@inproceedings{dadashkarimi-etal-2016-learning,
title = "Learning to Weight Translations using Ordinal Linear Regression and Query-generated Training Data for Ad-hoc Retrieval with Long Queries",
author = "Dadashkarimi, Javid and
Jalili Sabet, Masoud and
Shakery, Azadeh",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1162",
pages = "1725--1733",
abstract = "Ordinal regression which is known with learning to rank has long been used in information retrieval (IR). Learning to rank algorithms, have been tailored in document ranking, information filtering, and building large aligned corpora successfully. In this paper, we propose to use this algorithm for query modeling in cross-language environments. To this end, first we build a query-generated training data using pseudo-relevant documents to the query and all translation candidates. The pseudo-relevant documents are obtained by top-ranked documents in response to a translation of the original query. The class of each candidate in the training data is determined based on presence/absence of the candidate in the pseudo-relevant documents. We learn an ordinal regression model to score the candidates based on their relevance to the context of the query, and after that, we construct a query-dependent translation model using a softmax function. Finally, we re-weight the query based on the obtained model. Experimental results on French, German, Spanish, and Italian CLEF collections demonstrate that the proposed method achieves better results compared to state-of-the-art cross-language information retrieval methods, particularly in long queries with large training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dadashkarimi-etal-2016-learning">
<titleInfo>
<title>Learning to Weight Translations using Ordinal Linear Regression and Query-generated Training Data for Ad-hoc Retrieval with Long Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javid</namePart>
<namePart type="family">Dadashkarimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masoud</namePart>
<namePart type="family">Jalili Sabet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azadeh</namePart>
<namePart type="family">Shakery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ordinal regression which is known with learning to rank has long been used in information retrieval (IR). Learning to rank algorithms, have been tailored in document ranking, information filtering, and building large aligned corpora successfully. In this paper, we propose to use this algorithm for query modeling in cross-language environments. To this end, first we build a query-generated training data using pseudo-relevant documents to the query and all translation candidates. The pseudo-relevant documents are obtained by top-ranked documents in response to a translation of the original query. The class of each candidate in the training data is determined based on presence/absence of the candidate in the pseudo-relevant documents. We learn an ordinal regression model to score the candidates based on their relevance to the context of the query, and after that, we construct a query-dependent translation model using a softmax function. Finally, we re-weight the query based on the obtained model. Experimental results on French, German, Spanish, and Italian CLEF collections demonstrate that the proposed method achieves better results compared to state-of-the-art cross-language information retrieval methods, particularly in long queries with large training data.</abstract>
<identifier type="citekey">dadashkarimi-etal-2016-learning</identifier>
<location>
<url>https://aclanthology.org/C16-1162</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>1725</start>
<end>1733</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Weight Translations using Ordinal Linear Regression and Query-generated Training Data for Ad-hoc Retrieval with Long Queries
%A Dadashkarimi, Javid
%A Jalili Sabet, Masoud
%A Shakery, Azadeh
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F dadashkarimi-etal-2016-learning
%X Ordinal regression which is known with learning to rank has long been used in information retrieval (IR). Learning to rank algorithms, have been tailored in document ranking, information filtering, and building large aligned corpora successfully. In this paper, we propose to use this algorithm for query modeling in cross-language environments. To this end, first we build a query-generated training data using pseudo-relevant documents to the query and all translation candidates. The pseudo-relevant documents are obtained by top-ranked documents in response to a translation of the original query. The class of each candidate in the training data is determined based on presence/absence of the candidate in the pseudo-relevant documents. We learn an ordinal regression model to score the candidates based on their relevance to the context of the query, and after that, we construct a query-dependent translation model using a softmax function. Finally, we re-weight the query based on the obtained model. Experimental results on French, German, Spanish, and Italian CLEF collections demonstrate that the proposed method achieves better results compared to state-of-the-art cross-language information retrieval methods, particularly in long queries with large training data.
%U https://aclanthology.org/C16-1162
%P 1725-1733
Markdown (Informal)
[Learning to Weight Translations using Ordinal Linear Regression and Query-generated Training Data for Ad-hoc Retrieval with Long Queries](https://aclanthology.org/C16-1162) (Dadashkarimi et al., COLING 2016)
ACL