@inproceedings{pal-etal-2022-parameter,
title = "Parameter-Efficient Abstractive Question Answering over Tables or Text",
author = "Pal, Vaishali and
Kanoulas, Evangelos and
de Rijke, Maarten",
editor = "Feng, Song and
Wan, Hui and
Yuan, Caixia and
Yu, Han",
booktitle = "Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dialdoc-1.5/",
doi = "10.18653/v1/2022.dialdoc-1.5",
pages = "41--53",
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."
}
<?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">de 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>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caixia</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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 de Rijke, Maarten
%Y Feng, Song
%Y Wan, Hui
%Y Yuan, Caixia
%Y Yu, Han
%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)
ACL