@inproceedings{chen-etal-2024-improving-retrieval,
title = "Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts",
author = "Chen, Zhuo and
Wang, Xinyu and
Jiang, Yong and
Xie, Pengjun and
Huang, Fei and
Tu, Kewei",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.458",
pages = "7683--7694",
abstract = "In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of context is often limited, and it becomes challenging to empower the model to cover overlong contexts while answering questions from open domains. This paper proposes a general and convenient method to cover longer contexts in Open-Domain Question-Answering tasks. {\%}It leverages a small encoder language model that effectively encodes contexts, and the encoding applies cross-attention with origin inputs.It leverages a small encoder and cross-attention mechanism and effectively encodes contexts. With our method, the original language models can cover several times longer contexts while keeping the computing requirements close to the baseline. Our experiments demonstrate that after fine-tuning, there is improved performance across two held-in datasets, four held-out datasets, and also in two In Context Learning settings. Our code will be released at https://github.com/Alibaba-NLP/Vec-RA-ODQA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-improving-retrieval">
<titleInfo>
<title>Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengjun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of context is often limited, and it becomes challenging to empower the model to cover overlong contexts while answering questions from open domains. This paper proposes a general and convenient method to cover longer contexts in Open-Domain Question-Answering tasks. %It leverages a small encoder language model that effectively encodes contexts, and the encoding applies cross-attention with origin inputs.It leverages a small encoder and cross-attention mechanism and effectively encodes contexts. With our method, the original language models can cover several times longer contexts while keeping the computing requirements close to the baseline. Our experiments demonstrate that after fine-tuning, there is improved performance across two held-in datasets, four held-out datasets, and also in two In Context Learning settings. Our code will be released at https://github.com/Alibaba-NLP/Vec-RA-ODQA.</abstract>
<identifier type="citekey">chen-etal-2024-improving-retrieval</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.458</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7683</start>
<end>7694</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
%A Chen, Zhuo
%A Wang, Xinyu
%A Jiang, Yong
%A Xie, Pengjun
%A Huang, Fei
%A Tu, Kewei
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F chen-etal-2024-improving-retrieval
%X In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of context is often limited, and it becomes challenging to empower the model to cover overlong contexts while answering questions from open domains. This paper proposes a general and convenient method to cover longer contexts in Open-Domain Question-Answering tasks. %It leverages a small encoder language model that effectively encodes contexts, and the encoding applies cross-attention with origin inputs.It leverages a small encoder and cross-attention mechanism and effectively encodes contexts. With our method, the original language models can cover several times longer contexts while keeping the computing requirements close to the baseline. Our experiments demonstrate that after fine-tuning, there is improved performance across two held-in datasets, four held-out datasets, and also in two In Context Learning settings. Our code will be released at https://github.com/Alibaba-NLP/Vec-RA-ODQA.
%U https://aclanthology.org/2024.findings-acl.458
%P 7683-7694
Markdown (Informal)
[Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts](https://aclanthology.org/2024.findings-acl.458) (Chen et al., Findings 2024)
ACL