@inproceedings{hazem-etal-2017-mappsent,
title = "{M}app{S}ent: a Textual Mapping Approach for Question-to-Question Similarity",
author = "Hazem, Amir and
El Amel Boussaha, Basma and
Hernandez, Nicolas",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_040",
doi = "10.26615/978-954-452-049-6_040",
pages = "291--300",
abstract = "Since the advent of word embedding methods, the representation of longer pieces of texts such as sentences and paragraphs is gaining more and more interest, especially for textual similarity tasks. Mikolov et al. (2013) have demonstrated that words and phrases exhibit linear structures that allow to meaningfully combine words by an element-wise addition of their vector representations. Recently, Arora et al. (2017) have shown that removing the projections of the weighted average sum of word embedding vectors on their first principal components, outperforms sophisticated supervised methods including RNN{'}s and LSTM{'}s. Inspired by Mikolov et al. (2013) and Arora et al. (2017) findings and by a bilingual word mapping technique presented in Artetxe et al. (2016), we introduce MappSent, a novel approach for textual similarity. Based on a linear sentence embedding representation, its principle is to build a matrix that maps sentences in a joint-subspace where similar sets of sentences are pushed closer. We evaluate our approach on the SemEval 2016/2017 question-to-question similarity task and show that overall MappSent achieves competitive results and outperforms in most cases state-of-art methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazem-etal-2017-mappsent">
<titleInfo>
<title>MappSent: a Textual Mapping Approach for Question-to-Question Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hazem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Basma</namePart>
<namePart type="family">El Amel Boussaha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Since the advent of word embedding methods, the representation of longer pieces of texts such as sentences and paragraphs is gaining more and more interest, especially for textual similarity tasks. Mikolov et al. (2013) have demonstrated that words and phrases exhibit linear structures that allow to meaningfully combine words by an element-wise addition of their vector representations. Recently, Arora et al. (2017) have shown that removing the projections of the weighted average sum of word embedding vectors on their first principal components, outperforms sophisticated supervised methods including RNN’s and LSTM’s. Inspired by Mikolov et al. (2013) and Arora et al. (2017) findings and by a bilingual word mapping technique presented in Artetxe et al. (2016), we introduce MappSent, a novel approach for textual similarity. Based on a linear sentence embedding representation, its principle is to build a matrix that maps sentences in a joint-subspace where similar sets of sentences are pushed closer. We evaluate our approach on the SemEval 2016/2017 question-to-question similarity task and show that overall MappSent achieves competitive results and outperforms in most cases state-of-art methods.</abstract>
<identifier type="citekey">hazem-etal-2017-mappsent</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_040</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>291</start>
<end>300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MappSent: a Textual Mapping Approach for Question-to-Question Similarity
%A Hazem, Amir
%A El Amel Boussaha, Basma
%A Hernandez, Nicolas
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F hazem-etal-2017-mappsent
%X Since the advent of word embedding methods, the representation of longer pieces of texts such as sentences and paragraphs is gaining more and more interest, especially for textual similarity tasks. Mikolov et al. (2013) have demonstrated that words and phrases exhibit linear structures that allow to meaningfully combine words by an element-wise addition of their vector representations. Recently, Arora et al. (2017) have shown that removing the projections of the weighted average sum of word embedding vectors on their first principal components, outperforms sophisticated supervised methods including RNN’s and LSTM’s. Inspired by Mikolov et al. (2013) and Arora et al. (2017) findings and by a bilingual word mapping technique presented in Artetxe et al. (2016), we introduce MappSent, a novel approach for textual similarity. Based on a linear sentence embedding representation, its principle is to build a matrix that maps sentences in a joint-subspace where similar sets of sentences are pushed closer. We evaluate our approach on the SemEval 2016/2017 question-to-question similarity task and show that overall MappSent achieves competitive results and outperforms in most cases state-of-art methods.
%R 10.26615/978-954-452-049-6_040
%U https://doi.org/10.26615/978-954-452-049-6_040
%P 291-300
Markdown (Informal)
[MappSent: a Textual Mapping Approach for Question-to-Question Similarity](https://doi.org/10.26615/978-954-452-049-6_040) (Hazem et al., RANLP 2017)
ACL