc metrcs le Precson, Recall etc. [2] are avalable but there s no standard specfc metrcs for measurng the performance of ths system. A. Dfferent Degrees of MLIR Localzaton of user nterfaces, monolngual n dfferent languages Query n L, all documents n L 2 Query n L, documents n L +L 2...+L n Query n L, documents multlngual The MLIR, both the source and translated queres are used to search a mult-lngual collecton for relevant documents. Then, only retreved documents that are not n the user language are translated nto the user language. In prncple, we need only the engne to realze MLIR n the sense that users can retreve/ browse foregn documents through ther natve language. However, to mprove the qualty of our system, two alternatve post-processng modules can optonally be used. There are two types of techncal ssues must be addressed when dealng wth multlngual data [] () techncal ssues nvolvng data exchange, wth a set of attendant sub-ssues. () natural language questons, also wth a set of attendant research ssues. B. Multple translatons The query translaton process s accomplshed as follow: Let M be the number of query terms, then we defne user s query as: Q = {q } (= M) (7) Then we loo each q up n the dctonary [8] and after fndng translatons of q we splt the translatons nto ts consttuent toens. Weghted Structured Query Translaton[]: taes advantage of multple translatons and translaton probabltes TF and DF of query term e are computed usng TF and DF of ts translatons TF ( e, D ) = p( f e) TF( f, D ) f DF ( e ) = p ( f e ) DF ( f ) f (9) Where p (f e) s the estmated probablty that e would be properly translated to f. ) Precson (P MLIR ): precson s the rate between the relevant documents retreved by the MLIR system n response to a query and the total number of documents retreved. In bnary classfcaton precson s analogous to the postve predctve value. P MLIR () Where r d {, } the relevance of documents d for the user, f d {, } the retreval of documents d n the processng of the current query. (8) 724

4 IEEE-ICRTIT 2 2) Recall (R MLIR ): Recall s the rate between the number of relevant documents retreved and the total number of documents to the query exstng n the database. In bnary classfcaton recall s called as senstvty. R MLIR () Where r d {, } the relevance of documents d for the user, f d {, } the retreval of documents d n the processng of the current query. 3) Average Precson (AP MLIR ): Average of the precson values at the ponts at whch each relevant documents retreved n some user specfc languages. N P MLIR.B D AP MLIR (2) Where r=ran of the query n n languages, N=the number of retreved documents n n languages, B(r) =bnary functon on the relevance of a gven ran r n n languages, D =numbe of relevant documents, P MLIR (r) =Precson at a cut of ran r n n languages. P MLIR r (3) 4) Mean Average Precson (MAP MLIR ): Average of the average precson values for a number of queres n MLIR system. NQ AP MLIR NQ MAP MLIR (4) NQ Where NQ=number of queres The overall desgn of our system, whch conssts of an engne, and two post-processng modules, that s, re-ranng and clusterng modules. The engne retreves documents n response to user queres, and outputs those documents n the source (user) language. The MLIR, both the source and translated queres are used to search a mult-lngual collecton for relevant documents. Then, only retreved documents that are not n the user language are translated nto the user language. In prncple, we need only the engne to realze MLIR n the sense that users can retreve/ browse foregn documents through ther natve language. However, to mprove the qualty of our system, two alternatve postprocessng modules can optonally be used. The two-stage method, the re-ranng module re-rans documents retreved by the engne to mprove the retreval accuracy. In ths case, the engne and re- ranng module correspond to the frst and second stages, respectvely. The post-translaton query expanson component expands the query n the target language n a way smlar to pre-translaton expanson. Fnally document retreval [9] component taes the query n the target language and retrevng the relevant documents from the text collecton. V. EXPERIMENTAL RESULTS In the proposed MLIR metrcs, we used dctonary based query translaton usng word to word translaton. Altogether we have used documents whch nclude Englsh, Telugu and Hnd documents. Fnally MLIR metrcs Precson, Recall, Average Precson and Mean Average Precson are evaluated usng Natural language processng toolt named General Archtecture for Text Engneerng (GATE 6.-beta) that uses Java.6._7 on wndows XP. We used the Google Translate.7 API ( to translate the resources provded n other languages. In evaluaton of MLIR systems, we compared the attrbutes of exstng system that s IR system and we get mproved results of MLIR system n terms of effectve retreval. Table ncludes the calculated precson and Recall values obtaned from 2 Queres on IR and MLIR systems whch are graphcally shown n fg. and fg.2 respectvely. Table 2 contans calculated AP IR and AP MLIR values obtaned from queres appled on IR and MLIR systems. MAP IR and MAP MLIR values are calculated from AP IR and AP MLIR, as tabulated n table 3. Fg 3 gves the comparatve performance evaluaton of AP n IR System over AP n MLIR systems and fg.4 depcts the performance evaluaton of MAP n IR System to that of MLIR system. Expermental results show that the effectve retreval of MLIR system has mproved by 3.4% over IR system. TABLE. CALCULATED PRECISION AND RECALL IN MLIR SYSTEM Query Precson IR Precson MLIR Recall IR Recall MLIR

5 Performance Evaluaton of Multlngual Informaton Retreval (MLIR) System over Informaton Retreval (IR) System.8.4 PrecsonIR PrecsonMLIR Queres Fg. Calculated Precson values n IR and MLIR System.8 RecallIR RecallMLIR Queres TABLE 2.CALCULATED AP IN IR AND MLIR SYSTEMS Fg 2. Calculated Recall values n IR and MLIR System Query AP IR AP MLIR Number of Queres Fg4.comparson of MAP n IR and MLIR systems MAPIR MAPMLIR TABLE 3.CALCULATED MAP IN IR AND MLIR SYSTEMS No. of Queres MAP I IR MAP MLIR APIR APMLIR Query Number Fg 3. Comparson of AP n IR and MLIR systems VI. CONCLUTION Here multlngual dctonary based word-by-word query translaton s used and the text collectons of Englsh, Telugu and Hnd languages are beng processed n IR and MLIR systems. The expermental evaluaton of Precson, Recall, 726

6 IEEE-ICRTIT 2 Average Precson and Mean Average Precson n IR and MLIR systems have been done and the performance s beng compared. Expermental results show that the effectve retreval and performance of MLIR system has mproved by 3.4% over IR system. REFERENCES [] Daqng He, Dan Wu. "Enhancng Query Translaton wth Relevance Feedbac n Translngual Informaton Retreval." Informaton Processng and Management Vol 47, Issue, Pages -7, 2. [2] Dan Wu, Daqng He. A Study of Query Translaton usng Google Machne Translaton System. In Proceedngs of the 2 Internatonal Conference on Computatonal ntellgence and Software Engneerng (CSE 2), Dec. 2, Wuhan, Chna. [3] Dan Wu, Daqng He, Huln Wang. Cross-Language Query Expanson Usng Pseudo Relevance Feedbac. Journal of the Chnese Socety for Scentfc and Techncal Informaton (2): [4] Qang, Pu, Daqng He, Q L. "Query Expanson for Effectve Geographc Informaton Retreval." Evaluatng Systems for Multlngual and Multmodal Informaton Access, 9th Worshop of the Cross-Language Evaluaton Forum, CLEF 28, Aarhus, Denmar, Revsed Selected Papers. Sprnger. 29. [5] Al Dasdan, Kostas Tsoutsoulls, Emre Velpasaoglu Web Search Engne Metrcs for Measurng User Satsfacton {dasdan, Kostas, emrev}@yahoo-nc.com, Yahoo! Inc. 2 Apr 29 8th Internatonal World Wde Web Conference Aprl 2-24, 29. [6] Tetsuya Saa, Stephen Robertson, Modelng a User Populaton for Desgnng Informaton Retreval Metrcs, the Second Internatonal Worshop on Evaluatng Informaton Access (EVIA), December 6, 28, Toyo, Japan. [7] Daqng He, Dan Wu. Translaton Enhancement: A New Relevance Feedbac Method for Cross-Language Informaton Retreval. In the Proceedngs of ACM 7th Conference on Informaton and Knowledge Management (CIKM 28) pages [8] Chen-Hsn Cheng, Reuy-Jye Shue, Hung-Ln Lee, Shu-Yu Hseh, Guann-Cyun Yeh, & Guo-We Ban: AINLP at NTCIR-6: evaluatons for multlngual and cross-lngual nformaton retreval Proceedngs of NTCIR-6 Worshop Meetng, May 5-8, 27, Toyo, Japan. [9] Hsn-Chang Yang and Chung-Hong Lee (28) "Multlngual Informaton Retreval usng GHSOM." In Proceedngs of The Eghth Internatonal Conference on Intellgent Systems Desgn and Applcatons (ISDA-28), Vol., Kaohsung, Tawan, Nov , 28, pp [] D. W. Oard and B. J. Dorr. A survey of multlngual text retreval. Techncal Report UMIACS-TR-96-9, Unversty of Maryland, Insttute for Advanced Computer Studes, College Par, MD, 996. [] Jan-Yun Ne, Fuman Jn: A Multlngual Approach to Multlngual Informaton Retreval. CLEF 22: -. [2] L. Ballesteros and W. B. Croft. Dctonary-based methods for cross-lngual nformaton retreval. In Proceedngs of the 7th Internatonal DEXA Conference on Database and Expert Systems Applcatons, pages 79 8, 996. [3] D. A. Hull and G. Grefenstette. Queryng across languages: a dctonary-based approach to multlngual nformaton retreval. In Proceedngs of the 9th Internatonal Conference on Research and Development n Informaton Retreval, pages 49 57, 996. [4] H. H. Chen, C. C. Ln, and W. C. Ln. Constructon of a chneseenglsh wordnet and ts applcaton to clr. In Proceedngs of 5th Internatonal Worshop on Informaton Retreval wth Asan Languages, pages 89 96, 2. [5] L. Ballesteros and W. B. Croft. Dctonary-based methods for crosslngual nformaton retreval. In Proceedngs of the 7 th Internatonal DEXA Conference on Database and Expert Systems Applcatons, pages 79 8, 996. [6] Olver Chapelle, Quoc V. Le, Alex Smola, and Choon Hu Teo, Optmzaton of Ranng Measures, Journal of Machne Learnng Research (2) -48. [7] Chrstopher D. Mannng, Prabhaar Raghavan & Hnrch Schütze, An Introducton to Informaton Retreval 29 Cambrdge Unversty Press Prnted on Aprl, 29 Webste: [8] G. Salton. Automatc processng of foregn language documents. Journal of the Amercan Socety for Informaton Scence, 2(3):87 94, 97. [9] Alon Lave, Kenj Sagae, Shyamsundar Jayaraman the Sgnfcance of Recall n Automatc Metrcs for MT Evaluaton , In Proceedngs of the 6th Conference of the Assocaton for Machne Translaton n the Amercas (AMTA-24). [2] Mar Davs and Ted Dunnng. A trec evaluaton of query translaton methods for mult-lngual text retreval. In Proceedngs of the Fourth Retreval Conference (TREC-4) Gathersburg, MD: Natonal Insttute of Standards and Technology, Specal Publcaton 5-236, 995. [2] Saa, 26b Saa, T. (26b). Gve me just one hghly relevant document: P-measure. In Proceedngs of the 29th annual nternatonal ACM SIGIR conference on research and development n nformaton retreval (SIGIR 26). [22] Bucley and Voorhees, 24 Bucley, C., & Voorhees, E. M. (24). Retreval evaluaton wth ncomplete nformaton. In Proceedngs of the 27th annual nternatonal ACM SIGIR conference on research and development n nformaton retreval (SIGIR 24) (pp ). [23] Voorhees, 25 Voorhees, E. M. (25). Overvew of the TREC 24 robust retreval trac. In Proceedngs of the 3th text retreval conference (TREC 24). [24] Sanderson and Zobel, 25 Sanderson, M., & Zobel, J. (25). Informaton retreval system evaluaton: effort, senstvty, and relablty. In Proceedngs of the 28th annual nternatonal ACM SIGIR conference on research and development n nformaton retreval (SIGIR 25) (pp ). [25] Saa, 25a Saa, T. (25a). The effect of topc samplng on senstvty comparsons of nformaton retreval metrcs. In Proceedngs of the 5th NTCIR worshop on research n nformaton access technologes (NTCIR-5). [26] Saa, 26a Saa, T. (26a). Evaluatng evaluaton metrcs based on the bootstrap. In Proceedngs of the 29th annual nternatonal ACM SIGIR conference on research and development n nformaton retreval (SIGIR 26). [27] Saa, 24 Saa, T. (24). Ranng the NTCIR systems based on multgrade relevance. In Proceedngs of Asa nformaton retreval symposum 24 (pp. 7 77). [28] Vu and Gallnar, 25 Vu, H.-T., & Gallnar, P. (25). On effectveness measures and relevance functons n ranng INEX systems. In Proceedngs of Asa nformaton retreval symposum 25. Lecture notes n computer scence: Vol (pp ). [29] Krsten Parton, Kathleen McKeown, James Allan, Enrque Henestroza: Smultaneous multlngual search for translngual nformaton retreval. CIKM 28: [3] Contrbutors: Chrstan Fluhr Robert E. Frederng Doug Oard Atosh Oumura, Ka Ishawa, and Kenj Chapter 2 Multlngual (or Cross-lngual) Informaton Retreval,Edtors: Judth Klavans and Eduard Hovy Satoh 727

Description of NTU Approach to NTCIR3 Multilingual Information Retrieval

Description of NTU Approach to NTCIR3 Multilingual Information Retrieval Proceedngs of the Thrd NTCIR Workshop Descrpton of NTU Approach to NTCIR3 Multlngual Informaton Retreval Wen-Cheng Ln and Hsn-Hs Chen Department of Computer Scence and Informaton Engneerng Natonal Tawan

More information

UB at GeoCLEF Department of Geography Abstract

UB at GeoCLEF Department of Geography   Abstract UB at GeoCLEF 2006 Mguel E. Ruz (1), Stuart Shapro (2), June Abbas (1), Slva B. Southwck (1) and Davd Mark (3) State Unversty of New York at Buffalo (1) Department of Lbrary and Informaton Studes (2) Department

More information

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

Cross-lingual Pseudo Relevance Feedback Based on Weak Relevant Topic Alignment

Cross-lingual Pseudo Relevance Feedback Based on Weak Relevant Topic Alignment Cross-lngual Pseudo Relevance Feedback Based on Weak Relevant opc Algnment WANG Xu-wen Insttute of Medcal Informaton & Lbrary, Chnese Academy of Medcal Scences, Beng 100020 wang.xuwen@mcams.ac.cn ZHANG

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Query Clustering Using a Hybrid Query Similarity Measure

Query Clustering Using a Hybrid Query Similarity Measure Query clusterng usng a hybrd query smlarty measure Fu. L., Goh, D.H., & Foo, S. (2004). WSEAS Transacton on Computers, 3(3), 700-705. Query Clusterng Usng a Hybrd Query Smlarty Measure Ln Fu, Don Hoe-Lan

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty

More information

The Research of Support Vector Machine in Agricultural Data Classification

The Research of Support Vector Machine in Agricultural Data Classification The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Web Document Classification Based on Fuzzy Association

Web Document Classification Based on Fuzzy Association Web Document Classfcaton Based on Fuzzy Assocaton Choochart Haruechayasa, Me-Lng Shyu Department of Electrcal and Computer Engneerng Unversty of Mam Coral Gables, FL 33124, USA charuech@mam.edu, shyu@mam.edu

More information

Private Information Retrieval (PIR)

Private Information Retrieval (PIR) 2 Levente Buttyán Problem formulaton Alce wants to obtan nformaton from a database, but she does not want the database to learn whch nformaton she wanted e.g., Alce s an nvestor queryng a stock-market

More information

X- Chart Using ANOM Approach

X- Chart Using ANOM Approach ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

Semantic Image Retrieval Using Region Based Inverted File

Semantic Image Retrieval Using Region Based Inverted File Semantc Image Retreval Usng Regon Based Inverted Fle Dengsheng Zhang, Md Monrul Islam, Guoun Lu and Jn Hou 2 Gppsland School of Informaton Technology, Monash Unversty Churchll, VIC 3842, Australa E-mal:

More information

Enhancement of Infrequent Purchased Product Recommendation Using Data Mining Techniques

Enhancement of Infrequent Purchased Product Recommendation Using Data Mining Techniques Enhancement of Infrequent Purchased Product Recommendaton Usng Data Mnng Technques Noraswalza Abdullah, Yue Xu, Shlomo Geva, and Mark Loo Dscplne of Computer Scence Faculty of Scence and Technology Queensland

More information

Resolving Surface Forms to Wikipedia Topics

Resolving Surface Forms to Wikipedia Topics Resolvng Surface Forms to Wkpeda Topcs Ypng Zhou Lan Ne Omd Rouhan-Kalleh Flavan Vasle Scott Gaffney Yahoo! Labs at Sunnyvale {zhouy,lanne,omd,flavan,gaffney}@yahoo-nc.com Abstract Ambguty of entty mentons

More information

Available online at Available online at Advanced in Control Engineering and Information Science

Available online at   Available online at   Advanced in Control Engineering and Information Science Avalable onlne at wwwscencedrectcom Avalable onlne at wwwscencedrectcom Proceda Proceda Engneerng Engneerng 00 (2011) 15000 000 (2011) 1642 1646 Proceda Engneerng wwwelsevercom/locate/proceda Advanced

More information

CS47300: Web Information Search and Management

CS47300: Web Information Search and Management CS47300: Web Informaton Search and Management Prof. Chrs Clfton 15 September 2017 Materal adapted from course created by Dr. Luo S, now leadng Albaba research group Retreval Models Informaton Need Representaton

More information

Arabic Text Classification Using N-Gram Frequency Statistics A Comparative Study

Arabic Text Classification Using N-Gram Frequency Statistics A Comparative Study Arabc Text Classfcaton Usng N-Gram Frequency Statstcs A Comparatve Study Lala Khresat Dept. of Computer Scence, Math and Physcs Farlegh Dcknson Unversty 285 Madson Ave, Madson NJ 07940 Khresat@fdu.edu

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

Learning-Based Top-N Selection Query Evaluation over Relational Databases

Learning-Based Top-N Selection Query Evaluation over Relational Databases Learnng-Based Top-N Selecton Query Evaluaton over Relatonal Databases Lang Zhu *, Wey Meng ** * School of Mathematcs and Computer Scence, Hebe Unversty, Baodng, Hebe 071002, Chna, zhu@mal.hbu.edu.cn **

More information

Detection of an Object by using Principal Component Analysis

Detection of an Object by using Principal Component Analysis Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

More information

Cross-Language Information Retrieval

Cross-Language Information Retrieval Feature Artcle: Cross-Language Informaton Retreval 19 Cross-Language Informaton Retreval Jan-Yun Ne 1 Abstract A research group n Unversty of Montreal has worked on the problem of cross-language nformaton

More information

Querying by sketch geographical databases. Yu Han 1, a *

Querying by sketch geographical databases. Yu Han 1, a * 4th Internatonal Conference on Sensors, Measurement and Intellgent Materals (ICSMIM 2015) Queryng by sketch geographcal databases Yu Han 1, a * 1 Department of Basc Courses, Shenyang Insttute of Artllery,

More information

Keywords - Wep page classification; bag of words model; topic model; hierarchical classification; Support Vector Machines

Keywords - Wep page classification; bag of words model; topic model; hierarchical classification; Support Vector Machines (IJCSIS) Internatonal Journal of Computer Scence and Informaton Securty, Herarchcal Web Page Classfcaton Based on a Topc Model and Neghborng Pages Integraton Wongkot Srura Phayung Meesad Choochart Haruechayasak

More information

VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES

VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES UbCC 2011, Volume 6, 5002981-x manuscrpts OPEN ACCES UbCC Journal ISSN 1992-8424 www.ubcc.org VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES

More information

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval KD Lab at mageclef 2012 Personal Photo Retreval Cha-We Ku, Been-Chan Chen, Guan-Bn Chen, L-J Gaou, Rong-ng Huang, and ao-en Wang Knowledge, nformaton, and Database ystem Laboratory Department of Computer

More information

Improving the Quality of Information Retrieval Using Syntactic Analysis of Search Query

Improving the Quality of Information Retrieval Using Syntactic Analysis of Search Query Improvng the Qualty of Informaton Retreval Usng Syntactc Analyss of Search Query Nadezhda Yarushkna 1[0000-0002-5718-8732], Aleksey Flppov 1[0000-0003-0008-5035], and Mara Grgorcheva 1[0000-0001-7492-5178]

More information

MODULE DESIGN BASED ON INTERFACE INTEGRATION TO MAXIMIZE PRODUCT VARIETY AND MINIMIZE FAMILY COST

MODULE DESIGN BASED ON INTERFACE INTEGRATION TO MAXIMIZE PRODUCT VARIETY AND MINIMIZE FAMILY COST INTERNATIONAL CONFERENCE ON ENGINEERING DESIGN, ICED 07 28-31 AUGUST 2007, CITE DES SCIENCES ET DE L'INDUSTRIE, PARIS, FRANCE MODULE DESIGN BASED ON INTERFACE INTEGRATION TO MAIMIZE PRODUCT VARIETY AND

More information

Merging Results by Using Predicted Retrieval Effectiveness

Merging Results by Using Predicted Retrieval Effectiveness Mergng Results by Usng Predcted Retreval Effectveness Introducton Wen-Cheng Ln and Hsn-Hs Chen Departent of Coputer Scence and Inforaton Engneerng Natonal Tawan Unversty Tape, TAIWAN densln@nlg.cse.ntu.edu.tw;

More information

Combining Multiple Resources, Evidence and Criteria for Genomic Information Retrieval

Combining Multiple Resources, Evidence and Criteria for Genomic Information Retrieval Combnng Multple Resources, Evdence and Crtera for Genomc Informaton Retreval Luo S 1, Je Lu 2 and Jame Callan 2 1 Department of Computer Scence, Purdue Unversty, West Lafayette, IN 47907, USA ls@cs.purdue.edu

More information

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks Decson Strateges for Ratng Objects n Knowledge-Shared Research etwors ALEXADRA GRACHAROVA *, HAS-JOACHM ER **, HASSA OUR ELD ** OM SUUROE ***, HARR ARAKSE *** * nsttute of Control and System Research,

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

Pruning Training Corpus to Speedup Text Classification 1

Pruning Training Corpus to Speedup Text Classification 1 Prunng Tranng Corpus to Speedup Text Classfcaton Jhong Guan and Shugeng Zhou School of Computer Scence, Wuhan Unversty, Wuhan, 430079, Chna hguan@wtusm.edu.cn State Key Lab of Software Engneerng, Wuhan

More information

Meta-heuristics for Multidimensional Knapsack Problems

Meta-heuristics for Multidimensional Knapsack Problems 2012 4th Internatonal Conference on Computer Research and Development IPCSIT vol.39 (2012) (2012) IACSIT Press, Sngapore Meta-heurstcs for Multdmensonal Knapsack Problems Zhbao Man + Computer Scence Department,

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

Document Representation and Clustering with WordNet Based Similarity Rough Set Model

Document Representation and Clustering with WordNet Based Similarity Rough Set Model IJCSI Internatonal Journal of Computer Scence Issues, Vol. 8, Issue 5, No 3, September 20 ISSN (Onlne): 694-084 www.ijcsi.org Document Representaton and Clusterng wth WordNet Based Smlarty Rough Set Model

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications 14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of

More information

PRÉSENTATIONS DE PROJETS

PRÉSENTATIONS DE PROJETS PRÉSENTATIONS DE PROJETS Rex Onlne (V. Atanasu) What s Rex? Rex s an onlne browser for collectons of wrtten documents [1]. Asde ths core functon t has however many other applcatons that make t nterestng

More information

Selecting Query Term Alterations for Web Search by Exploiting Query Contexts

Selecting Query Term Alterations for Web Search by Exploiting Query Contexts Selectng Query Term Alteratons for Web Search by Explotng Query Contexts Guhong Cao Stephen Robertson Jan-Yun Ne Dept. of Computer Scence and Operatons Research Mcrosoft Research at Cambrdge Dept. of Computer

More information

Estimating Costs of Path Expression Evaluation in Distributed Object Databases

Estimating Costs of Path Expression Evaluation in Distributed Object Databases Estmatng Costs of Path Expresson Evaluaton n Dstrbuted Obect Databases Gabrela Ruberg, Fernanda Baão, and Marta Mattoso Department of Computer Scence COPPE/UFRJ P.O.Box 685, Ro de Janero, RJ, 2945-970

More information

Federated Search of Text-Based Digital Libraries in Hierarchical Peer-to-Peer Networks

Federated Search of Text-Based Digital Libraries in Hierarchical Peer-to-Peer Networks Federated Search of Text-Based Dgtal Lbrares n Herarchcal Peer-to-Peer Networks Je Lu School of Computer Scence Carnege Mellon Unversty Pttsburgh, PA 15213 jelu@cs.cmu.edu Jame Callan School of Computer

More information

Intrinsic Plagiarism Detection Using Character n-gram Profiles

Intrinsic Plagiarism Detection Using Character n-gram Profiles Intrnsc Plagarsm Detecton Usng Character n-gram Profles Efstathos Stamatatos Unversty of the Aegean 83200 - Karlovass, Samos, Greece stamatatos@aegean.gr Abstract: The task of ntrnsc plagarsm detecton

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010 Smulaton: Solvng Dynamc Models ABE 5646 Week Chapter 2, Sprng 200 Week Descrpton Readng Materal Mar 5- Mar 9 Evaluatng [Crop] Models Comparng a model wth data - Graphcal, errors - Measures of agreement

More information

A Generation Model to Unify Topic Relevance and Lexicon-based Sentiment for Opinion Retrieval

A Generation Model to Unify Topic Relevance and Lexicon-based Sentiment for Opinion Retrieval A Generaton Model to Unfy Topc Relevance and Lexcon-based Sentment for Opnon Retreval Mn Zhang State key lab of Intellgent Tech.& Sys, Dept. of Computer Scence, Tsnghua Unversty, Bejng, 00084, Chna 86-0-6279-2595

More information

HIGH-LEVEL SEMANTICS OF IMAGES IN WEB DOCUMENTS USING WEIGHTED TAGS AND STRENGTH MATRIX

HIGH-LEVEL SEMANTICS OF IMAGES IN WEB DOCUMENTS USING WEIGHTED TAGS AND STRENGTH MATRIX HIGH-LEVEL SEMANTICS OF IMAGES IN WEB DOCUMENTS USING WEIGHTED TAGS AND STRENGTH MATRIX P.Shanmugavadvu 1, P.Sumathy 2, A.Vadvel 3 12 Department of Computer Scence and Applcatons, Gandhgram Rural Insttute,

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents

More information

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

More information

A Method of Hot Topic Detection in Blogs Using N-gram Model

A Method of Hot Topic Detection in Blogs Using N-gram Model 84 JOURNAL OF SOFTWARE, VOL. 8, NO., JANUARY 203 A Method of Hot Topc Detecton n Blogs Usng N-gram Model Xaodong Wang College of Computer and Informaton Technology, Henan Normal Unversty, Xnxang, Chna

More information

A Novel Term_Class Relevance Measure for Text Categorization

A Novel Term_Class Relevance Measure for Text Categorization A Novel Term_Class Relevance Measure for Text Categorzaton D S Guru, Mahamad Suhl Department of Studes n Computer Scence, Unversty of Mysore, Mysore, Inda Abstract: In ths paper, we ntroduce a new measure

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Review of approximation techniques

Review of approximation techniques CHAPTER 2 Revew of appromaton technques 2. Introducton Optmzaton problems n engneerng desgn are characterzed by the followng assocated features: the objectve functon and constrants are mplct functons evaluated

More information

Information Retrieval

Information Retrieval Anmol Bhasn abhasn[at]cedar.buffalo.edu Moht Devnan mdevnan[at]cse.buffalo.edu Sprng 2005 #$ "% &'" (! Informaton Retreval )" " * + %, ##$ + *--. / "#,0, #'",,,#$ ", # " /,,#,0 1"%,2 '",, Documents are

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

A Novel Optimization Technique for Translation Retrieval in Networks Search Engines

A Novel Optimization Technique for Translation Retrieval in Networks Search Engines A Novel Optmzaton Technque for Translaton Retreval n Networks Search Engnes Yanyan Zhang Zhengzhou Unversty of Industral Technology, Henan, Chna Abstract - Ths paper studes models of Translaton Retreval.e.

More information

Relevance Feedback Document Retrieval using Non-Relevant Documents

Relevance Feedback Document Retrieval using Non-Relevant Documents Relevance Feedback Document Retreval usng Non-Relevant Documents TAKASHI ONODA, HIROSHI MURATA and SEIJI YAMADA Ths paper reports a new document retreval method usng non-relevant documents. From a large

More information

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1)

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1) Secton 1.2 Subsets and the Boolean operatons on sets If every element of the set A s an element of the set B, we say that A s a subset of B, or that A s contaned n B, or that B contans A, and we wrte A

More information

A new query expansion method based on query logs mining1

A new query expansion method based on query logs mining1 Internatonal Journal on Asan Language Processng, 19 (1): 1-12 1 A new query expanson method based on query logs mnng1 Zhu Kunpeng, Wang Xaolong, Lu Yuanchao School of Computer Scence and Technology, Harbn

More information

Relevance Feedback for Image Retrieval

Relevance Feedback for Image Retrieval Vashal D Dhale et al, / (IJCSIT Internatonal Journal of Computer Scence and Informaton Technologes, Vol 4 (2, 203, 39-323 Relevance Feedback for Image Retreval Vashal D Dhale, Dr A R Mahaan, Prof Uma Thakur

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

Cordial and 3-Equitable Labeling for Some Star Related Graphs

Cordial and 3-Equitable Labeling for Some Star Related Graphs Internatonal Mathematcal Forum, 4, 009, no. 31, 1543-1553 Cordal and 3-Equtable Labelng for Some Star Related Graphs S. K. Vadya Department of Mathematcs, Saurashtra Unversty Rajkot - 360005, Gujarat,

More information

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints Australan Journal of Basc and Appled Scences, 2(4): 1204-1208, 2008 ISSN 1991-8178 Sum of Lnear and Fractonal Multobjectve Programmng Problem under Fuzzy Rules Constrants 1 2 Sanjay Jan and Kalash Lachhwan

More information

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem An Effcent Genetc Algorthm wth Fuzzy c-means Clusterng for Travelng Salesman Problem Jong-Won Yoon and Sung-Bae Cho Dept. of Computer Scence Yonse Unversty Seoul, Korea jwyoon@sclab.yonse.ac.r, sbcho@cs.yonse.ac.r

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

Classic Term Weighting Technique for Mining Web Content Outliers

Classic Term Weighting Technique for Mining Web Content Outliers Internatonal Conference on Computatonal Technques and Artfcal Intellgence (ICCTAI'2012) Penang, Malaysa Classc Term Weghtng Technque for Mnng Web Content Outlers W.R. Wan Zulkfel, N. Mustapha, and A. Mustapha

More information

High-Boost Mesh Filtering for 3-D Shape Enhancement

High-Boost Mesh Filtering for 3-D Shape Enhancement Hgh-Boost Mesh Flterng for 3-D Shape Enhancement Hrokazu Yagou Λ Alexander Belyaev y Damng We z Λ y z ; ; Shape Modelng Laboratory, Unversty of Azu, Azu-Wakamatsu 965-8580 Japan y Computer Graphcs Group,

More information

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z.

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z. TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS Muradalyev AZ Azerbajan Scentfc-Research and Desgn-Prospectng Insttute of Energetc AZ1012, Ave HZardab-94 E-mal:aydn_murad@yahoocom Importance of

More information

A Method of Query Expansion Based on Event Ontology

A Method of Query Expansion Based on Event Ontology A Method of Query Expanson Based on Event Ontology Zhaoman Zhong, Cunhua L, Yan Guan, Zongtan Lu A Method of Query Expanson Based on Event Ontology 1 Zhaoman Zhong, 1 Cunhua L, 1 Yan Guan, 2 Zongtan Lu,

More information

Intelligent Information Acquisition for Improved Clustering

Intelligent Information Acquisition for Improved Clustering Intellgent Informaton Acquston for Improved Clusterng Duy Vu Unversty of Texas at Austn duyvu@cs.utexas.edu Mkhal Blenko Mcrosoft Research mblenko@mcrosoft.com Prem Melvlle IBM T.J. Watson Research Center

More information

Discriminative Dictionary Learning with Pairwise Constraints

Discriminative Dictionary Learning with Pairwise Constraints Dscrmnatve Dctonary Learnng wth Parwse Constrants Humn Guo Zhuoln Jang LARRY S. DAVIS UNIVERSITY OF MARYLAND Nov. 6 th, Outlne Introducton/motvaton Dctonary Learnng Dscrmnatve Dctonary Learnng wth Parwse

More information

Assembler. Building a Modern Computer From First Principles.

Assembler. Building a Modern Computer From First Principles. Assembler Buldng a Modern Computer From Frst Prncples www.nand2tetrs.org Elements of Computng Systems, Nsan & Schocken, MIT Press, www.nand2tetrs.org, Chapter 6: Assembler slde Where we are at: Human Thought

More information

Collaboratively Regularized Nearest Points for Set Based Recognition

Collaboratively Regularized Nearest Points for Set Based Recognition Academc Center for Computng and Meda Studes, Kyoto Unversty Collaboratvely Regularzed Nearest Ponts for Set Based Recognton Yang Wu, Mchhko Mnoh, Masayuk Mukunok Kyoto Unversty 9/1/013 BMVC 013 @ Brstol,

More information

Recommended Items Rating Prediction based on RBF Neural Network Optimized by PSO Algorithm

Recommended Items Rating Prediction based on RBF Neural Network Optimized by PSO Algorithm Recommended Items Ratng Predcton based on RBF Neural Network Optmzed by PSO Algorthm Chengfang Tan, Cayn Wang, Yuln L and Xx Q Abstract In order to mtgate the data sparsty and cold-start problems of recommendaton

More information

Improving Web Image Search using Meta Re-rankers

Improving Web Image Search using Meta Re-rankers VOLUME-1, ISSUE-V (Aug-Sep 2013) IS NOW AVAILABLE AT: www.dcst.com Improvng Web Image Search usng Meta Re-rankers B.Kavtha 1, N. Suata 2 1 Department of Computer Scence and Engneerng, Chtanya Bharath Insttute

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual Machine Migration based on Trust Measurement of Computer Node Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on

More information

A Novel Distributed Collaborative Filtering Algorithm and Its Implementation on P2P Overlay Network*

A Novel Distributed Collaborative Filtering Algorithm and Its Implementation on P2P Overlay Network* A Novel Dstrbuted Collaboratve Flterng Algorthm and Its Implementaton on P2P Overlay Network* Peng Han, Bo Xe, Fan Yang, Jajun Wang, and Rumn Shen Department of Computer Scence and Engneerng, Shangha Jao

More information

Bridges and cut-vertices of Intuitionistic Fuzzy Graph Structure

Bridges and cut-vertices of Intuitionistic Fuzzy Graph Structure Internatonal Journal of Engneerng, Scence and Mathematcs (UGC Approved) Journal Homepage: http://www.jesm.co.n, Emal: jesmj@gmal.com Double-Blnd Peer Revewed Refereed Open Access Internatonal Journal -

More information

A New Approach For the Ranking of Fuzzy Sets With Different Heights

A New Approach For the Ranking of Fuzzy Sets With Different Heights New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays

More information

Behavioral Model Extraction of Search Engines Used in an Intelligent Meta Search Engine

Behavioral Model Extraction of Search Engines Used in an Intelligent Meta Search Engine Behavoral Model Extracton of Search Engnes Used n an Intellgent Meta Search Engne AVEH AVOUSI Computer Department, Azad Unversty, Garmsar Branch BEHZAD MOSHIRI Electrcal and Computer department, Faculty

More information

Machine Learning. Topic 6: Clustering

Machine Learning. Topic 6: Clustering Machne Learnng Topc 6: lusterng lusterng Groupng data nto (hopefully useful) sets. Thngs on the left Thngs on the rght Applcatons of lusterng Hypothess Generaton lusters mght suggest natural groups. Hypothess

More information

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis Internatonal Mathematcal Forum, Vol. 6,, no. 7, 8 Soltary and Travelng Wave Solutons to a Model of Long Range ffuson Involvng Flux wth Stablty Analyss Manar A. Al-Qudah Math epartment, Rabgh Faculty of

More information

Optimizing Document Scoring for Query Retrieval

Optimizing Document Scoring for Query Retrieval Optmzng Document Scorng for Query Retreval Brent Ellwen baellwe@cs.stanford.edu Abstract The goal of ths project was to automate the process of tunng a document query engne. Specfcally, I used machne learnng

More information

Face Recognition using 3D Directional Corner Points

Face Recognition using 3D Directional Corner Points 2014 22nd Internatonal Conference on Pattern Recognton Face Recognton usng 3D Drectonal Corner Ponts Xun Yu, Yongsheng Gao School of Engneerng Grffth Unversty Nathan, QLD, Australa xun.yu@grffthun.edu.au,

More information

An Iterative Implicit Feedback Approach to Personalized Search

An Iterative Implicit Feedback Approach to Personalized Search An Iteratve Implct Feedback Approach to Personalzed Search Yuanhua Lv 1, Le Sun 2, Junln Zhang 2, Jan-Yun Ne 3, Wan Chen 4, and We Zhang 2 1, 2 Insttute of Software, Chnese Academy of Scences, Beng, 100080,

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB V. Hotař, A. Hotař Techncal Unversty of Lberec, Department of Glass Producng Machnes and Robotcs, Department of Materal

More information

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1 4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:

More information