Dimension Projection Among Languages Based on Pseudo-Relevant Documents for Query Translation

Using top-ranked documents retrieved in response to a query of a user has been shown to be an effective approach to improve the quality of query translation in dictionary-based cross-language information retrieval. In this paper, we propose a new method for dictionary-based query translation based on dimension projection of embedded vectors from the pseudo-relevant documents in the source language to their equivalents in the target language. To this end, first we learn low-dimensional vectors of the words in the pseudo-relevant collections separately and then aim to find a query-dependent transformation matrix between the vectors of translation pairs appeared in the collections. At the next step, the representation of each query term is projected to the target language and then, after using a softmax function, a translation model is built. Finally, the model is used for query translation. Our experiments on four CLEF collections in French, Spanish, German, and Italian demonstrate that the proposed method outperforms competitive baselines including a word embedding baseline based on bilingual shuffling. The proposed method reaches up to 87% performance of machine translation (MT) in short queries and considerable improvements in verbose queries.

[1]  Azadeh Shakery,et al.  Mining a Persian-English comparable corpus for cross-language information retrieval , 2014, Inf. Process. Manag..

[2]  W. Bruce Croft,et al.  Relevance-Based Language Models , 2001, SIGIR '01.

[3]  ChengXiang Zhai,et al.  Positional relevance model for pseudo-relevance feedback , 2010, SIGIR.

[4]  W. Bruce Croft,et al.  Cross-lingual relevance models , 2002, SIGIR '02.

[5]  Gareth J. F. Jones,et al.  Topical Relevance Model , 2012, AIRS.

[6]  Yoshua Bengio,et al.  BilBOWA: Fast Bilingual Distributed Representations without Word Alignments , 2014, ICML.

[7]  John D. Lafferty,et al.  Model-based feedback in the language modeling approach to information retrieval , 2001, CIKM '01.

[8]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[9]  Ahmet Aker,et al.  Bilingual dictionaries for all EU languages , 2014, LREC.

[10]  Quoc V. Le,et al.  Exploiting Similarities among Languages for Machine Translation , 2013, ArXiv.

[11]  Marie-Francine Moens,et al.  Monolingual and Cross-Lingual Information Retrieval Models Based on (Bilingual) Word Embeddings , 2015, SIGIR.

[12]  ChengXiang Zhai,et al.  Revisiting the Divergence Minimization Feedback Model , 2014, CIKM.

[13]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[14]  Azadeh Shakery,et al.  Pseudo-Relevance Feedback Based on Matrix Factorization , 2016, CIKM.

[15]  Gareth J. F. Jones,et al.  Cross-Lingual Topical Relevance Models , 2012, COLING.

[16]  Yanjun Ma,et al.  Opening Machine Translation Black Box for Cross-Language Information Retrieval , 2012, AIRS.

[17]  Marie-Francine Moens,et al.  Probabilistic topic modeling in multilingual settings: An overview of its methodology and applications , 2015, Inf. Process. Manag..

[18]  Christof Monz,et al.  Iterative translation disambiguation for cross-language information retrieval , 2005, SIGIR '05.