<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pal-etal-2022-parameter">
    <titleInfo>
        <title>Parameter-Efficient Abstractive Question Answering over Tables or Text</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vaishali</namePart>
        <namePart type="family">Pal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evangelos</namePart>
        <namePart type="family">Kanoulas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maarten</namePart>
        <namePart type="family">Rijke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A long-term ambition of information seeking QA systems is to reason over multi-modal contexts and generate natural answers to user queries. Today, memory intensive pre-trained language models are adapted to downstream tasks such as QA by fine-tuning the model on QA data in a specific modality like unstructured text or structured tables. To avoid training such memory-hungry models while utilizing a uniform architecture for each modality, parameter-efficient adapters add and train small task-specific bottle-neck layers between transformer layers. In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1.5% additional parameters for each modality. We also ablate over adapter layers in both encoder and decoder modules to study the efficiency-performance trade-off and demonstrate that reducing additional trainable parameters down to 0.7%-1.0% leads to comparable results. Our models out-perform current state-of-the-art models on tabular QA datasets such as Tablesum and FeTaQA, and achieve comparable performance on a textual QA dataset such as NarrativeQA using significantly less trainable parameters than fine-tuning.</abstract>
    <identifier type="citekey">pal-etal-2022-parameter</identifier>
    <identifier type="doi">10.18653/v1/2022.dialdoc-1.5</identifier>
    <location>
        <url>https://aclanthology.org/2022.dialdoc-1.5</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>41</start>
            <end>53</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Parameter-Efficient Abstractive Question Answering over Tables or Text
%A Pal, Vaishali
%A Kanoulas, Evangelos
%A Rijke, Maarten
%S Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F pal-etal-2022-parameter
%X A long-term ambition of information seeking QA systems is to reason over multi-modal contexts and generate natural answers to user queries. Today, memory intensive pre-trained language models are adapted to downstream tasks such as QA by fine-tuning the model on QA data in a specific modality like unstructured text or structured tables. To avoid training such memory-hungry models while utilizing a uniform architecture for each modality, parameter-efficient adapters add and train small task-specific bottle-neck layers between transformer layers. In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1.5% additional parameters for each modality. We also ablate over adapter layers in both encoder and decoder modules to study the efficiency-performance trade-off and demonstrate that reducing additional trainable parameters down to 0.7%-1.0% leads to comparable results. Our models out-perform current state-of-the-art models on tabular QA datasets such as Tablesum and FeTaQA, and achieve comparable performance on a textual QA dataset such as NarrativeQA using significantly less trainable parameters than fine-tuning.
%R 10.18653/v1/2022.dialdoc-1.5
%U https://aclanthology.org/2022.dialdoc-1.5
%U https://doi.org/10.18653/v1/2022.dialdoc-1.5
%P 41-53

Markdown (Informal)

[Parameter-Efficient Abstractive Question Answering over Tables or Text](https://aclanthology.org/2022.dialdoc-1.5) (Pal et al., dialdoc 2022)

• Parameter-Efficient Abstractive Question Answering over Tables or Text (Pal et al., dialdoc 2022)

ACL

• Vaishali Pal, Evangelos Kanoulas, and Maarten Rijke. 2022. Parameter-Efficient Abstractive Question Answering over Tables or Text. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 41–53, Dublin, Ireland. Association for Computational Linguistics.