<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-crake">
    <titleInfo>
        <title>Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Minhao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruoyu</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanzeng</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lei</namePart>
        <namePart type="family">Zou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Semantic parsing solves knowledge base (KB) question answering (KBQA) by composing a KB query, which generally involves node extraction (NE) and graph composition (GC) to detect and connect related nodes in a query. Despite the strong causal effects between NE and GC, previous works fail to directly model such causalities in their pipeline, hindering the learning of subtask correlations. Also, the sequence-generation process for GC in previous works induces ambiguity and exposure bias, which further harms accuracy. In this work, we formalize semantic parsing into two stages. In the first stage (graph structure generation), we propose a causal-enhanced table-filler to overcome the issues in sequence-modelling and to learn the internal causalities. In the second stage (relation extraction), an efficient beam-search algorithm is presented to scale complex queries on large-scale KBs. Experiments on LC-QuAD 1.0 indicate that our method surpasses previous state-of-the-arts by a large margin (17%) while remaining time and space efficiency.</abstract>
    <identifier type="citekey">zhang-etal-2022-crake</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-naacl.136</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-naacl.136</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>1787</start>
            <end>1798</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base
%A Zhang, Minhao
%A Zhang, Ruoyu
%A Li, Yanzeng
%A Zou, Lei
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F zhang-etal-2022-crake
%X Semantic parsing solves knowledge base (KB) question answering (KBQA) by composing a KB query, which generally involves node extraction (NE) and graph composition (GC) to detect and connect related nodes in a query. Despite the strong causal effects between NE and GC, previous works fail to directly model such causalities in their pipeline, hindering the learning of subtask correlations. Also, the sequence-generation process for GC in previous works induces ambiguity and exposure bias, which further harms accuracy. In this work, we formalize semantic parsing into two stages. In the first stage (graph structure generation), we propose a causal-enhanced table-filler to overcome the issues in sequence-modelling and to learn the internal causalities. In the second stage (relation extraction), an efficient beam-search algorithm is presented to scale complex queries on large-scale KBs. Experiments on LC-QuAD 1.0 indicate that our method surpasses previous state-of-the-arts by a large margin (17%) while remaining time and space efficiency.
%R 10.18653/v1/2022.findings-naacl.136
%U https://aclanthology.org/2022.findings-naacl.136
%U https://doi.org/10.18653/v1/2022.findings-naacl.136
%P 1787-1798

Markdown (Informal)

[Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base](https://aclanthology.org/2022.findings-naacl.136) (Zhang et al., Findings 2022)

• Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base (Zhang et al., Findings 2022)

ACL

• Minhao Zhang, Ruoyu Zhang, Yanzeng Li, and Lei Zou. 2022. Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1787–1798, Seattle, United States. Association for Computational Linguistics.