<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2018-learning">
    <titleInfo>
        <title>Learning to Embed Semantic Correspondence for Natural Language Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sangkeun</namePart>
        <namePart type="family">Jung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinsik</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiwon</namePart>
        <namePart type="family">Kim</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>While learning embedding models has yielded fruitful results in several NLP subfields, most notably Word2Vec, embedding correspondence has relatively not been well explored especially in the context of natural language understanding (NLU), a task that typically extracts structured semantic knowledge from a text. A NLU embedding model can facilitate analyzing and understanding relationships between unstructured texts and their corresponding structured semantic knowledge, essential for both researchers and practitioners of NLU. Toward this end, we propose a framework that learns to embed semantic correspondence between text and its extracted semantic knowledge, called semantic frame. One key contributed technique is semantic frame reconstruction used to derive a one-to-one mapping between embedded vectors and their corresponding semantic frames. Embedding into semantically meaningful vectors and computing their distances in vector space provides a simple, but effective way to measure semantic similarities. With the proposed framework, we demonstrate three key areas where the embedding model can be effective: visualization, semantic search and re-ranking.</abstract>
    <identifier type="citekey">jung-etal-2018-learning</identifier>
    <identifier type="doi">10.18653/v1/K18-1013</identifier>
    <location>
        <url>https://aclanthology.org/K18-1013</url>
    </location>
    <part>
        <date>2018-10</date>
        <extent unit="page">
            <start>131</start>
            <end>140</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Embed Semantic Correspondence for Natural Language Understanding
%A Jung, Sangkeun
%A Lee, Jinsik
%A Kim, Jiwon
%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 jung-etal-2018-learning
%X While learning embedding models has yielded fruitful results in several NLP subfields, most notably Word2Vec, embedding correspondence has relatively not been well explored especially in the context of natural language understanding (NLU), a task that typically extracts structured semantic knowledge from a text. A NLU embedding model can facilitate analyzing and understanding relationships between unstructured texts and their corresponding structured semantic knowledge, essential for both researchers and practitioners of NLU. Toward this end, we propose a framework that learns to embed semantic correspondence between text and its extracted semantic knowledge, called semantic frame. One key contributed technique is semantic frame reconstruction used to derive a one-to-one mapping between embedded vectors and their corresponding semantic frames. Embedding into semantically meaningful vectors and computing their distances in vector space provides a simple, but effective way to measure semantic similarities. With the proposed framework, we demonstrate three key areas where the embedding model can be effective: visualization, semantic search and re-ranking.
%R 10.18653/v1/K18-1013
%U https://aclanthology.org/K18-1013
%U https://doi.org/10.18653/v1/K18-1013
%P 131-140

Markdown (Informal)

[Learning to Embed Semantic Correspondence for Natural Language Understanding](https://aclanthology.org/K18-1013) (Jung et al., CoNLL 2018)

• Learning to Embed Semantic Correspondence for Natural Language Understanding (Jung et al., CoNLL 2018)

ACL

• Sangkeun Jung, Jinsik Lee, and Jiwon Kim. 2018. Learning to Embed Semantic Correspondence for Natural Language Understanding. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 131–140, Brussels, Belgium. Association for Computational Linguistics.