<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wieting-etal-2020-bilingual">
    <titleInfo>
        <title>A Bilingual Generative Transformer for Semantic Sentence Embedding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Wieting</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Taylor</namePart>
        <namePart type="family">Berg-Kirkpatrick</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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such embeddings: properties shared by both sentences in a translation pair are likely semantic, while divergent properties are likely stylistic or language-specific. We propose a deep latent variable model that attempts to perform source separation on parallel sentences, isolating what they have in common in a latent semantic vector, and explaining what is left over with language-specific latent vectors. Our proposed approach differs from past work on semantic sentence encoding in two ways. First, by using a variational probabilistic framework, we introduce priors that encourage source separation, and can use our model’s posterior to predict sentence embeddings for monolingual data at test time. Second, we use high-capacity transformers as both data generating distributions and inference networks – contrasting with most past work on sentence embeddings. In experiments, our approach substantially outperforms the state-of-the-art on a standard suite of unsupervised semantic similarity evaluations. Further, we demonstrate that our approach yields the largest gains on more difficult subsets of these evaluations where simple word overlap is not a good indicator of similarity.</abstract>
    <identifier type="citekey">wieting-etal-2020-bilingual</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.122</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.122</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1581</start>
            <end>1594</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Bilingual Generative Transformer for Semantic Sentence Embedding
%A Wieting, John
%A Neubig, Graham
%A Berg-Kirkpatrick, Taylor
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wieting-etal-2020-bilingual
%X Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such embeddings: properties shared by both sentences in a translation pair are likely semantic, while divergent properties are likely stylistic or language-specific. We propose a deep latent variable model that attempts to perform source separation on parallel sentences, isolating what they have in common in a latent semantic vector, and explaining what is left over with language-specific latent vectors. Our proposed approach differs from past work on semantic sentence encoding in two ways. First, by using a variational probabilistic framework, we introduce priors that encourage source separation, and can use our model’s posterior to predict sentence embeddings for monolingual data at test time. Second, we use high-capacity transformers as both data generating distributions and inference networks – contrasting with most past work on sentence embeddings. In experiments, our approach substantially outperforms the state-of-the-art on a standard suite of unsupervised semantic similarity evaluations. Further, we demonstrate that our approach yields the largest gains on more difficult subsets of these evaluations where simple word overlap is not a good indicator of similarity.
%R 10.18653/v1/2020.emnlp-main.122
%U https://aclanthology.org/2020.emnlp-main.122
%U https://doi.org/10.18653/v1/2020.emnlp-main.122
%P 1581-1594

Markdown (Informal)

[A Bilingual Generative Transformer for Semantic Sentence Embedding](https://aclanthology.org/2020.emnlp-main.122) (Wieting et al., EMNLP 2020)

• A Bilingual Generative Transformer for Semantic Sentence Embedding (Wieting et al., EMNLP 2020)

ACL

• John Wieting, Graham Neubig, and Taylor Berg-Kirkpatrick. 2020. A Bilingual Generative Transformer for Semantic Sentence Embedding. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1581–1594, Online. Association for Computational Linguistics.