<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-bowman-2018-language">
    <titleInfo>
        <title>Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kelly</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samuel</namePart>
        <namePart type="family">Bowman</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>Recently, researchers have found that deep LSTMs trained on tasks like machine translation learn substantial syntactic and semantic information about their input sentences, including part-of-speech. These findings begin to shed light on why pretrained representations, like ELMo and CoVe, are so beneficial for neural language understanding models. We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn. With this in mind, we compare four objectives—language modeling, translation, skip-thought, and autoencoding—on their ability to induce syntactic and part-of-speech information, holding constant the quantity and genre of the training data, as well as the LSTM architecture.</abstract>
    <identifier type="citekey">zhang-bowman-2018-language</identifier>
    <identifier type="doi">10.18653/v1/W18-5448</identifier>
    <location>
        <url>https://aclanthology.org/W18-5448</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>359</start>
            <end>361</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis
%A Zhang, Kelly
%A Bowman, Samuel
%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 zhang-bowman-2018-language
%X Recently, researchers have found that deep LSTMs trained on tasks like machine translation learn substantial syntactic and semantic information about their input sentences, including part-of-speech. These findings begin to shed light on why pretrained representations, like ELMo and CoVe, are so beneficial for neural language understanding models. We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn. With this in mind, we compare four objectives—language modeling, translation, skip-thought, and autoencoding—on their ability to induce syntactic and part-of-speech information, holding constant the quantity and genre of the training data, as well as the LSTM architecture.
%R 10.18653/v1/W18-5448
%U https://aclanthology.org/W18-5448
%U https://doi.org/10.18653/v1/W18-5448
%P 359-361

Markdown (Informal)

[Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis](https://aclanthology.org/W18-5448) (Zhang & Bowman, EMNLP 2018)

• Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis (Zhang & Bowman, EMNLP 2018)

ACL

• Kelly Zhang and Samuel Bowman. 2018. Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 359–361, Brussels, Belgium. Association for Computational Linguistics.