<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2019-towards">
    <titleInfo>
        <title>Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kaixin</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Francis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Quanyang</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eric</namePart>
        <namePart type="family">Nyberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alessandro</namePart>
        <namePart type="family">Oltramari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Ostermann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sheng</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Roth</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peter</namePart>
            <namePart type="family">Clark</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Non-extractive commonsense QA remains a challenging AI task, as it requires systems to reason about, synthesize, and gather disparate pieces of information, in order to generate responses to queries. Recent approaches on such tasks show increased performance, only when models are either pre-trained with additional information or when domain-specific heuristics are used, without any special consideration regarding the knowledge resource type. In this paper, we perform a survey of recent commonsense QA methods and we provide a systematic analysis of popular knowledge resources and knowledge-integration methods, across benchmarks from multiple commonsense datasets. Our results and analysis show that attention-based injection seems to be a preferable choice for knowledge integration and that the degree of domain overlap, between knowledge bases and datasets, plays a crucial role in determining model success.</abstract>
    <identifier type="citekey">ma-etal-2019-towards</identifier>
    <identifier type="doi">10.18653/v1/D19-6003</identifier>
    <location>
        <url>https://aclanthology.org/D19-6003</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>22</start>
            <end>32</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
%A Ma, Kaixin
%A Francis, Jonathan
%A Lu, Quanyang
%A Nyberg, Eric
%A Oltramari, Alessandro
%Y Ostermann, Simon
%Y Zhang, Sheng
%Y Roth, Michael
%Y Clark, Peter
%S Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ma-etal-2019-towards
%X Non-extractive commonsense QA remains a challenging AI task, as it requires systems to reason about, synthesize, and gather disparate pieces of information, in order to generate responses to queries. Recent approaches on such tasks show increased performance, only when models are either pre-trained with additional information or when domain-specific heuristics are used, without any special consideration regarding the knowledge resource type. In this paper, we perform a survey of recent commonsense QA methods and we provide a systematic analysis of popular knowledge resources and knowledge-integration methods, across benchmarks from multiple commonsense datasets. Our results and analysis show that attention-based injection seems to be a preferable choice for knowledge integration and that the degree of domain overlap, between knowledge bases and datasets, plays a crucial role in determining model success.
%R 10.18653/v1/D19-6003
%U https://aclanthology.org/D19-6003
%U https://doi.org/10.18653/v1/D19-6003
%P 22-32

Markdown (Informal)

[Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering](https://aclanthology.org/D19-6003) (Ma et al., 2019)

• Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering (Ma et al., 2019)

ACL

• Kaixin Ma, Jonathan Francis, Quanyang Lu, Eric Nyberg, and Alessandro Oltramari. 2019. Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering. In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pages 22–32, Hong Kong, China. Association for Computational Linguistics.