@inproceedings{gonzalez-etal-2018-strong,
title = "A strong baseline for question relevancy ranking",
author = "Gonzalez, Ana and
Augenstein, Isabelle and
S{\o}gaard, Anders",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1515",
doi = "10.18653/v1/D18-1515",
pages = "4810--4815",
abstract = "The best systems at the SemEval-16 and SemEval-17 community question answering shared tasks {--} a task that amounts to question relevancy ranking {--} involve complex pipelines and manual feature engineering. Despite this, many of these still fail at beating the IR baseline, i.e., the rankings provided by Google{'}s search engine. We present a strong baseline for question relevancy ranking by training a simple multi-task feed forward network on a bag of 14 distance measures for the input question pair. This baseline model, which is fast to train and uses only language-independent features, outperforms the best shared task systems on the task of retrieving relevant previously asked questions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-etal-2018-strong">
<titleInfo>
<title>A strong baseline for question relevancy ranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Gonzalez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The best systems at the SemEval-16 and SemEval-17 community question answering shared tasks – a task that amounts to question relevancy ranking – involve complex pipelines and manual feature engineering. Despite this, many of these still fail at beating the IR baseline, i.e., the rankings provided by Google’s search engine. We present a strong baseline for question relevancy ranking by training a simple multi-task feed forward network on a bag of 14 distance measures for the input question pair. This baseline model, which is fast to train and uses only language-independent features, outperforms the best shared task systems on the task of retrieving relevant previously asked questions.</abstract>
<identifier type="citekey">gonzalez-etal-2018-strong</identifier>
<identifier type="doi">10.18653/v1/D18-1515</identifier>
<location>
<url>https://aclanthology.org/D18-1515</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>4810</start>
<end>4815</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A strong baseline for question relevancy ranking
%A Gonzalez, Ana
%A Augenstein, Isabelle
%A Søgaard, Anders
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F gonzalez-etal-2018-strong
%X The best systems at the SemEval-16 and SemEval-17 community question answering shared tasks – a task that amounts to question relevancy ranking – involve complex pipelines and manual feature engineering. Despite this, many of these still fail at beating the IR baseline, i.e., the rankings provided by Google’s search engine. We present a strong baseline for question relevancy ranking by training a simple multi-task feed forward network on a bag of 14 distance measures for the input question pair. This baseline model, which is fast to train and uses only language-independent features, outperforms the best shared task systems on the task of retrieving relevant previously asked questions.
%R 10.18653/v1/D18-1515
%U https://aclanthology.org/D18-1515
%U https://doi.org/10.18653/v1/D18-1515
%P 4810-4815
Markdown (Informal)
[A strong baseline for question relevancy ranking](https://aclanthology.org/D18-1515) (Gonzalez et al., EMNLP 2018)
ACL
- Ana Gonzalez, Isabelle Augenstein, and Anders Søgaard. 2018. A strong baseline for question relevancy ranking. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4810–4815, Brussels, Belgium. Association for Computational Linguistics.