@inproceedings{campese-etal-2024-pre,
title = "Pre-Training Methods for Question Reranking",
author = "Campese, Stefano and
Lauriola, Ivano and
Moschitti, Alessandro",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-short.41",
pages = "469--476",
abstract = "One interesting approach to Question Answering (QA) is to search for semantically similar questions, which have been answered before. This task is different from answer retrieval as it focuses on questions rather than only on the answers, therefore it requires different model training on different data.In this work, we introduce a novel unsupervised pre-training method specialized for retrieving and ranking questions. This leverages (i) knowledge distillation from a basic question retrieval model, and (ii) new pre-training task and objective for learning to rank questions in terms of their relevance with the query. Our experiments show that (i) the proposed technique achieves state-of-the-art performance on QRC and Quora-match datasets, and (ii) the benefit of combining re-ranking and retrieval models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="campese-etal-2024-pre">
<titleInfo>
<title>Pre-Training Methods for Question Reranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Campese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivano</namePart>
<namePart type="family">Lauriola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One interesting approach to Question Answering (QA) is to search for semantically similar questions, which have been answered before. This task is different from answer retrieval as it focuses on questions rather than only on the answers, therefore it requires different model training on different data.In this work, we introduce a novel unsupervised pre-training method specialized for retrieving and ranking questions. This leverages (i) knowledge distillation from a basic question retrieval model, and (ii) new pre-training task and objective for learning to rank questions in terms of their relevance with the query. Our experiments show that (i) the proposed technique achieves state-of-the-art performance on QRC and Quora-match datasets, and (ii) the benefit of combining re-ranking and retrieval models.</abstract>
<identifier type="citekey">campese-etal-2024-pre</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-short.41</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>469</start>
<end>476</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-Training Methods for Question Reranking
%A Campese, Stefano
%A Lauriola, Ivano
%A Moschitti, Alessandro
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F campese-etal-2024-pre
%X One interesting approach to Question Answering (QA) is to search for semantically similar questions, which have been answered before. This task is different from answer retrieval as it focuses on questions rather than only on the answers, therefore it requires different model training on different data.In this work, we introduce a novel unsupervised pre-training method specialized for retrieving and ranking questions. This leverages (i) knowledge distillation from a basic question retrieval model, and (ii) new pre-training task and objective for learning to rank questions in terms of their relevance with the query. Our experiments show that (i) the proposed technique achieves state-of-the-art performance on QRC and Quora-match datasets, and (ii) the benefit of combining re-ranking and retrieval models.
%U https://aclanthology.org/2024.eacl-short.41
%P 469-476
Markdown (Informal)
[Pre-Training Methods for Question Reranking](https://aclanthology.org/2024.eacl-short.41) (Campese et al., EACL 2024)
ACL
- Stefano Campese, Ivano Lauriola, and Alessandro Moschitti. 2024. Pre-Training Methods for Question Reranking. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 469–476, St. Julian’s, Malta. Association for Computational Linguistics.