<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simov-etal-2017-towards">
    <titleInfo>
        <title>Towards Lexical Chains for Knowledge-Graph-based Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kiril</namePart>
        <namePart type="family">Simov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Svetla</namePart>
        <namePart type="family">Boytcheva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Petya</namePart>
        <namePart type="family">Osenova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-sep</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
        </titleInfo>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Word vectors with varying dimensionalities and produced by different algorithms have been extensively used in NLP. The corpora that the algorithms are trained on can contain either natural language text (e.g. Wikipedia or newswire articles) or artificially-generated pseudo corpora due to natural data sparseness. We exploit Lexical Chain based templates over Knowledge Graph for generating pseudo-corpora with controlled linguistic value. These corpora are then used for learning word embeddings. A number of experiments have been conducted over the following test sets: WordSim353 Similarity, WordSim353 Relatedness and SimLex-999. The results show that, on the one hand, the incorporation of many-relation lexical chains improves results, but on the other hand, unrestricted-length chains remain difficult to handle with respect to their huge quantity.</abstract>
    <identifier type="citekey">simov-etal-2017-towards</identifier>
    <identifier type="doi">10.26615/978-954-452-049-6_087</identifier>
    <part>
        <date>2017-sep</date>
        <extent unit="page">
            <start>679</start>
            <end>685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Lexical Chains for Knowledge-Graph-based Word Embeddings
%A Simov, Kiril
%A Boytcheva, Svetla
%A Osenova, Petya
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 sep
%I INCOMA Ltd.
%C Varna, Bulgaria
%F simov-etal-2017-towards
%X Word vectors with varying dimensionalities and produced by different algorithms have been extensively used in NLP. The corpora that the algorithms are trained on can contain either natural language text (e.g. Wikipedia or newswire articles) or artificially-generated pseudo corpora due to natural data sparseness. We exploit Lexical Chain based templates over Knowledge Graph for generating pseudo-corpora with controlled linguistic value. These corpora are then used for learning word embeddings. A number of experiments have been conducted over the following test sets: WordSim353 Similarity, WordSim353 Relatedness and SimLex-999. The results show that, on the one hand, the incorporation of many-relation lexical chains improves results, but on the other hand, unrestricted-length chains remain difficult to handle with respect to their huge quantity.
%R 10.26615/978-954-452-049-6_087
%U https://doi.org/10.26615/978-954-452-049-6_087
%P 679-685

Markdown (Informal)

[Towards Lexical Chains for Knowledge-Graph-based Word Embeddings](https://doi.org/10.26615/978-954-452-049-6_087) (Simov et al., RANLP 2017)

• Towards Lexical Chains for Knowledge-Graph-based Word Embeddings (Simov et al., RANLP 2017)

ACL

• Kiril Simov, Svetla Boytcheva, and Petya Osenova. 2017. Towards Lexical Chains for Knowledge-Graph-based Word Embeddings. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 679–685, Varna, Bulgaria. INCOMA Ltd..