<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trifonov-etal-2018-learning">
    <titleInfo>
        <title>Learning and Evaluating Sparse Interpretable Sentence Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Valentin</namePart>
        <namePart type="family">Trifonov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Octavian-Eugen</namePart>
        <namePart type="family">Ganea</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Potapenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Hofmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Tal</namePart>
            <namePart type="family">Linzen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Grzegorz</namePart>
            <namePart type="family">Chrupała</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Afra</namePart>
            <namePart type="family">Alishahi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased interpretability properties: to some degree, each dimension can be understood by a human and associated with a recognizable feature in the data. In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation. We further introduce a novel, quantitative and automated evaluation metric for sentence embedding interpretability, based on topic coherence methods. We observe an increase in interpretability compared to dense models, on a dataset of movie dialogs and on the scene descriptions from the MS COCO dataset.</abstract>
    <identifier type="citekey">trifonov-etal-2018-learning</identifier>
    <identifier type="doi">10.18653/v1/W18-5422</identifier>
    <location>
        <url>https://aclanthology.org/W18-5422</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>200</start>
            <end>210</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning and Evaluating Sparse Interpretable Sentence Embeddings
%A Trifonov, Valentin
%A Ganea, Octavian-Eugen
%A Potapenko, Anna
%A Hofmann, Thomas
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Alishahi, Afra
%S Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F trifonov-etal-2018-learning
%X Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased interpretability properties: to some degree, each dimension can be understood by a human and associated with a recognizable feature in the data. In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation. We further introduce a novel, quantitative and automated evaluation metric for sentence embedding interpretability, based on topic coherence methods. We observe an increase in interpretability compared to dense models, on a dataset of movie dialogs and on the scene descriptions from the MS COCO dataset.
%R 10.18653/v1/W18-5422
%U https://aclanthology.org/W18-5422
%U https://doi.org/10.18653/v1/W18-5422
%P 200-210

Markdown (Informal)

[Learning and Evaluating Sparse Interpretable Sentence Embeddings](https://aclanthology.org/W18-5422) (Trifonov et al., EMNLP 2018)

• Learning and Evaluating Sparse Interpretable Sentence Embeddings (Trifonov et al., EMNLP 2018)

ACL

• Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, and Thomas Hofmann. 2018. Learning and Evaluating Sparse Interpretable Sentence Embeddings. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 200–210, Brussels, Belgium. Association for Computational Linguistics.