Using an Image-Text Parallel Corpus and the Web for Query Expansion in Cross-Language Image Retrieval

Size: px
Start display at page:

Download "Using an Image-Text Parallel Corpus and the Web for Query Expansion in Cross-Language Image Retrieval"

Transcription

1 Using an Image-Text Parallel Corpus and the Web for Query Expansion in Cross-Language Image Retrieval Yih-Chen Chang and Hsin-Hsi Chen * Department of Computer Science and Information Engineering National Taiwan University Taipei, Taiwan ycchang@nlg.csie.ntu.edu.tw, hhchen@csie.ntu.edu.tw Abstract. ImageCLEF2007 photo task is different from those of the previous years in two aspects. The caption field in the image annotations and the narrative field in the text queries are removed, and the example images in the visual queries are also removed from the image collection. In the new definition, the information that can be employed is less than before. Thus matching query words and annotations directly is not feasible. This paper explores the web to expand queries and documents. The experiments show that query expansion improves the performance 16.11%, however, document expansion brings in too much noise and the performance decreases 28.24%. The media mapping method based on an image-text parallel corpus is regarded as query expansion. The results of the formal runs show this method performs the best. Compared with the performance of the models without expansion, the MAP improves about 86.69%~143.12%. Integration of the external and the internal resources gains no benefits in the further experiments. 1 Introduction Image retrieval becomes more important since large scale image data are available on the web. In ImageCLEFphoto task, each topic, which is composed of a text query and a visual query, simulates the information need of users. In the previous years [1] [2], a text query includes topic and narrative fields in several different languages and a visual query includes two or three example images in the image data set. Each image in the image collection is annotated with title, location, date, notes and a detail caption. The task definitions of ImageCLEFphoto2007 [3] are changed in two aspects. First, the caption field in the image annotations and the narrative field in the queries are removed. These changes aim to reflect the information needs of the real world, i.e., image annotations and queries are usually short and rough. Second, the example images of the visual queries do not belong to the image collection. This change reflects that users may use their own photos as examples rather than images in the collection. When the caption field in the image annotation is removed, matching query words and image annotations becomes more challenging than before. We will explore an external resource, e.g., the web, to expand queries and documents. Through a web * Corresponding author. C. Peters et al. (Eds.): CLEF 2007, LNCS 5152, pp , Springer-Verlag Berlin Heidelberg 2008

2 Using an Image-Text Parallel Corpus and the Web for Query Expansion 505 search engine such as Google, we can retrieve relevant web pages, and use them for expansion. Compared with query expansion of using pseudo relevance feedback in the corpus, the outside resource may bring in information that the target corpus may not have. However, the information retrieved from the web may contain noise at the same time. How to filter out noise is an important issue. In this paper, we restrict the search space to some kinds of web sites, e.g., Wikipedia, and investigate if it is helpful for retrieval. In addition to external resources, we employ internal resources such as an imagetext parallel corpus, i.e., the target collection itself. Under such a trans-media corpus, two approaches say, media mapping [4] and a trans-media dictionary [5] were proposed before. Media mapping approach, which can be regarded as a kind of pseudo relevance feedback across different media, has better performance than trans-media dictionary approach. We will employ media mapping to ImageCLEFphoto 2007, examine its performance in the new definitions, and analyze if the integration of external and internal resources is helpful. This paper is organized as follows. Section 2 introduces the three methods we explore. Section 3 specifies official and unofficial runs we design. Section 4 shows and discusses the experiment results. Finally, we conclude the remarks in Section 5. 2 Methods Three methods including query (document) expansion using the web and query expansion with media mapping via a cross-media corpus are presented in the following subsections. 2.1 Query Expansion Using the Web Queries and image annotations are both short in ImageCLEFphoto In this situation, we plan to expand the given queries and get more information. Several previous experiments have shown that query expansion using pseudo relevance feedback is very useful in this task. In this paper, we employ outside resource like the web for query expansion and analyze if it can bring in useful information. The best way to access the web is through a web search engine like Google. We submit a text query to retrieve relevant web pages. Because the language of a text query may be different from the language of image annotations, we have to introduce the language translation mechanism. There are two alternative ways to deal with this problem. The first is to submit a text query to the web search engine directly and then to translate the retrieved web pages into target language. The second is to translate a text query into target language and then to submit the translated query to the web search engine. The drawback of the first approach (i.e., translation after retrieval) is the cost to translate all the web pages we get. In contrast, the translation cost of the second approach (i.e., translation before retrieval) is relatively low. However, when there are named entities in queries, the second approach may get wrong translation and thus the retrieved web pages may be unrelated to the original query. In the experiments, we adopt the approach of translation before retrieval. Next, we have to select words from the retrieved results to expand the given query. The selection mechanism can filter out noisy information, but it may also lose some useful

3 506 Y.-C. Chang and H.-H. Chen information. Here, we adopt the simplest way, i.e., to employ the top ranked snippets to expand our query. For the issue of noise, we limit the websites we access to encyclopedia-based ones, e.g., Wikipedia, by adding a web site name as an extra query term when submitting a query to a web search engine. 2.2 Document Expansion Using the Web Direct keyword matching may not be workable after query expansion if the relevant documents do not mention the words in the expanded query. There are two alternative ways to deal with this problem. First, we can expand a query with the words appearing in a document. Query expansion using relevance feedback belongs to this type. Second, we may expand the documents. In this paper, we explore the document expansion using the web. This method is similar to the one used in query expansion. We consider the title field of an image annotation as a query, and submit it to the web search engine to get the top ranked snippets to expand documents. Because documents are in target language, language translation is not necessary during document expansion. That is the major difference from query expansion. Although document expansion avoids translation errors, expanding too many words may introduce noise. In document expansion, we restrict the selection scope as follows. Only those words nearby the words in the title field of image annotations are considered as candidates. We set a window size (e.g., 5) in the experiments. Besides the above noise issue, document expansion has a logical problem. Assume the word animal is in title field of an image annotation. When we expand hyponym words such as tiger, cat, dog, etc., we do not know which animals are actually mentioned in that image. If the image talks about rabbit, the wrong expansion may introduce erroneous terms. 2.3 Media Mapping with an Image-Text Parallel Corpus Media mapping method [4][6] regards the target collection as an image-text parallel corpus, and employs such an intermedia to translate a visual query into a text one, and vise versa. The intermedia link two kinds of media (i.e., text and image) in this paper. Media mapping method can be seen as relevance feedback across different media and used in query expansion. In ImageCLEFphoto2006, we created a new query using media mapping and merged the results of the new query and the original visual query. In ImageCLEFphoto 2007, we regard the media mapping as query expansion in the following way. First, we submit a visual query to a content-based information retrieval (CBIR) system. Because images and the corresponding text annotations are parallelized in the collection, we then rerank the top n returned images by using a text query. Finally, the text annotations of the top m images are added to the original text query. We submit the expanded query to a text retrieval system and get the final result. We can compare the results of query expansion using the web and the media mapping with intermedia. In addition, we can examine the feasibility of the media mapping method in the new task definitions. There are two new challenges. First, retrieving the related images in the intermedia via visual query becomes harder. In the past, the visual queries are images in the image collection, so that they always appear

4 Using an Image-Text Parallel Corpus and the Web for Query Expansion 507 in the top of the returned images. Second, the caption field in an image annotation has been removed beforehand, so that the text information we can get from the image counterparts is less than the one in the tasks of previous years. We are interested in if the media mapping method is still workable in the new environment. 3 Experiments We submitted 27 official runs including 18 cross-lingual runs for eight different languages, 8 mono-lingual runs for three different languages, and 1 run for visual query only. All the queries with different source languages were translated into target language (e.g., English) using SYSTRAN system. We adopted Okapi with BM25 formula for text retrieval. The experiments consider the following issues. First, we want to check if the retrieved web pages can bring in new information for query expansion. We examine the expanded words when the recall is improved. Second, we compare the results of query expansion runs that limit or do not limit the web sites. Third, we want to check the effects that document expansion achieves. The runs using both query expansion and document expansion are also checked. Fourth, we examine the performance of media mapping method. Then, we employ both media mapping and the web for query expansion, and check if the web can bring in new information that media mapping cannot do. Some of the above issues are verified in the official runs, while some are done in the unofficial runs. Our official runs are described as follows. A run is named by the format Source- Language-TargetLanguage-Automatic-FeedBack-Media, where DE (German), ES (Spanish), EN (English), FR (French), JP (Japanese), RU (Russian), ZHT (Traditional Chinese), ZHS (Simplified Chinese), AUTO (Automatic), NOFB (No Feedback), TE (Document Expansion), FBQE (Feedback and Query Expansion), TXT (Text), IMG (Image), and TXTIMG (Text and Image) cross-lingual runs that use text query only, and do not consider query expansion: ES-EN-AUTO-NOFB-TXT, FR-EN-AUTO-NOFB-TXT, RU-EN-AUTO-NOFB-TXT, PT-EN-AUTO-NOFB-TXT, JA-EN-AUTO-NOFB-TXT, IT-EN-AUTO-NOFB-TXT, ZHT-EN-AUTO-NOFB-TXT, ZHS-EN-AUTO-NOFB-TXT 2. 3 mono-lingual runs that use text query only, and do not consider query expansion: EN-EN-AUTO-NOFB-TXT, ES-ES-AUTO-NOFB-TXT, DE-DE-AUTO-NOFB-TXT 3. 3 mono-lingual runs that adopt the media mapping method for query expansion: ES-ES-AUTO-FBQE-TXTIMG, EN-EN-AUTO-FBQE-TXTIMG, DE-DE-AUTO-FBQE-TXTIMG 4. 8 cross-lingual runs that use the media mapping method for query expansion: PT-EN-AUTO-FBQE-TXTIMG, ES-EN-AUTO-FBQE-TXTIMG, RU-EN-AUTO-FBQE-TXTIMG, IT-EN-AUTO-FBQE-TXTIMG, ZHT-EN-AUTO-FBQE-TXTIMG, ZHS-EN-AUTO-FBQE-TXTIMG, JA-EN-AUTO-FBQE-TXTIMG, FR-EN-AUTO-FBQE-TXTIMG 5. 2 runs that expand query with the web, but do not consider document expansion: EN-EN-AUTO-QE-TXT-TOPIC, ZHT-EN-AUTO-QE-TXT-TOPIC 6. 2 runs that expand document with the web, but do not consider query expansion: EN-EN-AUTO-TE-TXT-CAPTION, ZHT-EN-AUTO-TE-TXT-CAPTION

5 508 Y.-C. Chang and H.-H. Chen 7. 1 run that use visual query and the media mapping method only: IMG-EN-AUTO-FB-TXTIMG Some unofficial runs are described as follows runs that consider both query expansion and document expansion: EN-EN-AUTO-TE-QE-TXT, ZHT-EN-AUTO-TE-QE-TXT 2. 2 runs that expand query with the web and limit the search space: EN-EN-AUTO-QE-WIKI-TXT, ZHT-EN-AUTO-QE-WIKI-TXT 3. 2 runs that use both the web and the media mapping for query expansion: EN-EN-AUTO-QE-FBQE-TXTIMG, ZHT-EN-AUTO-QE-FBQE-TXTIMG. 4 Results and Discussions In the first set of experiments, we use the top one snippet returned by Google to expand the text queries. Table 1 shows the results of runs EN-EN-AUTO-QE-TXT-TOPIC, ZHT-EN-AUTO-QE-TXT-TOPIC, EN-EN-AUTO-NOFB-TXT, and ZHT-EN-AUTO- NOFB-TXT. In both cross-lingual and mono-lingual cases, the performance of systems with query expansion is better than that without query expansion. After expansion, both recall and precision are improved. In the original expectation, precision is decreased since we do not apply any strategies to filter noise. Table 1. Results of models with/without query expansion Query Language- Document Language Evaluation Metric Query Expansion Using the Web Query Without Expansion Traditional Chinese- MAP ( %) English Recall ( %) English-English MAP (+7.57 %) Recall (+14.84%) In the second set of experiments, we compare the results of query expansion with and without limiting the search space. Table 2 shows that the performance does not change very much after restricting the web sites for cross-lingual retrieval. The performance even has a little decrease in mono-lingual runs. We find that restrictive access may retrieve unrelated pages in some cases. The third set of experiments aims to evaluate the effects of document expansion. Table 3 summarizes the results. Document expansion does not take positive effects. In both cross-lingual and mono-lingual runs, recall and MAP are decreased when document expansion is introduced no matter whether query expansion is employed or not. The major reason may be that the strategy brings in too much noise. The fourth set of experiments examines the performance of the media mapping method in the new definitions. The results are shown in Table 4. Total 8 cross-lingual runs and 3 mono-lingual runs are tested. Media mapping achieves very good performance. Compared with the performance of the models without expansion, the MAP improves about 86.69%~143.12%. In last year, media mapping improves the performance about 71%~119%. This result shows that media mapping method is robust under different task definitions.

6 Using an Image-Text Parallel Corpus and the Web for Query Expansion 509 Table 2. Results of models with and without limiting the search space Run Name (cross-lingual/mono-lingual) Limitation Recall MAP ZHT-EN-AUTO-QE-TXT-TOPIC (cross-lingual) No ZHT-EN-AUTO-QE-WIKI-TXT (cross-lingual) Yes EN-EN-AUTO-QE-TXT-TOPIC (mono-lingual) No EN-EN-AUTO-QE-WIKI-TXT English (mono-lingual) Yes Table 3. Results of models using or not using document expansion Runs Name (cross-lingual/mono-lingual) Document Query Recall MAP Expansion Expansion ZHT-EN-AUTO-NOFB-TXT (cross) No No ZHT-EN-AUTO-TE-TXT-CAPTION (cross) Yes No ZHT-EN-AUTO-QE-TXT-TOPIC (cross) No Yes ZHT-EN-AUTO-TE-QE-TXT (cross) Yes Yes EN-EN-AUTO-NOFB-TXT (mono) No No EN-EN-AUTO-TE-TXT-CAPTION (mono) Yes No EN-EN-AUTO-QE-TXT-TOPIC (mono) No Yes EN-EN-AUTO-TE-QE-TXT (mono) Yes Yes Table 4. Results of using the media mapping as query expansion Query Language- Document Language Traditional Chinese-English Simplified Chinese-English Portuguese-English Spanish-English Russian-English Italian-English French-English Japanese-English English-English Spanish-Spanish German-German Metric Query Expansion using Media Mapping Without Expansion MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %) MAP ( %) Recall ( %)

7 510 Y.-C. Chang and H.-H. Chen Tables 1 and 4 conclude that media mapping with an image-text parallel corpus and query expansion using the web are very useful, and the former is better than the latter. The last set of experiments checks if integrating the internal and the external resources gets better performance. Table 5 shows that such an integration does not have positive effects. MAP is decreased when the web is used. It may be due to that the external resource (i.e., the web) has more noise than the internal resource (i.e., the image-text parallel corpus). Table 5. Results of the models using both media mapping and the web Run Media Mapping the Web Recall MAP ZHT-EN-AUTO-FBQE-TXTIMG Yes No ZHT-EN-AUTO-QE-FBQE-TXTIMG Yes Yes EN-EN-AUTO-FBQE-TXTIMG Yes No EN-EN-AUTO-QE-FBQE-TXTIMG Yes Yes In the above sets of experiments, we compare the performance of different kinds of approaches. Media mapping with an image-text parallel corpus is the best of all. Table 6 summarizes the ranks of our official runs with media mapping approach in Image- CLEFphoto2007. Each row lists the language pair, total submitted runs and the rank of our runs. Compared with the runs of different participants, media mapping approach performs quite well in different language pairs. Except English mono-lingual and Simplified Chinese-English cross-lingual runs, our system ranks number 1 in the rest of official runs we submitted. That shows the robustness of our media mapping approach in integrating text and visual information. Table 6. Ranks of official runs using media mapping approach in ImageCLEFphoto2007 Mono-Lingual Run/Cross-Lingual Run Total Submitted Runs Rank English English German German 30 1 Spanish Spanish 15 1 Simplified Chinese English 23 2 Tradition Chinese English 1 1 French English 21 1 Italian English 10 1 Japanese English 6 1 Portuguese English 9 1 Russian English 6 1 Spanish English Conclusion This paper explores the use of the web for query and document expansion. The experiments show that the named entities expanded from the web are useful. Limiting the search web sites to Wikipedia seems not to improve the performance and may filter out some related webs. Document expansion brings in too much noise, so that

8 Using an Image-Text Parallel Corpus and the Web for Query Expansion 511 the performance decreases 28.24%. Regarding media mapping as query expansion improves the retrieval performance very much. It shows the robustness of media mapping method even the new task definition is more challenging than before. Integrating both the web and an image-text parallel corpus for query expansion cannot improve the performance. Acknowledgments. Research of this paper was partially supported by National Science Council, Taiwan, and Excellent Research Projects of National Taiwan University, under the contracts E and 96R0062-AE References 1. Clough, P., Sanderson, M., Müller, H.: The CLEF 2004 Cross-Language Image Retrieval Track. In: Peters, C., Clough, P., Gonzalo, J., Jones, G.J.F., Kluck, M., Magnini, B. (eds.) CLEF LNCS, vol. 3491, pp Springer, Heidelberg (2005) 2. Clough, P., Müller, H., Deselaers, T., Grubinger, M., Lehmann, T.M., Jensen, J., Hersh, W.: The CLEF 2005 Cross-Language Image Retrieval Track. In: Peters, C., Clough, P., Gonzalo, J., Jones, G., Kluck, M., Magnini, B. (eds.) CLEF LNCS, vol. 4022, pp Springer, Heidelberg (2006) 3. Grubinger, M., Clough, P., Hanbury, A., Müller, H.: Overview of the ImageCLEFphoto 2007 Photographic Retrieval Task. In: Nardi, A., Peters, C. (eds.) Working Notes of the 2007 CLEF Workshop (2007) 4. Chang, Y.C., Chen, H.H.: Approaches of Using a Word-Image Ontology and an Annotated Image Corpus as Intermedia for Cross-Language Image Retrieval. In: Peters, C., Clough, P., Gey, F.C., Karlgren, J., Magnini, B., Oard, D.W., de Rijke, M., Stempfhuber, M. (eds.) CLEF LNCS, vol. 4730, pp Springer, Heidelberg (2007) 5. Lin, W.C., Chang, Y.C., Chen, H.H.: Integrating Textual and Visual Information for Cross- Language Image Retrieval: A Trans-Media Dictionary Approach. Information Processing and Management 43, (2007) 6. Chen, H.H., Chang, Y.C.: Language Translation and Media Transformation in Cross- Language Image Retrieval. In: Sugimoto, S., Hunter, J., Rauber, A., Morishima, A. (eds.) ICADL LNCS, vol. 4312, pp Springer, Heidelberg (2006)

Experiment for Using Web Information to do Query and Document Expansion

Experiment for Using Web Information to do Query and Document Expansion Experiment for Using Web Information to do Query and Document Expansion Yih-Chen Chang and Hsin-Hsi Chen * Department of Computer Science and Information Engineering National Taiwan University Taipei,

More information

Evaluation of Automatically Assigned MeSH Terms for Retrieval of Medical Images

Evaluation of Automatically Assigned MeSH Terms for Retrieval of Medical Images Evaluation of Automatically Assigned MeSH Terms for Retrieval of Medical Images Miguel E. Ruiz 1 and Aurélie Névéol 2 1 University of North Texas, School of Library and Information Sciences P.O. Box 311068,

More information

A fully-automatic approach to answer geographic queries: GIRSA-WP at GikiP

A fully-automatic approach to answer geographic queries: GIRSA-WP at GikiP A fully-automatic approach to answer geographic queries: at GikiP Johannes Leveling Sven Hartrumpf Intelligent Information and Communication Systems (IICS) University of Hagen (FernUniversität in Hagen)

More information

Trans-Media Pseudo-Relevance Feedback Methods in Multimedia Retrieval

Trans-Media Pseudo-Relevance Feedback Methods in Multimedia Retrieval Trans-Media Pseudo-Relevance Feedback Methods in Multimedia Retrieval Stephane Clinchant, Jean-Michel Renders, and Gabriela Csurka Xerox Research Centre Europe, 6 ch. de Maupertuis, 38240 Meylan, France

More information

Overview of the ImageCLEFphoto 2007 Photographic Retrieval Task

Overview of the ImageCLEFphoto 2007 Photographic Retrieval Task Overview of the ImageCLEFphoto 2007 Photographic Retrieval Task Michael Grubinger 1,PaulClough 2, Allan Hanbury 3, and Henning Müller 4,5 1 Victoria University, Melbourne, Australia 2 Sheffield University,

More information

Clustering for Text and Image-Based Photo Retrieval at CLEF 2009

Clustering for Text and Image-Based Photo Retrieval at CLEF 2009 Clustering for ext and mage-based Photo Retrieval at CLEF 2009 Qian Zhu and Diana nkpen School of nformation echnology and Engineering University of Ottawa qzhu012@uottawa.ca, diana@site.uottawa.ca Abstract.

More information

Image Query Expansion Using Semantic Selectional Restrictions

Image Query Expansion Using Semantic Selectional Restrictions Image Query Expansion Using Semantic Selectional Restrictions Osama El Demerdash, Sabine Bergler and Leila Kosseim Concordia University {osama el,bergler,kosseim}@cse.concordia.ca CLaC Laboratory - Department

More information

Using XML Logical Structure to Retrieve (Multimedia) Objects

Using XML Logical Structure to Retrieve (Multimedia) Objects Using XML Logical Structure to Retrieve (Multimedia) Objects Zhigang Kong and Mounia Lalmas Queen Mary, University of London {cskzg,mounia}@dcs.qmul.ac.uk Abstract. This paper investigates the use of the

More information

Medical Image Annotation in ImageCLEF 2008

Medical Image Annotation in ImageCLEF 2008 Medical Image Annotation in ImageCLEF 2008 Thomas Deselaers 1 and Thomas M. Deserno 2 1 RWTH Aachen University, Computer Science Department, Aachen, Germany 2 RWTH Aachen University, Dept. of Medical Informatics,

More information

The CLEF 2005 Cross-Language Image Retrieval Track

The CLEF 2005 Cross-Language Image Retrieval Track The CLEF 2005 Cross-Language Image Retrieval Track Organised by Paul Clough, Henning Müller, Thomas Deselaers, Michael Grubinger, Thomas Lehmann, Jeffery Jensen and William Hersh Overview Image Retrieval

More information

MIRACLE at ImageCLEFmed 2008: Evaluating Strategies for Automatic Topic Expansion

MIRACLE at ImageCLEFmed 2008: Evaluating Strategies for Automatic Topic Expansion MIRACLE at ImageCLEFmed 2008: Evaluating Strategies for Automatic Topic Expansion Sara Lana-Serrano 1,3, Julio Villena-Román 2,3, José C. González-Cristóbal 1,3 1 Universidad Politécnica de Madrid 2 Universidad

More information

Overview of the ImageCLEF 2006 Photographic Retrieval and Object Annotation Tasks

Overview of the ImageCLEF 2006 Photographic Retrieval and Object Annotation Tasks Overview of the ImageCLEF 2006 Photographic Retrieval and Object Annotation Tasks Paul Clough 1, Michael Grubinger 2, Thomas Deselaers 3, Allan Hanbury 4, Henning Müller 5 1 Sheffield University, Sheffield,

More information

CLEF-IP 2009: Exploring Standard IR Techniques on Patent Retrieval

CLEF-IP 2009: Exploring Standard IR Techniques on Patent Retrieval DCU @ CLEF-IP 2009: Exploring Standard IR Techniques on Patent Retrieval Walid Magdy, Johannes Leveling, Gareth J.F. Jones Centre for Next Generation Localization School of Computing Dublin City University,

More information

NTUBROWS System for NTCIR-7. Information Retrieval for Question Answering

NTUBROWS System for NTCIR-7. Information Retrieval for Question Answering NTUBROWS System for NTCIR-7 Information Retrieval for Question Answering I-Chien Liu, Lun-Wei Ku, *Kuang-hua Chen, and Hsin-Hsi Chen Department of Computer Science and Information Engineering, *Department

More information

A Text-Based Approach to the ImageCLEF 2010 Photo Annotation Task

A Text-Based Approach to the ImageCLEF 2010 Photo Annotation Task A Text-Based Approach to the ImageCLEF 2010 Photo Annotation Task Wei Li, Jinming Min, Gareth J. F. Jones Center for Next Generation Localisation School of Computing, Dublin City University Dublin 9, Ireland

More information

krones Academy - media suite User guide

krones Academy - media suite User guide krones Academy - media suite User guide krones Academy Beispieltext media suite Login. Enter the following website address in the Internet Explorer: http://academy.krones.com. Enter login name and password.

More information

External Query Reformulation for Text-based Image Retrieval

External Query Reformulation for Text-based Image Retrieval External Query Reformulation for Text-based Image Retrieval Jinming Min and Gareth J. F. Jones Centre for Next Generation Localisation School of Computing, Dublin City University Dublin 9, Ireland {jmin,gjones}@computing.dcu.ie

More information

Wikipedia Retrieval Task ImageCLEF 2011

Wikipedia Retrieval Task ImageCLEF 2011 Wikipedia Retrieval Task ImageCLEF 2011 Theodora Tsikrika University of Applied Sciences Western Switzerland, Switzerland Jana Kludas University of Geneva, Switzerland Adrian Popescu CEA LIST, France Outline

More information

Applying the KISS Principle for the CLEF- IP 2010 Prior Art Candidate Patent Search Task

Applying the KISS Principle for the CLEF- IP 2010 Prior Art Candidate Patent Search Task Applying the KISS Principle for the CLEF- IP 2010 Prior Art Candidate Patent Search Task Walid Magdy, Gareth J.F. Jones Centre for Next Generation Localisation School of Computing Dublin City University,

More information

Multilingual Image Search from a user s perspective

Multilingual Image Search from a user s perspective Multilingual Image Search from a user s perspective Julio Gonzalo, Paul Clough, Jussi Karlgren QUAERO-Image CLEF workshop, 16/09/08 Finding is a matter of two fast stupid smart slow great potential for

More information

QUICK REFERENCE GUIDE: SHELL SUPPLIER PROFILE QUESTIONNAIRE (SPQ)

QUICK REFERENCE GUIDE: SHELL SUPPLIER PROFILE QUESTIONNAIRE (SPQ) QUICK REFERENCE GUIDE: SHELL SUPPLIER PROFILE QUESTIONNAIRE (SPQ) July 2018 July 2018 1 SPQ OVERVIEW July 2018 2 WHAT IS THE SHELL SUPPLIER PROFILE QUESTIONNAIRE? Shell needs all potential and existing

More information

University of Santiago de Compostela at CLEF-IP09

University of Santiago de Compostela at CLEF-IP09 University of Santiago de Compostela at CLEF-IP9 José Carlos Toucedo, David E. Losada Grupo de Sistemas Inteligentes Dept. Electrónica y Computación Universidad de Santiago de Compostela, Spain {josecarlos.toucedo,david.losada}@usc.es

More information

Overview of the ImageCLEFphoto 2008 Photographic Retrieval Task

Overview of the ImageCLEFphoto 2008 Photographic Retrieval Task Overview of the ImageCLEFphoto 2008 Photographic Retrieval Task Thomas Arni 1, Paul Clough 1, Mark Sanderson 1 and Michael Grubinger 2 1 Department of Information Studies, University of Sheffield, UK 2

More information

Understanding the Query: THCIB and THUIS at NTCIR-10 Intent Task. Junjun Wang 2013/4/22

Understanding the Query: THCIB and THUIS at NTCIR-10 Intent Task. Junjun Wang 2013/4/22 Understanding the Query: THCIB and THUIS at NTCIR-10 Intent Task Junjun Wang 2013/4/22 Outline Introduction Related Word System Overview Subtopic Candidate Mining Subtopic Ranking Results and Discussion

More information

A Practical Passage-based Approach for Chinese Document Retrieval

A Practical Passage-based Approach for Chinese Document Retrieval A Practical Passage-based Approach for Chinese Document Retrieval Szu-Yuan Chi 1, Chung-Li Hsiao 1, Lee-Feng Chien 1,2 1. Department of Information Management, National Taiwan University 2. Institute of

More information

Patent Terminlogy Analysis: Passage Retrieval Experiments for the Intellecutal Property Track at CLEF

Patent Terminlogy Analysis: Passage Retrieval Experiments for the Intellecutal Property Track at CLEF Patent Terminlogy Analysis: Passage Retrieval Experiments for the Intellecutal Property Track at CLEF Julia Jürgens, Sebastian Kastner, Christa Womser-Hacker, and Thomas Mandl University of Hildesheim,

More information

Searching and Organizing Images Across Languages

Searching and Organizing Images Across Languages Searching and Organizing Images Across Languages Paul Clough University of Sheffield Western Bank Sheffield, UK +44 114 222 2664 p.d.clough@sheffield.ac.uk Mark Sanderson University of Sheffield Western

More information

Integrating textual and visual information for cross-language image retrieval: A trans-media dictionary approach

Integrating textual and visual information for cross-language image retrieval: A trans-media dictionary approach Information Processing and Management 43 (2007) 488 502 www.elsevier.com/locate/infoproman Integrating textual and visual information for cross-language image retrieval: A trans-media dictionary approach

More information

Comment Extraction from Blog Posts and Its Applications to Opinion Mining

Comment Extraction from Blog Posts and Its Applications to Opinion Mining Comment Extraction from Blog Posts and Its Applications to Opinion Mining Huan-An Kao, Hsin-Hsi Chen Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan

More information

LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES

LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES Bo-ren Bai 1, Berlin Chen 2, Hsin-min Wang 2, Lee-feng Chien 2, and Lin-shan Lee 1,2 1 Department of Electrical

More information

Run on Earth User Guide

Run on Earth User Guide Run on Earth User Guide Run on Earth User Guide Outline 1. Connect Device to a PAFERS Enabled Fitness Machine 1. 30-pin fitness machine ios only 2. Bluetooth fitness machine - ios 3. Bluetooth fitness

More information

Multi-Modal Interactive Approach to ImageCLEF 2007 Photographic and Medical Retrieval Tasks by CINDI

Multi-Modal Interactive Approach to ImageCLEF 2007 Photographic and Medical Retrieval Tasks by CINDI Multi-Modal Interactive Approach to ImageCLEF 2007 Photographic and Medical Retrieval Tasks by CINDI M. M. Rahman, Bipin C. Desai, Prabir Bhattacharya Dept. of Computer Science & Software Engineering,

More information

ImageCLEF 2008: visual feature analysis in segmented images

ImageCLEF 2008: visual feature analysis in segmented images SZTAKI @ ImageCLEF 2008: visual feature analysis in segmented images Bálint Daróczy Zsolt Fekete Mátyás Brendel Simon Rácz András Benczúr Dávid Siklósi Attila Pereszlényi Data Mining and Web search Research

More information

Semantic Annotation of Web Resources Using IdentityRank and Wikipedia

Semantic Annotation of Web Resources Using IdentityRank and Wikipedia Semantic Annotation of Web Resources Using IdentityRank and Wikipedia Norberto Fernández, José M.Blázquez, Luis Sánchez, and Vicente Luque Telematic Engineering Department. Carlos III University of Madrid

More information

Google Search Appliance

Google Search Appliance Google Search Appliance Search Appliance Internationalization Google Search Appliance software version 7.2 and later Google, Inc. 1600 Amphitheatre Parkway Mountain View, CA 94043 www.google.com GSA-INTL_200.01

More information

Query Expansion from Wikipedia and Topic Web Crawler on CLIR

Query Expansion from Wikipedia and Topic Web Crawler on CLIR Query Expansion from Wikipedia and Topic Web Crawler on CLIR Meng-Chun Lin, Ming-Xiang Li, Chih-Chuan Hsu and Shih-Hung Wu* Department of Computer Science and Information Engineering Chaoyang University

More information

CACAO PROJECT AT THE 2009 TASK

CACAO PROJECT AT THE 2009 TASK CACAO PROJECT AT THE TEL@CLEF 2009 TASK Alessio Bosca, Luca Dini Celi s.r.l. - 10131 Torino - C. Moncalieri, 21 alessio.bosca, dini@celi.it Abstract This paper presents the participation of the CACAO prototype

More information

MSRA Columbus at GeoCLEF 2006

MSRA Columbus at GeoCLEF 2006 MSRA Columbus at GeoCLEF 2006 Zhisheng Li, Chong Wang 2, Xing Xie 2, Wei-Ying Ma 2 Department of Computer Science, University of Sci. & Tech. of China, Hefei, Anhui, 230026, P.R. China zsli@mail.ustc.edu.cn

More information

From CLIR to CLIE: Some Lessons in NTCIR Evaluation

From CLIR to CLIE: Some Lessons in NTCIR Evaluation From CLIR to CLIE: Some Lessons in NTCIR Evaluation Hsin-Hsi Chen Department of Computer Science and Information Engineering National Taiwan University Taipei, Taiwan +886-2-33664888 ext 311 hhchen@csie.ntu.edu.tw

More information

ImageCLEF 2008 Bálint Daróczy

ImageCLEF 2008 Bálint Daróczy SZTAKI @ ImageCLEF 2008 Bálint Daróczy joint work with András Benczúr, Mátyás Brendel, Zsolt Fekete, Attila Pereszlényi, Simon Rácz, Dávid Siklósi Data Mining and Web Search Group Computer and Automation

More information

Evaluating a Conceptual Indexing Method by Utilizing WordNet

Evaluating a Conceptual Indexing Method by Utilizing WordNet Evaluating a Conceptual Indexing Method by Utilizing WordNet Mustapha Baziz, Mohand Boughanem, Nathalie Aussenac-Gilles IRIT/SIG Campus Univ. Toulouse III 118 Route de Narbonne F-31062 Toulouse Cedex 4

More information

Content-Based Image Retrieval with LIRe and SURF on a Smartphone-Based Product Image Database

Content-Based Image Retrieval with LIRe and SURF on a Smartphone-Based Product Image Database Content-Based Image Retrieval with LIRe and SURF on a Smartphone-Based Product Image Database Kai Chen 1 and Jean Hennebert 2 1 University of Fribourg, DIVA-DIUF, Bd. de Pérolles 90, 1700 Fribourg, Switzerland

More information

Cross Lingual Question Answering using CINDI_QA for 2007

Cross Lingual Question Answering using CINDI_QA for 2007 Cross Lingual Question Answering using CINDI_QA for QA@CLEF 2007 Chedid Haddad, Bipin C. Desai Department of Computer Science and Software Engineering Concordia University 1455 De Maisonneuve Blvd. W.

More information

Document Expansion for Text-based Image Retrieval at CLEF 2009

Document Expansion for Text-based Image Retrieval at CLEF 2009 Document Expansion for Text-based Image Retrieval at CLEF 2009 Jinming Min, Peter Wilkins, Johannes Leveling, and Gareth Jones Centre for Next Generation Localisation School of Computing, Dublin City University

More information

Cross-Language Retrieval with Wikipedia

Cross-Language Retrieval with Wikipedia Cross-Language Retrieval with Wikipedia Péter Schönhofen, András Benczúr, István Bíró, and Károly Csalogány Data Mining and Web search Research Group, Informatics Laboratory Computer and Automation Research

More information

Open Archive Toulouse Archive Ouverte

Open Archive Toulouse Archive Ouverte Open Archive Toulouse Archive Ouverte OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible This is an author s version

More information

Experiments with Automatic Query Formulation in the Extended Boolean Model

Experiments with Automatic Query Formulation in the Extended Boolean Model Experiments with Automatic Query Formulation in the Extended Boolean Model Lucie Skorkovská and Pavel Ircing University of West Bohemia, Faculty of Applied Sciences, Dept. of Cybernetics Univerzitní 8,

More information

WikiTranslate: Query Translation for Cross-Lingual Information Retrieval Using Only Wikipedia

WikiTranslate: Query Translation for Cross-Lingual Information Retrieval Using Only Wikipedia WikiTranslate: Query Translation for Cross-Lingual Information Retrieval Using Only Wikipedia Dong Nguyen, Arnold Overwijk, Claudia Hauff, Dolf R.B. Trieschnigg, Djoerd Hiemstra, and Franciska M.G. de

More information

Medical Image Annotation in ImageCLEF 2008

Medical Image Annotation in ImageCLEF 2008 Medical Image Annotation in ImageCLEF 2008 Thomas Deselaers 1 and Thomas M. Deserno 2 1 RWTH Aachen University, Computer Science Department, Aachen, Germany deselaers@cs.rwth-aachen.de 2 RWTH Aachen University,

More information

Cross-Language Evaluation Forum - CLEF

Cross-Language Evaluation Forum - CLEF Cross-Language Evaluation Forum - CLEF Carol Peters IEI-CNR, Pisa, Italy IST-2000-31002 Kick-off: October 2001 Outline Project Objectives Background CLIR System Evaluation CLEF Infrastructure Results so

More information

BUILDING CORPORA OF TRANSCRIBED SPEECH FROM OPEN ACCESS SOURCES

BUILDING CORPORA OF TRANSCRIBED SPEECH FROM OPEN ACCESS SOURCES BUILDING CORPORA OF TRANSCRIBED SPEECH FROM OPEN ACCESS SOURCES O.O. Iakushkin a, G.A. Fedoseev, A.S. Shaleva, O.S. Sedova Saint Petersburg State University, 7/9 Universitetskaya nab., St. Petersburg,

More information

Overview of the ImageCLEFphoto 2007 photographic retrieval task

Overview of the ImageCLEFphoto 2007 photographic retrieval task Overview of the ImageCLEFphoto 2007 photographic retrieval task Michael Grubinger 1, Paul Clough 2, Allan Hanbury 3, Henning Müller 4 1 Victoria University, Melbourne, Australia 2 Sheffield University,

More information

Overview of WebCLEF 2007

Overview of WebCLEF 2007 Overview of WebCLEF 2007 Valentin Jijkoun Maarten de Rijke ISLA, University of Amsterdam jijkoun,mdr@science.uva.nl Abstract This paper describes the WebCLEF 2007 task. The task definition which goes beyond

More information

Evaluation and image retrieval

Evaluation and image retrieval Evaluation and image retrieval Henning Müller Thomas Deselaers Overview Information retrieval evaluation TREC Multimedia retrieval evaluation TRECVID, ImageEval, Benchathlon, ImageCLEF Past Future Information

More information

Document Structure Analysis in Associative Patent Retrieval

Document Structure Analysis in Associative Patent Retrieval Document Structure Analysis in Associative Patent Retrieval Atsushi Fujii and Tetsuya Ishikawa Graduate School of Library, Information and Media Studies University of Tsukuba 1-2 Kasuga, Tsukuba, 305-8550,

More information

SIMATIC. Industrial PC Microsoft Windows 7. Safety instructions 1. Initial startup: Commissioning the operating. system

SIMATIC. Industrial PC Microsoft Windows 7. Safety instructions 1. Initial startup: Commissioning the operating. system Safety instructions 1 Initial startup: Commissioning the operating 2 system SIMATIC Industrial PC Operating Instructions Restoring the factory settings of the operating system and 3 partitions (Restore)

More information

TCD-DCU at 2009: Document Expansion, Query Translation and Language Modeling

TCD-DCU at 2009: Document Expansion, Query Translation and Language Modeling TCD-DCU at TEL@CLEF 2009: Document Expansion, Query Translation and Language Modeling Johannes Leveling 1, Dong Zhou 2, Gareth F. Jones 1, and Vincent Wade 2 1 Centre for Next Generation Localisation School

More information

IPL at ImageCLEF 2010

IPL at ImageCLEF 2010 IPL at ImageCLEF 2010 Alexandros Stougiannis, Anestis Gkanogiannis, and Theodore Kalamboukis Information Processing Laboratory Department of Informatics Athens University of Economics and Business 76 Patission

More information

MetaMoJi Share for Business Ver. 2 MetaMoJi Note for Business Ver. 2 Installation and Operation Guide

MetaMoJi Share for Business Ver. 2 MetaMoJi Note for Business Ver. 2 Installation and Operation Guide MetaMoJi Share for Business Ver. 2 MetaMoJi Note for Business Ver. 2 Installation and Operation Guide First Edition - ios is a trademark or registered trademark of Cisco in the U.S. and other countries

More information

IPAL at CLEF 2008: Mixed-Modality based Image Search, Novelty based Re-ranking and Extended Matching

IPAL at CLEF 2008: Mixed-Modality based Image Search, Novelty based Re-ranking and Extended Matching IPAL at CLEF 2008: Mixed-Modality based Image Search, Novelty based Re-ranking and Extended Matching Sheng Gao, Jean-Pierre Chevallet and Joo-Hwee Lim IPAL, Institute for Infocomm Research, A*Star, Singapore

More information

FAO TERM PORTAL User s Guide

FAO TERM PORTAL User s Guide FAO TERM PORTAL User s Guide February 2016 Table of contents 1. Introduction to the FAO Term Portal... 3 2. Home Page description... 4 3. How to search for a term... 6 4. Results view... 8 5. Entry Details

More information

GoNTogle: A Tool for Semantic Annotation and Search

GoNTogle: A Tool for Semantic Annotation and Search GoNTogle: A Tool for Semantic Annotation and Search Giorgos Giannopoulos 1,2, Nikos Bikakis 1,2, Theodore Dalamagas 2, and Timos Sellis 1,2 1 KDBSL Lab, School of ECE, Nat. Tech. Univ. of Athens, Greece

More information

ResPubliQA 2010

ResPubliQA 2010 SZTAKI @ ResPubliQA 2010 David Mark Nemeskey Computer and Automation Research Institute, Hungarian Academy of Sciences, Budapest, Hungary (SZTAKI) Abstract. This paper summarizes the results of our first

More information

HUKB at NTCIR-12 IMine-2 task: Utilization of Query Analysis Results and Wikipedia Data for Subtopic Mining

HUKB at NTCIR-12 IMine-2 task: Utilization of Query Analysis Results and Wikipedia Data for Subtopic Mining HUKB at NTCIR-12 IMine-2 task: Utilization of Query Analysis Results and Wikipedia Data for Subtopic Mining Masaharu Yoshioka Graduate School of Information Science and Technology, Hokkaido University

More information

Large-Scale Interactive Evaluation of Multilingual Information Access Systems the iclef Flickr Challenge

Large-Scale Interactive Evaluation of Multilingual Information Access Systems the iclef Flickr Challenge Large-Scale Interactive Evaluation of Multilingual Information Access Systems the iclef Flickr Challenge 1 Paul Clough, 2 Julio Gonzalo, 3 Jussi Karlgren, 1 Emma Barker, 2 Javier Artiles, 2 Victor Peinado

More information

indexing and query processing. The inverted le was constructed for the retrieval target collection which contains full texts of two years' Japanese pa

indexing and query processing. The inverted le was constructed for the retrieval target collection which contains full texts of two years' Japanese pa Term Distillation in Patent Retrieval Hideo Itoh Hiroko Mano Yasushi Ogawa Software R&D Group, RICOH Co., Ltd. 1-1-17 Koishikawa, Bunkyo-ku, Tokyo 112-0002, JAPAN fhideo,mano,yogawag@src.ricoh.co.jp Abstract

More information

CIRGDISCO at RepLab2012 Filtering Task: A Two-Pass Approach for Company Name Disambiguation in Tweets

CIRGDISCO at RepLab2012 Filtering Task: A Two-Pass Approach for Company Name Disambiguation in Tweets CIRGDISCO at RepLab2012 Filtering Task: A Two-Pass Approach for Company Name Disambiguation in Tweets Arjumand Younus 1,2, Colm O Riordan 1, and Gabriella Pasi 2 1 Computational Intelligence Research Group,

More information

CriES 2010

CriES 2010 CriES Workshop @CLEF 2010 Cross-lingual Expert Search - Bridging CLIR and Social Media Institut AIFB Forschungsgruppe Wissensmanagement (Prof. Rudi Studer) Organizing Committee: Philipp Sorg Antje Schultz

More information

PKU at ImageCLEF 2008: Experiments with Query Extension Techniques. for Text-Base and Content-Based Image Retrieval

PKU at ImageCLEF 2008: Experiments with Query Extension Techniques. for Text-Base and Content-Based Image Retrieval PKU at ImageCLEF 2008: Experiments with Query Extension Techniques for Text-Base and Content-Based Image Retrieval Zhi Zhou 1,2, Yonghong Tian 2, Yuanning Li 1,2, Ting Liu 1,2, Tiejun Huang 2, Wen Gao

More information

Task 3 Patient-Centred Information Retrieval: Team CUNI

Task 3 Patient-Centred Information Retrieval: Team CUNI Task 3 Patient-Centred Information Retrieval: Team CUNI Shadi Saleh and Pavel Pecina Charles University Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics, Czech Republic {saleh,pecina}@ufal.mff.cuni.cz

More information

3 Publishing Technique

3 Publishing Technique Publishing Tool 32 3 Publishing Technique As discussed in Chapter 2, annotations can be extracted from audio, text, and visual features. The extraction of text features from the audio layer is the approach

More information

Overview of the CLEF 2010 medical image retrieval track

Overview of the CLEF 2010 medical image retrieval track Overview of the CLEF 2010 medical image retrieval track Henning Müller 1,2, Jayashree Kalpathy Cramer 3, Ivan Eggel 1, Steven Bedrick 3, Joe Reisetter 3, Charles E. Kahn Jr. 4, William Hersh 3 1 Geneva

More information

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Abstract Automatic linguistic indexing of pictures is an important but highly challenging problem for researchers in content-based

More information

Ranking Web Pages by Associating Keywords with Locations

Ranking Web Pages by Associating Keywords with Locations Ranking Web Pages by Associating Keywords with Locations Peiquan Jin, Xiaoxiang Zhang, Qingqing Zhang, Sheng Lin, and Lihua Yue University of Science and Technology of China, 230027, Hefei, China jpq@ustc.edu.cn

More information

DUTH at ImageCLEF 2011 Wikipedia Retrieval

DUTH at ImageCLEF 2011 Wikipedia Retrieval DUTH at ImageCLEF 2011 Wikipedia Retrieval Avi Arampatzis, Konstantinos Zagoris, and Savvas A. Chatzichristofis Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi

More information

User Experiments with the Eurovision Cross-Language Image Retrieval System. Paul Clough and Mark Sanderson. University of Sheffield. Sheffield, UK.

User Experiments with the Eurovision Cross-Language Image Retrieval System. Paul Clough and Mark Sanderson. University of Sheffield. Sheffield, UK. Running head: CROSS-LANGUAGE IMAGE RETRIEVAL User Experiments with the Eurovision Cross-Language Image Retrieval System Paul Clough and Mark Sanderson University of Sheffield Sheffield, UK. Abstract In

More information

MetaMoJi Share for Business Ver. 3 MetaMoJi Note for Business Ver. 3 Administrator s Guide

MetaMoJi Share for Business Ver. 3 MetaMoJi Note for Business Ver. 3 Administrator s Guide MetaMoJi Share for Business Ver. 3 MetaMoJi Note for Business Ver. 3 Administrator s Guide Second Edition - ios is a trademark or registered trademark of Cisco in the U.S. and other countries and is used

More information

SIMATIC. Industrial PC Microsoft Windows 7 (USB stick) Safety instructions 1. Initial startup: Commissioning the operating system

SIMATIC. Industrial PC Microsoft Windows 7 (USB stick) Safety instructions 1. Initial startup: Commissioning the operating system Safety instructions 1 Initial startup: Commissioning the operating system 2 SIMATIC Industrial PC Operating Instructions Restoring the factory settings of the operating system and partitions(restore) 3

More information

Overview of iclef 2008: search log analysis for Multilingual Image Retrieval

Overview of iclef 2008: search log analysis for Multilingual Image Retrieval Overview of iclef 2008: search log analysis for Multilingual Image Retrieval Julio Gonzalo Paul Clough Jussi Karlgren UNED U. Sheffield SICS Spain United Kingdom Sweden julio@lsi.uned.es p.d.clough@sheffield.ac.uk

More information

STRUCTURE-BASED QUERY EXPANSION FOR XML SEARCH ENGINE

STRUCTURE-BASED QUERY EXPANSION FOR XML SEARCH ENGINE STRUCTURE-BASED QUERY EXPANSION FOR XML SEARCH ENGINE Wei-ning Qian, Hai-lei Qian, Li Wei, Yan Wang and Ao-ying Zhou Computer Science Department Fudan University Shanghai 200433 E-mail: wnqian@fudan.edu.cn

More information

TEXT CHAPTER 5. W. Bruce Croft BACKGROUND

TEXT CHAPTER 5. W. Bruce Croft BACKGROUND 41 CHAPTER 5 TEXT W. Bruce Croft BACKGROUND Much of the information in digital library or digital information organization applications is in the form of text. Even when the application focuses on multimedia

More information

University of Amsterdam at INEX 2010: Ad hoc and Book Tracks

University of Amsterdam at INEX 2010: Ad hoc and Book Tracks University of Amsterdam at INEX 2010: Ad hoc and Book Tracks Jaap Kamps 1,2 and Marijn Koolen 1 1 Archives and Information Studies, Faculty of Humanities, University of Amsterdam 2 ISLA, Faculty of Science,

More information

Overview of the wikipediamm task at ImageCLEF 2008

Overview of the wikipediamm task at ImageCLEF 2008 Overview of the wikipediamm task at ImageCLEF 2008 Theodora Tsikrika 1 and Jana Kludas 2 1 CWI, Amsterdam, The Netherlands 2 CUI, University of Geneva, Switzerland Theodora.Tsikrika@cwi.nl, jana.kludas@cui.unige.ch

More information

Prior Art Retrieval Using Various Patent Document Fields Contents

Prior Art Retrieval Using Various Patent Document Fields Contents Prior Art Retrieval Using Various Patent Document Fields Contents Metti Zakaria Wanagiri and Mirna Adriani Fakultas Ilmu Komputer, Universitas Indonesia Depok 16424, Indonesia metti.zakaria@ui.edu, mirna@cs.ui.ac.id

More information

The Wikipedia XML Corpus

The Wikipedia XML Corpus INEX REPORT The Wikipedia XML Corpus Ludovic Denoyer, Patrick Gallinari Laboratoire d Informatique de Paris 6 8 rue du capitaine Scott 75015 Paris http://www-connex.lip6.fr/denoyer/wikipediaxml {ludovic.denoyer,

More information

Oracle Policy Automation Release Notes

Oracle Policy Automation Release Notes Oracle Policy Automation 10.1.0 Release Notes Contents Release Overview 2 Oracle Policy Modeling 4 Singleton entities should not be used... 4 InstanceValueIf function... 4 Automatic entity containment...

More information

Task3 Patient-Centred Information Retrieval: Team CUNI

Task3 Patient-Centred Information Retrieval: Team CUNI Task3 Patient-Centred Information Retrieval: Team CUNI Shadi Saleh and Pavel Pecina Charles University Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics, Czech Republic {saleh,pecina}@ufal.mff.cuni.cz

More information

INEX REPORT. Report on INEX 2012

INEX REPORT. Report on INEX 2012 INEX REPORT Report on INEX 2012 P. Bellot T. Chappell A. Doucet S. Geva S. Gurajada J. Kamps G. Kazai M. Koolen M. Landoni M. Marx A. Mishra V. Moriceau J. Mothe M. Preminger G. Ramírez M. Sanderson E.

More information

Linking Entities in Chinese Queries to Knowledge Graph

Linking Entities in Chinese Queries to Knowledge Graph Linking Entities in Chinese Queries to Knowledge Graph Jun Li 1, Jinxian Pan 2, Chen Ye 1, Yong Huang 1, Danlu Wen 1, and Zhichun Wang 1(B) 1 Beijing Normal University, Beijing, China zcwang@bnu.edu.cn

More information

Predicting Next Search Actions with Search Engine Query Logs

Predicting Next Search Actions with Search Engine Query Logs 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology Predicting Next Search Actions with Search Engine Query Logs Kevin Hsin-Yih Lin Chieh-Jen Wang Hsin-Hsi

More information

Time-Surfer: Time-Based Graphical Access to Document Content

Time-Surfer: Time-Based Graphical Access to Document Content Time-Surfer: Time-Based Graphical Access to Document Content Hector Llorens 1,EstelaSaquete 1,BorjaNavarro 1,andRobertGaizauskas 2 1 University of Alicante, Spain {hllorens,stela,borja}@dlsi.ua.es 2 University

More information

Table of Contents. Welcome to Immobel. Below you will find documentation regarding our products and services.

Table of Contents. Welcome to Immobel. Below you will find documentation regarding our products and services. Immobel.com and NTREIS Welcome to Immobel. Below you will find documentation regarding our products and services. Table of Contents 1. Login Page... 2 2. Homepage... 3 3. My Profile and Account... 4 3.1

More information

Global Training Catalog

Global Training Catalog Global Training Catalog Table of Contents What We Offer 4 Electronic Article Surveillance 5 Technical Training 5 EAS... 5 Synergy... 5 UltraExit... 5 ProMax... 6 Essentials... 6 Loop Systems... 6 Deactivation...

More information

The University of Évora s Participation in

The University of Évora s Participation in The University of Évora s Participation in QA@CLEF-2007 José Saias and Paulo Quaresma Departamento de Informática Universidade de Évora, Portugal {jsaias,pq}@di.uevora.pt Abstract. The University of Évora

More information

Profiling Web Archive Coverage for Top-Level Domain & Content Language

Profiling Web Archive Coverage for Top-Level Domain & Content Language Old Dominion University ODU Digital Commons Computer Science Presentations Computer Science 9-23-2013 Profiling Web Archive Coverage for Top-Level Domain & Content Language Ahmed AlSum Old Dominion University

More information

Building Simulated Queries for Known-Item Topics

Building Simulated Queries for Known-Item Topics Building Simulated Queries for Known-Item Topics An Analysis using Six European Languages Leif Azzopardi Dept. of Computing Science University of Glasgow, Glasgow G12 8QQ leif@dcs.gla.ac.uk Maarten de

More information

led to different techniques for cross-language retrieval, ones which utilized the power of human indexing of documents to improve retrieval via bi-lin

led to different techniques for cross-language retrieval, ones which utilized the power of human indexing of documents to improve retrieval via bi-lin Cross-Language Retrieval for the CLEF Collections Comparing Multiple Methods of Retrieval Fredric C. Gey 1, Hailing Jiang 2, Vivien Petras 2 and Aitao Chen 2 1 UC Data Archive & Technical Assistance, 2

More information

Entity Linking at TAC Task Description

Entity Linking at TAC Task Description Entity Linking at TAC 2013 Task Description Version 1.0 of April 9, 2013 1 Introduction The main goal of the Knowledge Base Population (KBP) track at TAC 2013 is to promote research in and to evaluate

More information

Annotating Spatio-Temporal Information in Documents

Annotating Spatio-Temporal Information in Documents Annotating Spatio-Temporal Information in Documents Jannik Strötgen University of Heidelberg Institute of Computer Science Database Systems Research Group http://dbs.ifi.uni-heidelberg.de stroetgen@uni-hd.de

More information

CroLOM: Cross-Lingual Ontology Matching System

CroLOM: Cross-Lingual Ontology Matching System CroLOM: Cross-Lingual Ontology Matching System Results for OAEI 2016 Abderrahmane Khiat LITIO Laboratory, University of Oran1 Ahmed Ben Bella, Oran, Algeria abderrahmane khiat@yahoo.com Abstract. The current

More information