<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ebrahimi-etal-2020-self">
    <titleInfo>
        <title>How Can Self-Attention Networks Recognize Dyck-n Languages?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Javid</namePart>
        <namePart type="family">Ebrahimi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dhruv</namePart>
        <namePart type="family">Gelda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <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>We focus on the recognition of Dyck-n (Dn) languages with self-attention (SA) networks, which has been deemed to be a difficult task for these networks. We compare the performance of two variants of SA, one with a starting symbol (SA+) and one without (SA-). Our results show that SA+ is able to generalize to longer sequences and deeper dependencies. For D2, we find that SA- completely breaks down on long sequences whereas the accuracy of SA+ is 58.82%. We find attention maps learned by SA+ to be amenable to interpretation and compatible with a stack-based language recognizer. Surprisingly, the performance of SA networks is at par with LSTMs, which provides evidence on the ability of SA to learn hierarchies without recursion.</abstract>
    <identifier type="citekey">ebrahimi-etal-2020-self</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.384</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.384</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>4301</start>
            <end>4306</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How Can Self-Attention Networks Recognize Dyck-n Languages?
%A Ebrahimi, Javid
%A Gelda, Dhruv
%A Zhang, Wei
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ebrahimi-etal-2020-self
%X We focus on the recognition of Dyck-n (Dn) languages with self-attention (SA) networks, which has been deemed to be a difficult task for these networks. We compare the performance of two variants of SA, one with a starting symbol (SA+) and one without (SA-). Our results show that SA+ is able to generalize to longer sequences and deeper dependencies. For D2, we find that SA- completely breaks down on long sequences whereas the accuracy of SA+ is 58.82%. We find attention maps learned by SA+ to be amenable to interpretation and compatible with a stack-based language recognizer. Surprisingly, the performance of SA networks is at par with LSTMs, which provides evidence on the ability of SA to learn hierarchies without recursion.
%R 10.18653/v1/2020.findings-emnlp.384
%U https://aclanthology.org/2020.findings-emnlp.384
%U https://doi.org/10.18653/v1/2020.findings-emnlp.384
%P 4301-4306

Markdown (Informal)

[How Can Self-Attention Networks Recognize Dyck-n Languages?](https://aclanthology.org/2020.findings-emnlp.384) (Ebrahimi et al., Findings 2020)

• How Can Self-Attention Networks Recognize Dyck-n Languages? (Ebrahimi et al., Findings 2020)

ACL

• Javid Ebrahimi, Dhruv Gelda, and Wei Zhang. 2020. How Can Self-Attention Networks Recognize Dyck-n Languages?. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4301–4306, Online. Association for Computational Linguistics.