<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-lapata-2018-weakly">
    <titleInfo>
        <title>Weakly-Supervised Neural Semantic Parsing with a Generative Ranker</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jianpeng</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mirella</namePart>
        <namePart type="family">Lapata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd Conference on Computational Natural Language Learning</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">Ivan</namePart>
            <namePart type="family">Titov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker system for weakly-supervised semantic parsing. The parser generates candidate tree-structured logical forms from utterances using clues of denotations. These candidates are then ranked based on two criterion: their likelihood of executing to the correct denotation, and their agreement with the utterance semantics. We present a scheduled training procedure to balance the contribution of the two objectives. Furthermore, we propose to use a neurally encoded lexicon to inject prior domain knowledge to the model. Experiments on three Freebase datasets demonstrate the effectiveness of our semantic parser, achieving results within the state-of-the-art range.</abstract>
    <identifier type="citekey">cheng-lapata-2018-weakly</identifier>
    <identifier type="doi">10.18653/v1/K18-1035</identifier>
    <location>
        <url>https://aclanthology.org/K18-1035</url>
    </location>
    <part>
        <date>2018-10</date>
        <extent unit="page">
            <start>356</start>
            <end>367</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Weakly-Supervised Neural Semantic Parsing with a Generative Ranker
%A Cheng, Jianpeng
%A Lapata, Mirella
%Y Korhonen, Anna
%Y Titov, Ivan
%S Proceedings of the 22nd Conference on Computational Natural Language Learning
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F cheng-lapata-2018-weakly
%X Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker system for weakly-supervised semantic parsing. The parser generates candidate tree-structured logical forms from utterances using clues of denotations. These candidates are then ranked based on two criterion: their likelihood of executing to the correct denotation, and their agreement with the utterance semantics. We present a scheduled training procedure to balance the contribution of the two objectives. Furthermore, we propose to use a neurally encoded lexicon to inject prior domain knowledge to the model. Experiments on three Freebase datasets demonstrate the effectiveness of our semantic parser, achieving results within the state-of-the-art range.
%R 10.18653/v1/K18-1035
%U https://aclanthology.org/K18-1035
%U https://doi.org/10.18653/v1/K18-1035
%P 356-367

Markdown (Informal)

[Weakly-Supervised Neural Semantic Parsing with a Generative Ranker](https://aclanthology.org/K18-1035) (Cheng & Lapata, CoNLL 2018)

• Weakly-Supervised Neural Semantic Parsing with a Generative Ranker (Cheng & Lapata, CoNLL 2018)

ACL

• Jianpeng Cheng and Mirella Lapata. 2018. Weakly-Supervised Neural Semantic Parsing with a Generative Ranker. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 356–367, Brussels, Belgium. Association for Computational Linguistics.