Exploiting Bilingual Information to Improve Web Search

Web search quality can vary widely across languages, even for the same information need. We propose to exploit this variation in quality by learning a ranking function on bilingual queries: queries that appear in query logs for two languages but represent equivalent search interests. For a given bilingual query, along with corresponding monolingual query log and monolingual ranking, we generate a ranking on pairs of documents, one from each language. Then we learn a linear ranking function which exploits bilingual features on pairs of documents, as well as standard monolingual features. Finally, we show how to reconstruct monolingual ranking from a learned bilingual ranking. Using publicly available Chinese and English query logs, we demonstrate for both languages that our ranking technique exploiting bilingual data leads to significant improvements over a state-of-the-art monolingual ranking algorithm.

• Publication year

  2009

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2009-08-02

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/1690219.1690296
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unsupervised Constraint Driven Learning For Transliteration Discovery

  2009cited by this paper
• Bilingual topic aspect classification with a few training examples

  2008cited by this paper
• Two Languages are Better than One (for Syntactic Parsing)

  2008cited by this paper
• Unsupervised Multilingual Learning for Morphological Segmentation

  2008cited by this paper
• Are click-through data adequate for learning web search rankings?

  2008influential reference
• Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web search

  2007cited by this paper
• Automatic search engine performance evaluation with click-through data analysis

  2007influential reference
• Supervised rank aggregation

  2007influential reference
• A comparison of statistical significance tests for information retrieval evaluation

  2007influential reference
• LETOR: Benchmark Dataset for Research on Learning to Rank for Information Retrieval

  2007influential reference
• A picture of search

  2006cited by this paper
• Bootstrapping parsers via syntactic projection across parallel texts

  2005cited by this paper
• Bilingual Parsing with Factored Estimation: Using English to Parse Korean

  2004cited by this paper
• Multilingual document clusters discovery

  2004cited by this paper
• Cross-lingual relevance models

  2002cited by this paper
• Optimizing search engines using clickthrough data

  2002influential reference
• Rank aggregation methods for the Web

  2001cited by this paper
• Introduction to Algorithms, 2nd edition.

  2001cited by this paper
• A study of smoothing methods for language models applied to Ad Hoc information retrieval

  2001cited by this paper
• Large margin rank boundaries for ordinal regression

  2000influential reference
• IR evaluation methods for retrieving highly relevant documents

  2000cited by this paper
• The Anatomy of a Large-Scale Hypertextual Web Search Engine

  1998cited by this paper
• Overview of the Okapi projects

  1997influential reference
• Introduction to algorithms

  1996cited by this paper
• Automatic text processing

  1988cited by this paper
• Relevance weighting of search terms

  1976cited by this paper
• A NEW MEASURE OF RANK CORRELATION

  1938cited by this paper
• Mathematical Programming manuscript No. (will be inserted by the editor) Pegasos: Primal Estimated sub-GrAdient SOlver for SVM

  year unknowncited by this paper

• Query-dependent learning to rank for cross-lingual information retrieval

  2018influential citation
• Emotion Analysis in Code-Switching Text With Joint Factor Graph Model

  2017cites this paper
• Online Learning to Rank for Cross-Language Information Retrieval

  2017cites this paper
• A Bilingual Attention Network for Code-switched Emotion Prediction

  2016cites this paper
• Emotion in Code-switching Texts: Corpus Construction and Analysis

  2015cites this paper
• Multi-view learning for emotion detection in code-switching texts

  2015cites this paper
• Information-Theoretic Multi-view Domain Adaptation: A Theoretical and Empirical Study

  2014cites this paper
• Discriminative Interlingual Representations

  2013cites this paper
• Joint Bilingual Sentiment Classification with Unlabeled Parallel Corpora

  2011cites this paper
• From Bilingual Dictionaries to Interlingual Document Representations

  2011cites this paper
• Improving Bilingual Projections via Sparse Covariance Matrices

  2011cites this paper
• Enriching document representation via translation for improved monolingual information retrieval

  2011cites this paper
• Learning to Rank with Supplementary Data

  2010cites this paper