<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2022-pacific">
    <titleInfo>
        <title>PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Deng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenqiang</namePart>
        <namePart type="family">Lei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenxuan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wai</namePart>
        <namePart type="family">Lam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tat-Seng</namePart>
        <namePart type="family">Chua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC. Compared with existing CQA datasets, PACIFIC exhibits three key features: (i) proactivity, (ii) numerical reasoning, and (iii) hybrid context of tables and text. A new task is defined accordingly to study Proactive Conversational Question Answering (PCQA), which combines clarification question generation and CQA. In addition, we propose a novel method, namely UniPCQA, to adapt a hybrid format of input and output content in PCQA into the Seq2Seq problem, including the reformulation of the numerical reasoning process as code generation. UniPCQA performs multi-task learning over all sub-tasks in PCQA and incorporates a simple ensemble strategy to alleviate the error propagation issue in the multi-task learning by cross-validating top-k sampled Seq2Seq outputs. We benchmark the PACIFIC dataset with extensive baselines and provide comprehensive evaluations on each sub-task of PCQA.</abstract>
    <identifier type="citekey">deng-etal-2022-pacific</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.469</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.469</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6970</start>
            <end>6984</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance
%A Deng, Yang
%A Lei, Wenqiang
%A Zhang, Wenxuan
%A Lam, Wai
%A Chua, Tat-Seng
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F deng-etal-2022-pacific
%X To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC. Compared with existing CQA datasets, PACIFIC exhibits three key features: (i) proactivity, (ii) numerical reasoning, and (iii) hybrid context of tables and text. A new task is defined accordingly to study Proactive Conversational Question Answering (PCQA), which combines clarification question generation and CQA. In addition, we propose a novel method, namely UniPCQA, to adapt a hybrid format of input and output content in PCQA into the Seq2Seq problem, including the reformulation of the numerical reasoning process as code generation. UniPCQA performs multi-task learning over all sub-tasks in PCQA and incorporates a simple ensemble strategy to alleviate the error propagation issue in the multi-task learning by cross-validating top-k sampled Seq2Seq outputs. We benchmark the PACIFIC dataset with extensive baselines and provide comprehensive evaluations on each sub-task of PCQA.
%R 10.18653/v1/2022.emnlp-main.469
%U https://aclanthology.org/2022.emnlp-main.469
%U https://doi.org/10.18653/v1/2022.emnlp-main.469
%P 6970-6984

Markdown (Informal)

[PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance](https://aclanthology.org/2022.emnlp-main.469) (Deng et al., EMNLP 2022)

• PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance (Deng et al., EMNLP 2022)

ACL

• Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, and Tat-Seng Chua. 2022. PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6970–6984, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.