<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simeonova-etal-2019-morpho">
    <titleInfo>
        <title>A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lilia</namePart>
        <namePart type="family">Simeonova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <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">Petya</namePart>
        <namePart type="family">Osenova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preslav</namePart>
        <namePart type="family">Nakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose a morphologically informed model for named entity recognition, which is based on LSTM-CRF architecture and combines word embeddings, Bi-LSTM character embeddings, part-of-speech (POS) tags, and morphological information. While previous work has focused on learning from raw word input, using word and character embeddings only, we show that for morphologically rich languages, such as Bulgarian, access to POS information contributes more to the performance gains than the detailed morphological information. Thus, we show that named entity recognition needs only coarse-grained POS tags, but at the same time it can benefit from simultaneously using some POS information of different granularity. Our evaluation results over a standard dataset show sizeable improvements over the state-of-the-art for Bulgarian NER.</abstract>
    <identifier type="citekey">simeonova-etal-2019-morpho</identifier>
    <identifier type="doi">10.26615/978-954-452-056-4_127</identifier>
    <location>
        <url>https://aclanthology.org/R19-1127</url>
    </location>
    <part>
        <date>2019-09</date>
        <extent unit="page">
            <start>1104</start>
            <end>1113</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition
%A Simeonova, Lilia
%A Simov, Kiril
%A Osenova, Petya
%A Nakov, Preslav
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F simeonova-etal-2019-morpho
%X We propose a morphologically informed model for named entity recognition, which is based on LSTM-CRF architecture and combines word embeddings, Bi-LSTM character embeddings, part-of-speech (POS) tags, and morphological information. While previous work has focused on learning from raw word input, using word and character embeddings only, we show that for morphologically rich languages, such as Bulgarian, access to POS information contributes more to the performance gains than the detailed morphological information. Thus, we show that named entity recognition needs only coarse-grained POS tags, but at the same time it can benefit from simultaneously using some POS information of different granularity. Our evaluation results over a standard dataset show sizeable improvements over the state-of-the-art for Bulgarian NER.
%R 10.26615/978-954-452-056-4_127
%U https://aclanthology.org/R19-1127
%U https://doi.org/10.26615/978-954-452-056-4_127
%P 1104-1113

Markdown (Informal)

[A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition](https://aclanthology.org/R19-1127) (Simeonova et al., RANLP 2019)

• A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition (Simeonova et al., RANLP 2019)

ACL

• Lilia Simeonova, Kiril Simov, Petya Osenova, and Preslav Nakov. 2019. A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1104–1113, Varna, Bulgaria. INCOMA Ltd..