@inproceedings{mirisaee-etal-2019-terminology,
title = "Terminology-based Text Embedding for Computing Document Similarities on Technical Content",
author = "Mirisaee, Hamid and
Gaussier, Eric and
Lagnier, Cedric and
Guerraz, Agnes",
editor = "Morin, Emmanuel and
Rosset, Sophie and
Zweigenbaum, Pierre",
booktitle = "Actes de la Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles (TALN) PFIA 2019. Terminologie et Intelligence Artificielle (atelier TALN-RECITAL {\textbackslash}{\&} IC)",
month = "7",
year = "2019",
address = "Toulouse, France",
publisher = "ATALA",
url = "https://aclanthology.org/2019.jeptalnrecital-tia.3",
pages = "31--42",
abstract = "We propose in this paper a new, hybrid document embedding approach in order to address the problem of document similarities with respect to the technical content. To do so, we employ a state-of-the-art graph techniques to first extract the keyphrases (composite keywords) of documents and, then, use them to score the sentences. Using the ranked sentences, we propose two approaches to embed documents and show their performances with respect to two baselines. With domain expert annotations, we illustrate that the proposed methods can find more relevant documents and outperform the baselines up to 27{\%} in terms of NDCG.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mirisaee-etal-2019-terminology">
<titleInfo>
<title>Terminology-based Text Embedding for Computing Document Similarities on Technical Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamid</namePart>
<namePart type="family">Mirisaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Gaussier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cedric</namePart>
<namePart type="family">Lagnier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnes</namePart>
<namePart type="family">Guerraz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) PFIA 2019. Terminologie et Intelligence Artificielle (atelier TALN-RECITAL \textbackslash& IC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Morin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA</publisher>
<place>
<placeTerm type="text">Toulouse, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose in this paper a new, hybrid document embedding approach in order to address the problem of document similarities with respect to the technical content. To do so, we employ a state-of-the-art graph techniques to first extract the keyphrases (composite keywords) of documents and, then, use them to score the sentences. Using the ranked sentences, we propose two approaches to embed documents and show their performances with respect to two baselines. With domain expert annotations, we illustrate that the proposed methods can find more relevant documents and outperform the baselines up to 27% in terms of NDCG.</abstract>
<identifier type="citekey">mirisaee-etal-2019-terminology</identifier>
<location>
<url>https://aclanthology.org/2019.jeptalnrecital-tia.3</url>
</location>
<part>
<date>2019-7</date>
<extent unit="page">
<start>31</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Terminology-based Text Embedding for Computing Document Similarities on Technical Content
%A Mirisaee, Hamid
%A Gaussier, Eric
%A Lagnier, Cedric
%A Guerraz, Agnes
%Y Morin, Emmanuel
%Y Rosset, Sophie
%Y Zweigenbaum, Pierre
%S Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) PFIA 2019. Terminologie et Intelligence Artificielle (atelier TALN-RECITAL \textbackslash& IC)
%D 2019
%8 July
%I ATALA
%C Toulouse, France
%F mirisaee-etal-2019-terminology
%X We propose in this paper a new, hybrid document embedding approach in order to address the problem of document similarities with respect to the technical content. To do so, we employ a state-of-the-art graph techniques to first extract the keyphrases (composite keywords) of documents and, then, use them to score the sentences. Using the ranked sentences, we propose two approaches to embed documents and show their performances with respect to two baselines. With domain expert annotations, we illustrate that the proposed methods can find more relevant documents and outperform the baselines up to 27% in terms of NDCG.
%U https://aclanthology.org/2019.jeptalnrecital-tia.3
%P 31-42
Markdown (Informal)
[Terminology-based Text Embedding for Computing Document Similarities on Technical Content](https://aclanthology.org/2019.jeptalnrecital-tia.3) (Mirisaee et al., JEP/TALN/RECITAL 2019)
ACL