Attentive Neural Architecture for Ad-hoc Structured Document Retrieval

Size: px
Start display at page:

Download "Attentive Neural Architecture for Ad-hoc Structured Document Retrieval"

Transcription

1 Attentive Neural Architecture for Ad-hoc Structured Document Retrieval Saeid Balaneshin 1 Alexander Kotov 1 Fedor Nikolaev 1,2 1 Textual Data Analytics Lab, Department of Computer Science, Wayne State University 2 Kazan Federal University 1/25

2 Ad-hoc Structured (Multi-field) Document Retrieval IR research traditionally views documents as holistic and homogeneous units of text The task of retrieving structured (multi-field) documents arises in many information access scenarios: Entity retrieval from knowledge graph(s) Web document retrieval Product search in e-commerce 2/25

3 Entity Retrieval from Knowledge Graph(s) Names Attributes Categories Similar Entity Names Related Entity Names 3/25

4 Entity Retrieval from Knowledge Graph(s) Names Attributes Categories Similar Entity Names Related Entity Names 3/25

5 Entity Retrieval from Knowledge Graph(s) Names Attributes Categories Similar Entity Names Related Entity Names 3/25

6 Entity Retrieval from Knowledge Graph(s) Names Attributes Categories Similar Entity Names Related Entity Names 3/25

7 Product Search Title Description Attributes 4/25

8 Product Search Title Description Attributes 4/25

9 Product Search Title Description Attributes 4/25

10 Product Search Title Description Attributes 4/25

11 Web Search Title Texts in Large Font Contents Incoming Hyper-links Document Meta-data Alternative Texts for Images 5/25

12 Web Search Title Texts in Large Font Contents Incoming Hyper-links Document Meta-data Alternative Texts for Images 5/25

13 Web Search Title Texts in Large Font Contents Incoming Hyper-links Document Meta-data Alternative Texts for Images 5/25

14 Web Search Title Texts in Large Font Contents Incoming Hyper-links Document Meta-data Alternative Texts for Images 5/25

15 Document vs. Structured Document Retrieval Document Retrieval - relevance is quantified by aggregating heuristics calculated at the document or collection level (# of occurrences and proximity of query terms, IDF, document length) Structured Document Retrieval - requires strategies for aggregating heuristics calculated at the level of document fields into the matching score of an entire document - effective for retrieving documents with lexically similar, but semantically diverse fields 6/25

16 Importance of Document Fields Aggregation of field-level statistics of query terms in structured document retrieval is informed by a relative importance of document fields, which depends on: properties or semantics of document fields: e.g. a query term matched in a section of a Web page, which is in larger font, should have a different importance than a query term matched in other sections query intent: e.g. in the query attractive outdoor light with security features attractive refers to product description, outdoor light to product name and security features to product attributes 7/25

17 Mixture of Language Models (MLM) [Ogilvie and Callan, SIGIR 03] Document D with F fields is ranked w.r.t query Q according to: P(Q D) rank = q i Q P(q i θ D ) n(q i,q) where F P(q i θ D ) = w j P(q i θ j ) j=1 8/25

18 Fielded Sequential Dependence Model (FSDM) [Zhiltsov et al., SIGIR 15] Extends SDM to the case of structured document retrieval (i.e. accounts for both unigram and sequential bigram concepts in a query and document structure) Document D with F fields is ranked w.r.t query Q according to: P(D Q) rank = λ T q i Q f T (q i, D) + λ O f O (q i, q i+1, D)+ λ U f U (q i, q i+1, D) q i Q Potential function for query unigram q i : q i Q F f T (q i, D) = log w j P(q i θ j ) j=1 9/25

19 Challenges of Structured Document Retrieval Methods for structured document retrieval (SDR) face three major challenges: identifying the key concepts (words or phrases) in keyword queries semantic matching of the key query concepts in different fields of structured documents aggregating the scores of the matched query phrases into the overall score of a structured document Key limitation: all previously proposed SDR methods are based on direct matching of concepts in queries and document fields lexical gap 10/25

20 Proposed Neural Architecture Attention-based Neural Architecture for Ad-hoc Structured Document Retrieval (ANSR): Input: embeddings of words in a query and document fields Pooling layers: create compressed interaction matrices of the same dimensions between unigram- and bigram-based query and document field phrases Matching score aggregation layers: combine the matching scores of query phrases in different document fields into the overall document relevance score by taking into account relative importance of query phrases and document fields Document field attention layers: calculate relative importance of document fields Query phrase attention layers: calculate relative importance of query phrases 11/25

21 Pooling Layers (1) Step 1: create distributed representations of a query and each document field Query: automobile capital and the Detroit of Italy Document: Taurinum Turin is an important business and cultural center in northern Italy, capital city of the Piedmont region attributes located mainly on the left bank of the Po River Susa Valley Italy it is also dubbed la capitale Sabauda Savoyard capital related entity names Space Station Teatro Carignano Savoie List of political philosophers Haifa Parola, Carlo Residences of the Royal House of Savoy Eco, Duchy of Milan Mezzo-soprano Genoa Ginzburg Alessandro Pertini attributes related entity names Taurinum city space Parola Italy capital Milan Pertini 12/25

22 Pooling Layers (2) Step 2: create document fields interaction matrix for each query phrase distributed representations of query and document fields compressed interaction matrices for unigram-based query phrases automobile capital attributes automobile capital Taurinum Italy city capital Italy related entity names space Parola 0.19 Milan Pertini 0.22 attributes Taurinum city Italy capital attributes Taurinum city 0.35 Italy Italy capital 0.39 related entity names space Parola Milan Pertini related entity names space Milan Parola Pertini /25

23 Document Field Attention Layers Goal: compute the importance weights of document fields for aggregating the matching scores of query phrases Document: attributes Taurinum city Italy capital importance weights 0.21 attributes related entity names space Parola Milan Pertini softmax 0.18 related entity names 14/25

24 Query Phrase Attention Layers Goal: compute the importance weights of query phrases for aggregating the matching scores of query phrases of the same type Query: automobile capital and the Detroit of Italy query phrase importance weights automobile capital 0.24 automobile capital softmax query phrase Italy 0.19 Italy 15/25

25 Matching Score Aggregation Layers attributes related entity names attributes Interaction Matrices query phrase: automobile capital Taurinum city space Parola 0.19 Taurinum city 0.35 Italy capital Milan Pertini 0.22 query phrase: Italy Italy capital 0.39 matching score of 'automobile capital' in all document fields matching score of unigram based query phrases 0.30 aggregation of matching scores of all unigramand bigram-based query phrases related entity names space Parola Milan Pertini matching score of 'Italy' in all document fields aggregation of query phrase matching scores in document fields aggregation of matching scores of query phrases of the same type 16/25

26 Training ANSR is trained to minimize contrastive max-margin loss, given a collection of triplets <q, d n, d r > consisting of relevant d r and non-relevant d n documents for query q: ( min W <q,d n,d r > T max(0, ζ s(q, d r ) + s(q, d n )) + γ 2 W 2 2 ) 17/25

27 Experiments Language modeling and probabilistic baselines: PRMS (Probabilistic Retrieval Model for Semistructured Data) [Kim, Xue and Croft, ECIR 09] MLM (Mixture of Language Models) [Ogilvie and Callan, SIGIR 03] BM25F [Robertson, Zaragoza and Taylor, CIKM 04] FSDM (Fielded Sequential Dependence Model) [Zhiltsov, Kotov and Nikolaev, SIGIR 15] Neural baselines: DRMM (Deep Relevance Matching Model) [Guo, Fan, Ai and Croft, CIKM 16] DESM (Dual Embedding Space Model ) [Nalisnick, Mitra, Craswell and Caruanan, WWW 16] NRM-F (Neural Ranking Model with Multiple Document Fields) [ Zamani, Mitra, Song, Craswell and Tiwary, WSDM 18] 18/25

28 Performance of ANSR and the baselines GOV2 collection MAP PRMS (-39.49%) (-32.62%) (-30.16%) MLM (-10.41%) (-6.23%) (-4.21%) BM25F (-9.00%) (-9.05%) (-7.72%) FSDM (-7.21%) (-3.42%) (-3.00%) DESM (-8.56%) (-5.13%) (-7.33%) DRMM (4.10%) (-2.37%) (-4.35%) NRM-F (-54.07%) (-51.80%) (-56.82%) ANSR ANSR achieved 7.21% and 3% improvement over FSDM in terms of MAP and and 4.35% improvement over DRMM in terms of 19/25

29 Performance of ANSR and the baselines HomeDepot collection MAP PRMS (-19.64%) (-21.57%) (-17.57%) MLM (-13.00%) (-14.09%) (-9.71%) BM25F (-10.86%) (-12.78%) (-7.87%) FSDM (-8.96%) (-12.42%) (-5.62%) DESM (-17.46%) (-19.61%) (-8.15%) DRMM (-12.72%) (-17.86%) (-7.87%) NRM-F (-46.03%) (-47.49%) (-42.82%) ANSR ANSR achieved 8.96% and 5.62% improvement over FSDM as well as 12.72% and 7.87% improvement over DRMM in terms of MAP and 19/25

30 Performance of ANSR and the baselines DBPedia-v2 collection MAP PRMS (-26.50%) (-15.55%) (-14.26%) MLM (-13.15%) (-8.67%) (-9.29%) BM25F (-4.83%) (-4.21%) (-4.30%) FSDM (-7.84%) (-4.30%) (-5.99%) DESM (-11.75%) (-8.51%) (-5.92%) DRMM (-7.77%) (-5.73%) (-6.17%) NRM-F (-52.96%) (-50.85%) (-50.08%) ANSR ANSR achieved 4.83% and 4.30% improvement over BM25F as well as 7.77% and 6.17% improvement over DRMM in terms of MAP and 19/25

31 Topic-level difference in retrieval accuracy between ANSR and FSDM difference difference 0.0 difference k k k (a) GOV2 (b) HomeDepot (c) DBpedia-v2 ANSR has higher average precision than FSDM for 58.88% of the queries in HomeDepot collection In GOV2, the magnitude of improvements in average precision is 1.66 times greater than the magnitude of reductions Superior ability of ANSR to deal with long field documents, due to utilization of compressed representations and explicit correction of the pooling bias 20/25

32 The effect of the pooling size (k) on the performance of ANSR and ANSR-no-pooling ANSR-no-pooling: select the first k terms in each document field instead of pooling map ANSR ANSR no pooling map ANSR ANSR no pooling map ANSR ANSR no pooling k k k (a) GOV2 (b) HomeDepot (c) DBpedia-v2 ANSR has substantially better retrieval accuracy in terms of MAP than ANSR-no-pooling The optimal value of k depends on the collection and the retrieval task: ANSR has the best performance on GOV2, DBpedia-v2 and HomeDepot collections when k = 10, k = 6 and k = 6, respectively 21/25

33 Best performing queries in comparison to FSDM The best performing query is single lever hole bathroom sink faucet : only one relevant document with the title Belle Foret Single Hole 1-Handle High Arc Bathroom Vessel Faucet in Chrome with Metal Lever Handles in relevance judgments This document has longer fields than the average field length in this collection 22/25

34 Worst performing queries in comparison to FSDM The worst performing query is popular : only one relevant document with the title Bloomsz Most Popular Water Plant Collection (8-Pack) in relevance judgments ANSR ranked the document with the title South Shore Furniture Popular Twin Mates Bed in Mocha as the top-ranked document, since it has more words that are semantically similar to the query term popular This can be a consequence of using word embeddings by ANSR, which can cause topic drift for very short queries 23/25

35 Summary ANSR utilizes pooling to generate fixed-size interactions matrices between representations of phrases in a query and document fields and employs an attention mechanism to focus on the most important document fields and query phrases ANSR includes the layers to compute and aggregate the relevance score of a structured document at different levels of granularity ANSR outperforms state-of-the-art LM and neural baselines in different SDR tasks, such as Web search, product search and entity retrieval from a knowledge graph. 24/25

36 Thank you! Questions? 25/25

Attentive Neural Architecture for Ad-hoc Structured Document Retrieval

Attentive Neural Architecture for Ad-hoc Structured Document Retrieval Attentive Neural Architecture for Ad-hoc Structured Document Retrieval Saeid Balaneshinordan saeid@wayne.edu Wayne State University Detroit, MI, USA Alexander Kotov otov@wayne.edu Wayne State University

More information

A Deep Relevance Matching Model for Ad-hoc Retrieval

A Deep Relevance Matching Model for Ad-hoc Retrieval A Deep Relevance Matching Model for Ad-hoc Retrieval Jiafeng Guo 1, Yixing Fan 1, Qingyao Ai 2, W. Bruce Croft 2 1 CAS Key Lab of Web Data Science and Technology, Institute of Computing Technology, Chinese

More information

Entity and Knowledge Base-oriented Information Retrieval

Entity and Knowledge Base-oriented Information Retrieval Entity and Knowledge Base-oriented Information Retrieval Presenter: Liuqing Li liuqing@vt.edu Digital Library Research Laboratory Virginia Polytechnic Institute and State University Blacksburg, VA 24061

More information

A Deep Top-K Relevance Matching Model for Ad-hoc Retrieval

A Deep Top-K Relevance Matching Model for Ad-hoc Retrieval A Deep Top-K Relevance Matching Model for Ad-hoc Retrieval Zhou Yang, Qingfeng Lan, Jiafeng Guo, Yixing Fan, Xiaofei Zhu, Yanyan Lan, Yue Wang, and Xueqi Cheng School of Computer Science and Engineering,

More information

Improving Difficult Queries by Leveraging Clusters in Term Graph

Improving Difficult Queries by Leveraging Clusters in Term Graph Improving Difficult Queries by Leveraging Clusters in Term Graph Rajul Anand and Alexander Kotov Department of Computer Science, Wayne State University, Detroit MI 48226, USA {rajulanand,kotov}@wayne.edu

More information

Parameterized Fielded Term Dependence Models for Ad-hoc Entity Retrieval from Knowledge Graph

Parameterized Fielded Term Dependence Models for Ad-hoc Entity Retrieval from Knowledge Graph Parameterized Fielded Term Dependence Models for Ad-hoc Entity Retrieval from Knowledge Graph Fedor Nikolaev Department of Computer Science Wayne State University Detroit, Michigan 48202 fedor@wayne.edu

More information

NEURAL MODELS FOR INFORMATION RETRIEVAL

NEURAL MODELS FOR INFORMATION RETRIEVAL NEURAL MODELS FOR INFORMATION RETRIEVAL November, 2017 BHASKAR MITRA Principal Applied Scientist Microsoft AI and Research Research Student Dept. of Computer Science University College London This talk

More information

Model SDM-ELR FSDM-ELR

Model SDM-ELR FSDM-ELR rom recall@ sults are below top-10. Model BM25 PRMS MLM-all LM SDM LM-ELR SDM-ELR MLM-CA BM25-CA FSDM BM25F-CA FSDM-ELR max gap Total 0.1823.5175.7703.2522.8009.2571.6136.8009.2607.6413.8009.2659.6674.8633.2646.6483.8006.2739.6782.8633.2639.6370.8329.2782.6727.8708.2812.6667.8455.2811.6912.8653.2872.6765.8450.2872.6912.8708.5836.1796

More information

A Study of MatchPyramid Models on Ad hoc Retrieval

A Study of MatchPyramid Models on Ad hoc Retrieval A Study of MatchPyramid Models on Ad hoc Retrieval Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xueqi Cheng Institute of Computing Technology, Chinese Academy of Sciences Text Matching Many text based

More information

WSU-IR at TREC 2015 Clinical Decision Support Track: Joint Weighting of Explicit and Latent Medical Query Concepts from Diverse Sources

WSU-IR at TREC 2015 Clinical Decision Support Track: Joint Weighting of Explicit and Latent Medical Query Concepts from Diverse Sources WSU-IR at TREC 2015 Clinical Decision Support Track: Joint Weighting of Explicit and Latent Medical Query Concepts from Diverse Sources Saeid Balaneshin-kordan, Alexander Kotov, and Railan Xisto Department

More information

Learning to Reweight Terms with Distributed Representations

Learning to Reweight Terms with Distributed Representations Learning to Reweight Terms with Distributed Representations School of Computer Science Carnegie Mellon University August 12, 215 Outline Goal: Assign weights to query terms for better retrieval results

More information

arxiv: v1 [cs.ir] 16 Oct 2017

arxiv: v1 [cs.ir] 16 Oct 2017 DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Jingfang Xu, Xueqi Cheng pl8787@gmail.com,{lanyanyan,guojiafeng,junxu,cxq}@ict.ac.cn,xujingfang@sogou-inc.com

More information

A Machine Learning Approach for Improved BM25 Retrieval

A Machine Learning Approach for Improved BM25 Retrieval A Machine Learning Approach for Improved BM25 Retrieval Krysta M. Svore and Christopher J. C. Burges Microsoft Research One Microsoft Way Redmond, WA 98052 {ksvore,cburges}@microsoft.com Microsoft Research

More information

Window Extraction for Information Retrieval

Window Extraction for Information Retrieval Window Extraction for Information Retrieval Samuel Huston Center for Intelligent Information Retrieval University of Massachusetts Amherst Amherst, MA, 01002, USA sjh@cs.umass.edu W. Bruce Croft Center

More information

Diversifying Query Suggestions Based on Query Documents

Diversifying Query Suggestions Based on Query Documents Diversifying Query Suggestions Based on Query Documents Youngho Kim University of Massachusetts Amherst yhkim@cs.umass.edu W. Bruce Croft University of Massachusetts Amherst croft@cs.umass.edu ABSTRACT

More information

An Investigation of Basic Retrieval Models for the Dynamic Domain Task

An Investigation of Basic Retrieval Models for the Dynamic Domain Task An Investigation of Basic Retrieval Models for the Dynamic Domain Task Razieh Rahimi and Grace Hui Yang Department of Computer Science, Georgetown University rr1042@georgetown.edu, huiyang@cs.georgetown.edu

More information

End-to-End Neural Ad-hoc Ranking with Kernel Pooling

End-to-End Neural Ad-hoc Ranking with Kernel Pooling End-to-End Neural Ad-hoc Ranking with Kernel Pooling Chenyan Xiong 1,Zhuyun Dai 1, Jamie Callan 1, Zhiyuan Liu, and Russell Power 3 1 :Language Technologies Institute, Carnegie Mellon University :Tsinghua

More information

Focused Retrieval Using Topical Language and Structure

Focused Retrieval Using Topical Language and Structure Focused Retrieval Using Topical Language and Structure A.M. Kaptein Archives and Information Studies, University of Amsterdam Turfdraagsterpad 9, 1012 XT Amsterdam, The Netherlands a.m.kaptein@uva.nl Abstract

More information

Term Frequency Normalisation Tuning for BM25 and DFR Models

Term Frequency Normalisation Tuning for BM25 and DFR Models Term Frequency Normalisation Tuning for BM25 and DFR Models Ben He and Iadh Ounis Department of Computing Science University of Glasgow United Kingdom Abstract. The term frequency normalisation parameter

More information

UMass at TREC 2017 Common Core Track

UMass at TREC 2017 Common Core Track UMass at TREC 2017 Common Core Track Qingyao Ai, Hamed Zamani, Stephen Harding, Shahrzad Naseri, James Allan and W. Bruce Croft Center for Intelligent Information Retrieval College of Information and Computer

More information

Chapter 6: Information Retrieval and Web Search. An introduction

Chapter 6: Information Retrieval and Web Search. An introduction Chapter 6: Information Retrieval and Web Search An introduction Introduction n Text mining refers to data mining using text documents as data. n Most text mining tasks use Information Retrieval (IR) methods

More information

arxiv: v3 [cs.ir] 21 Jul 2017

arxiv: v3 [cs.ir] 21 Jul 2017 PACRR: A Position-Aware Neural IR Model for Relevance Matching Kai Hui MPI for Informatics Saarbrücken Graduate School of Computer Science Andrew Yates MPI for Informatics Klaus Berberich htw saar MPI

More information

On Duplicate Results in a Search Session

On Duplicate Results in a Search Session On Duplicate Results in a Search Session Jiepu Jiang Daqing He Shuguang Han School of Information Sciences University of Pittsburgh jiepu.jiang@gmail.com dah44@pitt.edu shh69@pitt.edu ABSTRACT In this

More information

Exploiting Entity Linking in Queries for Entity Retrieval

Exploiting Entity Linking in Queries for Entity Retrieval Exploiting Entity Linking in Queries for Entity Retrieval Faegheh Hasibi Norwegian University of Science and Technology faegheh.hasibi@idi.ntnu.no Krisztian Balog University of Stavanger krisztian.balog@uis.no

More information

Microsoft Research Asia at the Web Track of TREC 2009

Microsoft Research Asia at the Web Track of TREC 2009 Microsoft Research Asia at the Web Track of TREC 2009 Zhicheng Dou, Kun Chen, Ruihua Song, Yunxiao Ma, Shuming Shi, and Ji-Rong Wen Microsoft Research Asia, Xi an Jiongtong University {zhichdou, rsong,

More information

Reducing Redundancy with Anchor Text and Spam Priors

Reducing Redundancy with Anchor Text and Spam Priors Reducing Redundancy with Anchor Text and Spam Priors Marijn Koolen 1 Jaap Kamps 1,2 1 Archives and Information Studies, Faculty of Humanities, University of Amsterdam 2 ISLA, Informatics Institute, University

More information

5. Novelty & Diversity

5. Novelty & Diversity 5. Novelty & Diversity Outline 5.1. Why Novelty & Diversity? 5.2. Probability Ranking Principled Revisited 5.3. Implicit Diversification 5.4. Explicit Diversification 5.5. Evaluating Novelty & Diversity

More information

Information Retrieval: Retrieval Models

Information Retrieval: Retrieval Models CS473: Web Information Retrieval & Management CS-473 Web Information Retrieval & Management Information Retrieval: Retrieval Models Luo Si Department of Computer Science Purdue University Retrieval Models

More information

CS47300: Web Information Search and Management

CS47300: Web Information Search and Management CS47300: Web Information Search and Management Federated Search Prof. Chris Clifton 13 November 2017 Federated Search Outline Introduction to federated search Main research problems Resource Representation

More information

Ranking models in Information Retrieval: A Survey

Ranking models in Information Retrieval: A Survey Ranking models in Information Retrieval: A Survey R.Suganya Devi Research Scholar Department of Computer Science and Engineering College of Engineering, Guindy, Chennai, Tamilnadu, India Dr D Manjula Professor

More information

A Study of Pattern-based Subtopic Discovery and Integration in the Web Track

A Study of Pattern-based Subtopic Discovery and Integration in the Web Track A Study of Pattern-based Subtopic Discovery and Integration in the Web Track Wei Zheng and Hui Fang Department of ECE, University of Delaware Abstract We report our systems and experiments in the diversity

More information

TREC-10 Web Track Experiments at MSRA

TREC-10 Web Track Experiments at MSRA TREC-10 Web Track Experiments at MSRA Jianfeng Gao*, Guihong Cao #, Hongzhao He #, Min Zhang ##, Jian-Yun Nie**, Stephen Walker*, Stephen Robertson* * Microsoft Research, {jfgao,sw,ser}@microsoft.com **

More information

Federated Search. Jaime Arguello INLS 509: Information Retrieval November 21, Thursday, November 17, 16

Federated Search. Jaime Arguello INLS 509: Information Retrieval November 21, Thursday, November 17, 16 Federated Search Jaime Arguello INLS 509: Information Retrieval jarguell@email.unc.edu November 21, 2016 Up to this point... Classic information retrieval search from a single centralized index all ueries

More information

From Neural Re-Ranking to Neural Ranking:

From Neural Re-Ranking to Neural Ranking: From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing Hamed Zamani (1), Mostafa Dehghani (2), W. Bruce Croft (1), Erik Learned-Miller (1), and Jaap Kamps (2)

More information

Risk Minimization and Language Modeling in Text Retrieval Thesis Summary

Risk Minimization and Language Modeling in Text Retrieval Thesis Summary Risk Minimization and Language Modeling in Text Retrieval Thesis Summary ChengXiang Zhai Language Technologies Institute School of Computer Science Carnegie Mellon University July 21, 2002 Abstract This

More information

PUTTING CONTEXT INTO SEARCH AND SEARCH INTO CONTEXT. Susan Dumais, Microsoft Research

PUTTING CONTEXT INTO SEARCH AND SEARCH INTO CONTEXT. Susan Dumais, Microsoft Research PUTTING CONTEXT INTO SEARCH AND SEARCH INTO CONTEXT Susan Dumais, Microsoft Research Overview Importance of context in IR Potential for personalization framework Examples Personal navigation Client-side

More information

Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding

Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding Chenyan Xiong Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA cx@cs.cmu.edu Russell Power Allen

More information

Learning to Rank with Attentive Media Attributes

Learning to Rank with Attentive Media Attributes Learning to Rank with Attentive Media Attributes Baldo Faieta Yang (Allie) Yang Adobe Adobe San Francisco, CA 94103 San Francisco, CA. 94103 bfaieta@adobe.com yangyan@adobe.com Abstract In the context

More information

Predicting Query Performance on the Web

Predicting Query Performance on the Web Predicting Query Performance on the Web No Author Given Abstract. Predicting performance of queries has many useful applications like automatic query reformulation and automatic spell correction. However,

More information

Fall CS646: Information Retrieval. Lecture 2 - Introduction to Search Result Ranking. Jiepu Jiang University of Massachusetts Amherst 2016/09/12

Fall CS646: Information Retrieval. Lecture 2 - Introduction to Search Result Ranking. Jiepu Jiang University of Massachusetts Amherst 2016/09/12 Fall 2016 CS646: Information Retrieval Lecture 2 - Introduction to Search Result Ranking Jiepu Jiang University of Massachusetts Amherst 2016/09/12 More course information Programming Prerequisites Proficiency

More information

Semantic Entity Retrieval using Web Queries over Structured RDF Data

Semantic Entity Retrieval using Web Queries over Structured RDF Data Semantic Entity Retrieval using Web Queries over Structured RDF Data Jeff Dalton and Sam Huston CS645 Project Final Report May 11, 2010 Abstract We investigate the problem of performing entity retrieval

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

Effective Latent Space Graph-based Re-ranking Model with Global Consistency

Effective Latent Space Graph-based Re-ranking Model with Global Consistency Effective Latent Space Graph-based Re-ranking Model with Global Consistency Feb. 12, 2009 1 Outline Introduction Related work Methodology Graph-based re-ranking model Learning a latent space graph A case

More information

University of Delaware at Diversity Task of Web Track 2010

University of Delaware at Diversity Task of Web Track 2010 University of Delaware at Diversity Task of Web Track 2010 Wei Zheng 1, Xuanhui Wang 2, and Hui Fang 1 1 Department of ECE, University of Delaware 2 Yahoo! Abstract We report our systems and experiments

More information

Semantic and Distributed Entity Search in the Web of Data

Semantic and Distributed Entity Search in the Web of Data Semantic and Distributed Entity Search in the Web of Data Robert Neumayer neumayer@idi.ntnu.no Norwegian University of Science and Technology Trondheim, Norway March 6, 2013 1/48 1. Entity Search and the

More information

CS54701: Information Retrieval

CS54701: Information Retrieval CS54701: Information Retrieval Basic Concepts 19 January 2016 Prof. Chris Clifton 1 Text Representation: Process of Indexing Remove Stopword, Stemming, Phrase Extraction etc Document Parser Extract useful

More information

Jan Pedersen 22 July 2010

Jan Pedersen 22 July 2010 Jan Pedersen 22 July 2010 Outline Problem Statement Best effort retrieval vs automated reformulation Query Evaluation Architecture Query Understanding Models Data Sources Standard IR Assumptions Queries

More information

WEIGHTING QUERY TERMS USING WORDNET ONTOLOGY

WEIGHTING QUERY TERMS USING WORDNET ONTOLOGY IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.4, April 2009 349 WEIGHTING QUERY TERMS USING WORDNET ONTOLOGY Mohammed M. Sakre Mohammed M. Kouta Ali M. N. Allam Al Shorouk

More information

AComparisonofRetrievalModelsusingTerm Dependencies

AComparisonofRetrievalModelsusingTerm Dependencies AComparisonofRetrievalModelsusingTerm Dependencies Samuel Huston and W. Bruce Croft Center for Intelligent Information Retrieval University of Massachusetts Amherst 140 Governors Dr, Amherst, Massachusetts,

More information

Supporting Scholarly Search with Keyqueries

Supporting Scholarly Search with Keyqueries Supporting Scholarly Search with Keyqueries Matthias Hagen Anna Beyer Tim Gollub Kristof Komlossy Benno Stein Bauhaus-Universität Weimar matthias.hagen@uni-weimar.de @matthias_hagen ECIR 2016 Padova, Italy

More information

Mining the Search Trails of Surfing Crowds: Identifying Relevant Websites from User Activity Data

Mining the Search Trails of Surfing Crowds: Identifying Relevant Websites from User Activity Data Mining the Search Trails of Surfing Crowds: Identifying Relevant Websites from User Activity Data Misha Bilenko and Ryen White presented by Matt Richardson Microsoft Research Search = Modeling User Behavior

More information

arxiv: v1 [cs.ir] 15 May 2018

arxiv: v1 [cs.ir] 15 May 2018 Modeling Diverse Relevance Patterns in Ad-hoc Retrieval Yixing Fan,, Jiafeng Guo,, Yanyan Lan,, Jun Xu,, Chengxiang Zhai and Xueqi Cheng, University of Chinese Academy of Sciences, Beijing, China CAS Key

More information

Robust Relevance-Based Language Models

Robust Relevance-Based Language Models Robust Relevance-Based Language Models Xiaoyan Li Department of Computer Science, Mount Holyoke College 50 College Street, South Hadley, MA 01075, USA Email: xli@mtholyoke.edu ABSTRACT We propose a new

More information

Natural Language Processing

Natural Language Processing Natural Language Processing Information Retrieval Potsdam, 14 June 2012 Saeedeh Momtazi Information Systems Group based on the slides of the course book Outline 2 1 Introduction 2 Indexing Block Document

More information

arxiv: v1 [cs.ir] 26 Oct 2016

arxiv: v1 [cs.ir] 26 Oct 2016 Learning to Match Using Local and Distributed Representations of Text for Web Search Bhaskar Mitra 1,2, Fernando Diaz 1, and Nick Craswell 1 1 Microsoft, {bmitra, fdiaz, nickcr}@microsoft.com 2 University

More information

Heading-aware Snippet Generation for Web Search

Heading-aware Snippet Generation for Web Search Heading-aware Snippet Generation for Web Search Tomohiro Manabe and Keishi Tajima Graduate School of Informatics, Kyoto Univ. {manabe@dl.kuis, tajima@i}.kyoto-u.ac.jp Web Search Result Snippets Are short

More information

Chrome based Keyword Visualizer (under sparse text constraint) SANGHO SUH MOONSHIK KANG HOONHEE CHO

Chrome based Keyword Visualizer (under sparse text constraint) SANGHO SUH MOONSHIK KANG HOONHEE CHO Chrome based Keyword Visualizer (under sparse text constraint) SANGHO SUH MOONSHIK KANG HOONHEE CHO INDEX Proposal Recap Implementation Evaluation Future Works Proposal Recap Keyword Visualizer (chrome

More information

TREC 2016 Dynamic Domain Track: Exploiting Passage Representation for Retrieval and Relevance Feedback

TREC 2016 Dynamic Domain Track: Exploiting Passage Representation for Retrieval and Relevance Feedback RMIT @ TREC 2016 Dynamic Domain Track: Exploiting Passage Representation for Retrieval and Relevance Feedback Ameer Albahem ameer.albahem@rmit.edu.au Lawrence Cavedon lawrence.cavedon@rmit.edu.au Damiano

More information

A Study of Methods for Negative Relevance Feedback

A Study of Methods for Negative Relevance Feedback A Study of Methods for Negative Relevance Feedback Xuanhui Wang University of Illinois at Urbana-Champaign Urbana, IL 61801 xwang20@cs.uiuc.edu Hui Fang The Ohio State University Columbus, OH 43210 hfang@cse.ohiostate.edu

More information

Introduction to Information Retrieval. Hongning Wang

Introduction to Information Retrieval. Hongning Wang Introduction to Information Retrieval Hongning Wang CS@UVa What is information retrieval? 2 Why information retrieval Information overload It refers to the difficulty a person can have understanding an

More information

From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing

From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing Hamed Zamani University of Massachusetts Amherst zamani@cs.umass.edu Mostafa Dehghani University of Amsterdam

More information

LaHC at CLEF 2015 SBS Lab

LaHC at CLEF 2015 SBS Lab LaHC at CLEF 2015 SBS Lab Nawal Ould-Amer, Mathias Géry To cite this version: Nawal Ould-Amer, Mathias Géry. LaHC at CLEF 2015 SBS Lab. Conference and Labs of the Evaluation Forum, Sep 2015, Toulouse,

More information

Supervised Reranking for Web Image Search

Supervised Reranking for Web Image Search for Web Image Search Query: Red Wine Current Web Image Search Ranking Ranking Features http://www.telegraph.co.uk/306737/red-wineagainst-radiation.html 2 qd, 2.5.5 0.5 0 Linjun Yang and Alan Hanjalic 2

More information

Retrieval and Feedback Models for Blog Distillation

Retrieval and Feedback Models for Blog Distillation Retrieval and Feedback Models for Blog Distillation Jonathan Elsas, Jaime Arguello, Jamie Callan, Jaime Carbonell Language Technologies Institute, School of Computer Science, Carnegie Mellon University

More information

Learning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li

Learning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li Learning to Match Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li 1. Introduction The main tasks in many applications can be formalized as matching between heterogeneous objects, including search, recommendation,

More information

Estimating Embedding Vectors for Queries

Estimating Embedding Vectors for Queries Estimating Embedding Vectors for Queries Hamed Zamani Center for Intelligent Information Retrieval College of Information and Computer Sciences University of Massachusetts Amherst Amherst, MA 01003 zamani@cs.umass.edu

More information

Effect of log-based Query Term Expansion on Retrieval Effectiveness in Patent Searching

Effect of log-based Query Term Expansion on Retrieval Effectiveness in Patent Searching Effect of log-based Query Term Expansion on Retrieval Effectiveness in Patent Searching Wolfgang Tannebaum, Parvaz Madabi and Andreas Rauber Institute of Software Technology and Interactive Systems, Vienna

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

UMass at TREC 2006: Enterprise Track

UMass at TREC 2006: Enterprise Track UMass at TREC 2006: Enterprise Track Desislava Petkova and W. Bruce Croft Center for Intelligent Information Retrieval Department of Computer Science University of Massachusetts, Amherst, MA 01003 Abstract

More information

Introduction to Information Retrieval

Introduction to Information Retrieval Introduction to Information Retrieval Mohsen Kamyar چهارمین کارگاه ساالنه آزمایشگاه فناوری و وب بهمن ماه 1391 Outline Outline in classic categorization Information vs. Data Retrieval IR Models Evaluation

More information

Book Recommendation based on Social Information

Book Recommendation based on Social Information Book Recommendation based on Social Information Chahinez Benkoussas and Patrice Bellot LSIS Aix-Marseille University chahinez.benkoussas@lsis.org patrice.bellot@lsis.org Abstract : In this paper, we present

More information

Multimodal topic model for texts and images utilizing their embeddings

Multimodal topic model for texts and images utilizing their embeddings Multimodal topic model for texts and images utilizing their embeddings Nikolay Smelik, smelik@rain.ifmo.ru Andrey Filchenkov, afilchenkov@corp.ifmo.ru Computer Technologies Lab IDP-16. Barcelona, Spain,

More information

Research Article An Exponentiation Method for XML Element Retrieval

Research Article An Exponentiation Method for XML Element Retrieval e Scientific World Journal, Article ID 404518, 10 pages http://dx.doi.org/10.1155/2014/404518 Research Article An Exponentiation Method for XML Element Retrieval Tanakorn Wichaiwong Department of Computer

More information

COLLABORATIVE LOCATION AND ACTIVITY RECOMMENDATIONS WITH GPS HISTORY DATA

COLLABORATIVE LOCATION AND ACTIVITY RECOMMENDATIONS WITH GPS HISTORY DATA COLLABORATIVE LOCATION AND ACTIVITY RECOMMENDATIONS WITH GPS HISTORY DATA Vincent W. Zheng, Yu Zheng, Xing Xie, Qiang Yang Hong Kong University of Science and Technology Microsoft Research Asia WWW 2010

More information

Advanced Topics in Information Retrieval. Learning to Rank. ATIR July 14, 2016

Advanced Topics in Information Retrieval. Learning to Rank. ATIR July 14, 2016 Advanced Topics in Information Retrieval Learning to Rank Vinay Setty vsetty@mpi-inf.mpg.de Jannik Strötgen jannik.stroetgen@mpi-inf.mpg.de ATIR July 14, 2016 Before we start oral exams July 28, the full

More information

A Formal Approach to Score Normalization for Meta-search

A Formal Approach to Score Normalization for Meta-search A Formal Approach to Score Normalization for Meta-search R. Manmatha and H. Sever Center for Intelligent Information Retrieval Computer Science Department University of Massachusetts Amherst, MA 01003

More information

Improving Patent Search by Search Result Diversification

Improving Patent Search by Search Result Diversification Improving Patent Search by Search Result Diversification Youngho Kim University of Massachusetts Amherst yhkim@cs.umass.edu W. Bruce Croft University of Massachusetts Amherst croft@cs.umass.edu ABSTRACT

More information

University of Virginia Department of Computer Science. CS 4501: Information Retrieval Fall 2015

University of Virginia Department of Computer Science. CS 4501: Information Retrieval Fall 2015 University of Virginia Department of Computer Science CS 4501: Information Retrieval Fall 2015 5:00pm-6:15pm, Monday, October 26th Name: ComputingID: This is a closed book and closed notes exam. No electronic

More information

Ranking with Query-Dependent Loss for Web Search

Ranking with Query-Dependent Loss for Web Search Ranking with Query-Dependent Loss for Web Search Jiang Bian 1, Tie-Yan Liu 2, Tao Qin 2, Hongyuan Zha 1 Georgia Institute of Technology 1 Microsoft Research Asia 2 Outline Motivation Incorporating Query

More information

Jianyong Wang Department of Computer Science and Technology Tsinghua University

Jianyong Wang Department of Computer Science and Technology Tsinghua University Jianyong Wang Department of Computer Science and Technology Tsinghua University jianyong@tsinghua.edu.cn Joint work with Wei Shen (Tsinghua), Ping Luo (HP), and Min Wang (HP) Outline Introduction to entity

More information

Query Expansion using Wikipedia and DBpedia

Query Expansion using Wikipedia and DBpedia Query Expansion using Wikipedia and DBpedia Nitish Aggarwal and Paul Buitelaar Unit for Natural Language Processing, Digital Enterprise Research Institute, National University of Ireland, Galway firstname.lastname@deri.org

More information

A Machine Learning Approach for Information Retrieval Applications. Luo Si. Department of Computer Science Purdue University

A Machine Learning Approach for Information Retrieval Applications. Luo Si. Department of Computer Science Purdue University A Machine Learning Approach for Information Retrieval Applications Luo Si Department of Computer Science Purdue University Why Information Retrieval: Information Overload: Since the introduction of digital

More information

Query Transformations for Result Merging

Query Transformations for Result Merging Query Transformations for Result Merging Shriphani Palakodety School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213, USA spalakod@cs.cmu.edu Jamie Callan School of Computer Science

More information

A New Approach to Query Segmentation for Relevance Ranking in Web Search

A New Approach to Query Segmentation for Relevance Ranking in Web Search Noname manuscript No. (will be inserted by the editor) A New Approach to Query Segmentation for Relevance Ranking in Web Search Haocheng Wu Yunhua Hu Hang Li Enhong Chen Received: date / Accepted: date

More information

Learning Semantic Entity Representations with Knowledge Graph and Deep Neural Networks and its Application to Named Entity Disambiguation

Learning Semantic Entity Representations with Knowledge Graph and Deep Neural Networks and its Application to Named Entity Disambiguation Learning Semantic Entity Representations with Knowledge Graph and Deep Neural Networks and its Application to Named Entity Disambiguation Hongzhao Huang 1 and Larry Heck 2 Computer Science Department,

More information

Modern Retrieval Evaluations. Hongning Wang

Modern Retrieval Evaluations. Hongning Wang Modern Retrieval Evaluations Hongning Wang CS@UVa What we have known about IR evaluations Three key elements for IR evaluation A document collection A test suite of information needs A set of relevance

More information

CS473: Course Review CS-473. Luo Si Department of Computer Science Purdue University

CS473: Course Review CS-473. Luo Si Department of Computer Science Purdue University CS473: CS-473 Course Review Luo Si Department of Computer Science Purdue University Basic Concepts of IR: Outline Basic Concepts of Information Retrieval: Task definition of Ad-hoc IR Terminologies and

More information

On Duplicate Results in a Search Session

On Duplicate Results in a Search Session On Duplicate Results in a Search Session Jiepu Jiang Daqing He Shuguang Han School of Information Sciences University of Pittsburgh jiepu.jiang@gmail.com dah44@pitt.edu shh69@pitt.edu ABSTRACT In this

More information

Information Retrieval and Web Search

Information Retrieval and Web Search Information Retrieval and Web Search Introduction to IR models and methods Rada Mihalcea (Some of the slides in this slide set come from IR courses taught at UT Austin and Stanford) Information Retrieval

More information

Diversification of Query Interpretations and Search Results

Diversification of Query Interpretations and Search Results Diversification of Query Interpretations and Search Results Advanced Methods of IR Elena Demidova Materials used in the slides: Charles L.A. Clarke, Maheedhar Kolla, Gordon V. Cormack, Olga Vechtomova,

More information

Information Retrieval (Part 1)

Information Retrieval (Part 1) Information Retrieval (Part 1) Fabio Aiolli http://www.math.unipd.it/~aiolli Dipartimento di Matematica Università di Padova Anno Accademico 2008/2009 1 Bibliographic References Copies of slides Selected

More information

Is Brad Pitt Related to Backstreet Boys? Exploring Related Entities

Is Brad Pitt Related to Backstreet Boys? Exploring Related Entities Is Brad Pitt Related to Backstreet Boys? Exploring Related Entities Nitish Aggarwal, Kartik Asooja, Paul Buitelaar, and Gabriela Vulcu Unit for Natural Language Processing Insight-centre, National University

More information

Learning to Match using Local and Distributed Representations of Text for Web Search

Learning to Match using Local and Distributed Representations of Text for Web Search Learning to Match using Local and Distributed Representations of Text for Web Search Bhaskar Mitra 1,2, Fernando Diaz 1, and Nick Craswell 1 1 Microsoft, {bmitra, fdiaz, nickcr}@microsoft.com 2 University

More information

The University of Amsterdam at the CLEF 2008 Domain Specific Track

The University of Amsterdam at the CLEF 2008 Domain Specific Track The University of Amsterdam at the CLEF 2008 Domain Specific Track Parsimonious Relevance and Concept Models Edgar Meij emeij@science.uva.nl ISLA, University of Amsterdam Maarten de Rijke mdr@science.uva.nl

More information

Word Embedding for Social Book Suggestion

Word Embedding for Social Book Suggestion Word Embedding for Social Book Suggestion Nawal Ould-Amer 1, Philippe Mulhem 1, Mathias Géry 2, and Karam Abdulahhad 1 1 Univ. Grenoble Alpes, LIG, F-38000 Grenoble, France CNRS, LIG, F-38000 Grenoble,

More information

Query Likelihood with Negative Query Generation

Query Likelihood with Negative Query Generation Query Likelihood with Negative Query Generation Yuanhua Lv Department of Computer Science University of Illinois at Urbana-Champaign Urbana, IL 61801 ylv2@uiuc.edu ChengXiang Zhai Department of Computer

More information

Exploring Reductions for Long Web Queries

Exploring Reductions for Long Web Queries Exploring Reductions for Long Web Queries Niranjan Balasubramanian University of Massachusetts Amherst 140 Governors Drive, Amherst, MA 01003 niranjan@cs.umass.edu Giridhar Kumaran and Vitor R. Carvalho

More information

Interpreting Document Collections with Topic Models. Nikolaos Aletras University College London

Interpreting Document Collections with Topic Models. Nikolaos Aletras University College London Interpreting Document Collections with Topic Models Nikolaos Aletras University College London Acknowledgements Mark Stevenson, Sheffield Tim Baldwin, Melbourne Jey Han Lau, IBM Research Talk Outline Introduction

More information

Automatic Summarization

Automatic Summarization Automatic Summarization CS 769 Guest Lecture Andrew B. Goldberg goldberg@cs.wisc.edu Department of Computer Sciences University of Wisconsin, Madison February 22, 2008 Andrew B. Goldberg (CS Dept) Summarization

More information

A Comparative Analysis of Cascade Measures for Novelty and Diversity

A Comparative Analysis of Cascade Measures for Novelty and Diversity A Comparative Analysis of Cascade Measures for Novelty and Diversity Charles Clarke, University of Waterloo Nick Craswell, Microsoft Ian Soboroff, NIST Azin Ashkan, University of Waterloo Background Measuring

More information