<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weber-etal-2019-nlprolog">
    <titleInfo>
        <title>NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Leon</namePart>
        <namePart type="family">Weber</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pasquale</namePart>
        <namePart type="family">Minervini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jannes</namePart>
        <namePart type="family">Münchmeyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ulf</namePart>
        <namePart type="family">Leser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tim</namePart>
        <namePart type="family">Rocktäschel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving natural language, due to its large linguistic variability. In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret. In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language. Specifically, we propose to use an Prolog prover which we extend to utilize a similarity function over pretrained sentence encoders. We fine-tune the representations for the similarity function via backpropagation. This leads to a system that can apply rule-based reasoning to natural language, and induce domain-specific natural language rules from training data. We evaluate the proposed system on two different question answering tasks, showing that it outperforms two baselines – BiDAF (Seo et al., 2016a) and FastQA( Weissenborn et al., 2017) on a subset of the WikiHop corpus and achieves competitive results on the MedHop data set (Welbl et al., 2017).</abstract>
    <identifier type="citekey">weber-etal-2019-nlprolog</identifier>
    <identifier type="doi">10.18653/v1/P19-1618</identifier>
    <location>
        <url>https://aclanthology.org/P19-1618</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>6151</start>
            <end>6161</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
%A Weber, Leon
%A Minervini, Pasquale
%A Münchmeyer, Jannes
%A Leser, Ulf
%A Rocktäschel, Tim
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F weber-etal-2019-nlprolog
%X Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving natural language, due to its large linguistic variability. In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret. In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language. Specifically, we propose to use an Prolog prover which we extend to utilize a similarity function over pretrained sentence encoders. We fine-tune the representations for the similarity function via backpropagation. This leads to a system that can apply rule-based reasoning to natural language, and induce domain-specific natural language rules from training data. We evaluate the proposed system on two different question answering tasks, showing that it outperforms two baselines – BiDAF (Seo et al., 2016a) and FastQA( Weissenborn et al., 2017) on a subset of the WikiHop corpus and achieves competitive results on the MedHop data set (Welbl et al., 2017).
%R 10.18653/v1/P19-1618
%U https://aclanthology.org/P19-1618
%U https://doi.org/10.18653/v1/P19-1618
%P 6151-6161

Markdown (Informal)

[NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language](https://aclanthology.org/P19-1618) (Weber et al., ACL 2019)

• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (Weber et al., ACL 2019)

ACL

• Leon Weber, Pasquale Minervini, Jannes Münchmeyer, Ulf Leser, and Tim Rocktäschel. 2019. NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6151–6161, Florence, Italy. Association for Computational Linguistics.