<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2022-improving">
    <titleInfo>
        <title>Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yechun</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoxia</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiming</namePart>
        <namePart type="family">Lu</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>Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions. However, there is a significant semantic and structural gap between natural language and action sequences, which makes this conversion difficult. In this paper, we introduce an alignment-enhanced complex question answering framework, called ALCQA, which mitigates this gap through question-to-action alignment and question-to-question alignment. We train a question rewriting model to align the question and each action, and utilize a pretrained language model to implicitly align the question and KG artifacts. Moreover, considering that similar questions correspond to similar action sequences, we retrieve top-k similar question-answer pairs at the inference stage through question-to-question alignment and propose a novel reward-guided action sequence selection strategy to select from candidate action sequences. We conduct experiments on CQA and WQSP datasets, and the results show that our approach outperforms state-of-the-art methods and obtains a 9.88% improvements in the F1 metric on CQA dataset. Our source code is available at https://github.com/TTTTTTTTy/ALCQA.</abstract>
    <identifier type="citekey">tang-etal-2022-improving</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.10</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>137</start>
            <end>147</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment
%A Tang, Yechun
%A Cheng, Xiaoxia
%A Lu, Weiming
%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 tang-etal-2022-improving
%X Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions. However, there is a significant semantic and structural gap between natural language and action sequences, which makes this conversion difficult. In this paper, we introduce an alignment-enhanced complex question answering framework, called ALCQA, which mitigates this gap through question-to-action alignment and question-to-question alignment. We train a question rewriting model to align the question and each action, and utilize a pretrained language model to implicitly align the question and KG artifacts. Moreover, considering that similar questions correspond to similar action sequences, we retrieve top-k similar question-answer pairs at the inference stage through question-to-question alignment and propose a novel reward-guided action sequence selection strategy to select from candidate action sequences. We conduct experiments on CQA and WQSP datasets, and the results show that our approach outperforms state-of-the-art methods and obtains a 9.88% improvements in the F1 metric on CQA dataset. Our source code is available at https://github.com/TTTTTTTTy/ALCQA.
%U https://aclanthology.org/2022.emnlp-main.10
%P 137-147

Markdown (Informal)

[Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment](https://aclanthology.org/2022.emnlp-main.10) (Tang et al., EMNLP 2022)

• Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment (Tang et al., EMNLP 2022)

ACL

• Yechun Tang, Xiaoxia Cheng, and Weiming Lu. 2022. Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 137–147, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.