<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-titov-2017-optimizing">
    <titleInfo>
        <title>Optimizing Differentiable Relaxations of Coreference Evaluation Metrics</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Phong</namePart>
        <namePart type="family">Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Titov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Roger</namePart>
            <namePart type="family">Levy</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end goal, resulting in suboptimal performance. Instead, we propose a differentiable relaxation that lends itself to gradient-based optimisation, thus bypassing the need for reinforcement learning or heuristic modification of cross-entropy. We show that by modifying the training objective of a competitive neural coreference system, we obtain a substantial gain in performance. This suggests that our approach can be regarded as a viable alternative to using reinforcement learning or more computationally expensive imitation learning.</abstract>
    <identifier type="citekey">le-titov-2017-optimizing</identifier>
    <identifier type="doi">10.18653/v1/K17-1039</identifier>
    <location>
        <url>https://aclanthology.org/K17-1039</url>
    </location>
    <part>
        <date>2017-08</date>
        <extent unit="page">
            <start>390</start>
            <end>399</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Optimizing Differentiable Relaxations of Coreference Evaluation Metrics
%A Le, Phong
%A Titov, Ivan
%Y Levy, Roger
%Y Specia, Lucia
%S Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F le-titov-2017-optimizing
%X Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end goal, resulting in suboptimal performance. Instead, we propose a differentiable relaxation that lends itself to gradient-based optimisation, thus bypassing the need for reinforcement learning or heuristic modification of cross-entropy. We show that by modifying the training objective of a competitive neural coreference system, we obtain a substantial gain in performance. This suggests that our approach can be regarded as a viable alternative to using reinforcement learning or more computationally expensive imitation learning.
%R 10.18653/v1/K17-1039
%U https://aclanthology.org/K17-1039
%U https://doi.org/10.18653/v1/K17-1039
%P 390-399

Markdown (Informal)

[Optimizing Differentiable Relaxations of Coreference Evaluation Metrics](https://aclanthology.org/K17-1039) (Le & Titov, CoNLL 2017)

• Optimizing Differentiable Relaxations of Coreference Evaluation Metrics (Le & Titov, CoNLL 2017)

ACL

• Phong Le and Ivan Titov. 2017. Optimizing Differentiable Relaxations of Coreference Evaluation Metrics. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 390–399, Vancouver, Canada. Association for Computational Linguistics.