<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakashole-flauger-2017-knowledge">
    <titleInfo>
        <title>Knowledge Distillation for Bilingual Dictionary Induction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ndapandula</namePart>
        <namePart type="family">Nakashole</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raphael</namePart>
        <namePart type="family">Flauger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Leveraging zero-shot learning to learn mapping functions between vector spaces of different languages is a promising approach to bilingual dictionary induction. However, methods using this approach have not yet achieved high accuracy on the task. In this paper, we propose a bridging approach, where our main contribution is a knowledge distillation training objective. As teachers, rich resource translation paths are exploited in this role. And as learners, translation paths involving low resource languages learn from the teachers. Our training objective allows seamless addition of teacher translation paths for any given low resource pair. Since our approach relies on the quality of monolingual word embeddings, we also propose to enhance vector representations of both the source and target language with linguistic information. Our experiments on various languages show large performance gains from our distillation training objective, obtaining as high as 17% accuracy improvements.</abstract>
    <identifier type="citekey">nakashole-flauger-2017-knowledge</identifier>
    <identifier type="doi">10.18653/v1/D17-1264</identifier>
    <location>
        <url>https://aclanthology.org/D17-1264</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>2497</start>
            <end>2506</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Knowledge Distillation for Bilingual Dictionary Induction
%A Nakashole, Ndapandula
%A Flauger, Raphael
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F nakashole-flauger-2017-knowledge
%X Leveraging zero-shot learning to learn mapping functions between vector spaces of different languages is a promising approach to bilingual dictionary induction. However, methods using this approach have not yet achieved high accuracy on the task. In this paper, we propose a bridging approach, where our main contribution is a knowledge distillation training objective. As teachers, rich resource translation paths are exploited in this role. And as learners, translation paths involving low resource languages learn from the teachers. Our training objective allows seamless addition of teacher translation paths for any given low resource pair. Since our approach relies on the quality of monolingual word embeddings, we also propose to enhance vector representations of both the source and target language with linguistic information. Our experiments on various languages show large performance gains from our distillation training objective, obtaining as high as 17% accuracy improvements.
%R 10.18653/v1/D17-1264
%U https://aclanthology.org/D17-1264
%U https://doi.org/10.18653/v1/D17-1264
%P 2497-2506

Markdown (Informal)

[Knowledge Distillation for Bilingual Dictionary Induction](https://aclanthology.org/D17-1264) (Nakashole & Flauger, EMNLP 2017)

• Knowledge Distillation for Bilingual Dictionary Induction (Nakashole & Flauger, EMNLP 2017)

ACL

• Ndapandula Nakashole and Raphael Flauger. 2017. Knowledge Distillation for Bilingual Dictionary Induction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2497–2506, Copenhagen, Denmark. Association for Computational Linguistics.