<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="knaebel-stede-2020-contextualized">
    <titleInfo>
        <title>Contextualized Embeddings for Connective Disambiguation in Shallow Discourse Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">René</namePart>
        <namePart type="family">Knaebel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manfred</namePart>
        <namePart type="family">Stede</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Computational Approaches to Discourse</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper studies a novel model that simplifies the disambiguation of connectives for explicit discourse relations. We use a neural approach that integrates contextualized word embeddings and predicts whether a connective candidate is part of a discourse relation or not. We study the influence of those context-specific embeddings. Further, we show the benefit of training the tasks of connective disambiguation and sense classification together at the same time. The success of our approach is supported by state-of-the-art results.</abstract>
    <identifier type="citekey">knaebel-stede-2020-contextualized</identifier>
    <identifier type="doi">10.18653/v1/2020.codi-1.7</identifier>
    <location>
        <url>https://aclanthology.org/2020.codi-1.7</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>65</start>
            <end>75</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Contextualized Embeddings for Connective Disambiguation in Shallow Discourse Parsing
%A Knaebel, René
%A Stede, Manfred
%S Proceedings of the First Workshop on Computational Approaches to Discourse
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F knaebel-stede-2020-contextualized
%X This paper studies a novel model that simplifies the disambiguation of connectives for explicit discourse relations. We use a neural approach that integrates contextualized word embeddings and predicts whether a connective candidate is part of a discourse relation or not. We study the influence of those context-specific embeddings. Further, we show the benefit of training the tasks of connective disambiguation and sense classification together at the same time. The success of our approach is supported by state-of-the-art results.
%R 10.18653/v1/2020.codi-1.7
%U https://aclanthology.org/2020.codi-1.7
%U https://doi.org/10.18653/v1/2020.codi-1.7
%P 65-75

Markdown (Informal)

[Contextualized Embeddings for Connective Disambiguation in Shallow Discourse Parsing](https://aclanthology.org/2020.codi-1.7) (Knaebel & Stede, CODI 2020)

• Contextualized Embeddings for Connective Disambiguation in Shallow Discourse Parsing (Knaebel & Stede, CODI 2020)

ACL

• René Knaebel and Manfred Stede. 2020. Contextualized Embeddings for Connective Disambiguation in Shallow Discourse Parsing. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 65–75, Online. Association for Computational Linguistics.