@inproceedings{yang-etal-2021-neural-retrieval,
title = "Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation",
author = "Yang, Yinfei and
Jin, Ning and
Lin, Kuo and
Guo, Mandy and
Cer, Daniel",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.35",
doi = "10.18653/v1/2021.acl-short.35",
pages = "263--268",
abstract = "Early fusion models with cross-attention have shown better-than-human performance on some question answer benchmarks, while it is a poor fit for retrieval since it prevents pre-computation of the answer representations. We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. We first train an accurate classification model with cross-attention between questions and answers. The cross-attention model is then used to annotate additional passages in order to generate weighted training examples for a neural retrieval model. The resulting retrieval model with additional data significantly outperforms retrieval models directly trained with gold annotations on Precision at N (P@N) and Mean Reciprocal Rank (MRR).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-neural-retrieval">
<titleInfo>
<title>Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinfei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuo</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandy</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Early fusion models with cross-attention have shown better-than-human performance on some question answer benchmarks, while it is a poor fit for retrieval since it prevents pre-computation of the answer representations. We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. We first train an accurate classification model with cross-attention between questions and answers. The cross-attention model is then used to annotate additional passages in order to generate weighted training examples for a neural retrieval model. The resulting retrieval model with additional data significantly outperforms retrieval models directly trained with gold annotations on Precision at N (P@N) and Mean Reciprocal Rank (MRR).</abstract>
<identifier type="citekey">yang-etal-2021-neural-retrieval</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.35</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.35</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>263</start>
<end>268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation
%A Yang, Yinfei
%A Jin, Ning
%A Lin, Kuo
%A Guo, Mandy
%A Cer, Daniel
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F yang-etal-2021-neural-retrieval
%X Early fusion models with cross-attention have shown better-than-human performance on some question answer benchmarks, while it is a poor fit for retrieval since it prevents pre-computation of the answer representations. We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. We first train an accurate classification model with cross-attention between questions and answers. The cross-attention model is then used to annotate additional passages in order to generate weighted training examples for a neural retrieval model. The resulting retrieval model with additional data significantly outperforms retrieval models directly trained with gold annotations on Precision at N (P@N) and Mean Reciprocal Rank (MRR).
%R 10.18653/v1/2021.acl-short.35
%U https://aclanthology.org/2021.acl-short.35
%U https://doi.org/10.18653/v1/2021.acl-short.35
%P 263-268
Markdown (Informal)
[Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation](https://aclanthology.org/2021.acl-short.35) (Yang et al., ACL-IJCNLP 2021)
ACL