@inproceedings{mallick-etal-2023-adapting,
title = "Adapting Pre-trained Generative Models for Extractive Question Answering",
author = "Mallick, Prabir and
Nayak, Tapas and
Bhattacharya, Indrajit",
editor = "Gehrmann, Sebastian and
Wang, Alex and
Sedoc, Jo{\~a}o and
Clark, Elizabeth and
Dhole, Kaustubh and
Chandu, Khyathi Raghavi and
Santus, Enrico and
Sedghamiz, Hooman",
booktitle = "Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.gem-1.11",
pages = "128--137",
abstract = "Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization. However, the potential of generative models in extractive QA tasks, where discriminative models are commonly employed, remains largely unexplored. Discriminative models often encounter challenges associated with label sparsity, particularly when only a small portion of the context contains the answer. The challenge is more pronounced for multi-span answers. In this work, we introduce a novel approach that uses the power of pre-trained generative models to address extractive QA tasks by generating indexes corresponding to context tokens or sentences that form part of the answer. Through comprehensive evaluations on multiple extractive QA datasets, including MultiSpanQA, BioASQ, MASHQA, and WikiQA, we demonstrate the superior performance of our proposed approach compared to existing state-of-the-art models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mallick-etal-2023-adapting">
<titleInfo>
<title>Adapting Pre-trained Generative Models for Extractive Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prabir</namePart>
<namePart type="family">Mallick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tapas</namePart>
<namePart type="family">Nayak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Indrajit</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hooman</namePart>
<namePart type="family">Sedghamiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization. However, the potential of generative models in extractive QA tasks, where discriminative models are commonly employed, remains largely unexplored. Discriminative models often encounter challenges associated with label sparsity, particularly when only a small portion of the context contains the answer. The challenge is more pronounced for multi-span answers. In this work, we introduce a novel approach that uses the power of pre-trained generative models to address extractive QA tasks by generating indexes corresponding to context tokens or sentences that form part of the answer. Through comprehensive evaluations on multiple extractive QA datasets, including MultiSpanQA, BioASQ, MASHQA, and WikiQA, we demonstrate the superior performance of our proposed approach compared to existing state-of-the-art models.</abstract>
<identifier type="citekey">mallick-etal-2023-adapting</identifier>
<location>
<url>https://aclanthology.org/2023.gem-1.11</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>128</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting Pre-trained Generative Models for Extractive Question Answering
%A Mallick, Prabir
%A Nayak, Tapas
%A Bhattacharya, Indrajit
%Y Gehrmann, Sebastian
%Y Wang, Alex
%Y Sedoc, João
%Y Clark, Elizabeth
%Y Dhole, Kaustubh
%Y Chandu, Khyathi Raghavi
%Y Santus, Enrico
%Y Sedghamiz, Hooman
%S Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F mallick-etal-2023-adapting
%X Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization. However, the potential of generative models in extractive QA tasks, where discriminative models are commonly employed, remains largely unexplored. Discriminative models often encounter challenges associated with label sparsity, particularly when only a small portion of the context contains the answer. The challenge is more pronounced for multi-span answers. In this work, we introduce a novel approach that uses the power of pre-trained generative models to address extractive QA tasks by generating indexes corresponding to context tokens or sentences that form part of the answer. Through comprehensive evaluations on multiple extractive QA datasets, including MultiSpanQA, BioASQ, MASHQA, and WikiQA, we demonstrate the superior performance of our proposed approach compared to existing state-of-the-art models.
%U https://aclanthology.org/2023.gem-1.11
%P 128-137
Markdown (Informal)
[Adapting Pre-trained Generative Models for Extractive Question Answering](https://aclanthology.org/2023.gem-1.11) (Mallick et al., GEM-WS 2023)
ACL