<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-nie-2020-inducing">
    <titleInfo>
        <title>Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuhui</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Allen</namePart>
        <namePart type="family">Nie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Shruti</namePart>
            <namePart type="family">Rijhwani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiangming</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yizhong</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rotem</namePart>
            <namePart type="family">Dror</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>The principle of compositionality has deep roots in linguistics: the meaning of an expression is determined by its structure and the meanings of its constituents. However, modern neural network models such as long short-term memory network process expressions in a linear fashion and do not seem to incorporate more complex compositional patterns. In this work, we show that we can explicitly induce grammar by tracing the computational process of a long short-term memory network. We show: (i) the multiplicative nature of long short-term memory network allows complex interaction beyond sequential linear combination; (ii) we can generate compositional trees from the network without external linguistic knowledge; (iii) we evaluate the syntactic difference between the generated trees, randomly generated trees and gold reference trees produced by constituency parsers; (iv) we evaluate whether the generated trees contain the rich semantic information.</abstract>
    <identifier type="citekey">zhang-nie-2020-inducing</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-srw.40</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-srw.40</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>299</start>
            <end>305</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition
%A Zhang, Yuhui
%A Nie, Allen
%Y Rijhwani, Shruti
%Y Liu, Jiangming
%Y Wang, Yizhong
%Y Dror, Rotem
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F zhang-nie-2020-inducing
%X The principle of compositionality has deep roots in linguistics: the meaning of an expression is determined by its structure and the meanings of its constituents. However, modern neural network models such as long short-term memory network process expressions in a linear fashion and do not seem to incorporate more complex compositional patterns. In this work, we show that we can explicitly induce grammar by tracing the computational process of a long short-term memory network. We show: (i) the multiplicative nature of long short-term memory network allows complex interaction beyond sequential linear combination; (ii) we can generate compositional trees from the network without external linguistic knowledge; (iii) we evaluate the syntactic difference between the generated trees, randomly generated trees and gold reference trees produced by constituency parsers; (iv) we evaluate whether the generated trees contain the rich semantic information.
%R 10.18653/v1/2020.acl-srw.40
%U https://aclanthology.org/2020.acl-srw.40
%U https://doi.org/10.18653/v1/2020.acl-srw.40
%P 299-305

Markdown (Informal)

[Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition](https://aclanthology.org/2020.acl-srw.40) (Zhang & Nie, ACL 2020)

• Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition (Zhang & Nie, ACL 2020)

ACL

• Yuhui Zhang and Allen Nie. 2020. Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 299–305, Online. Association for Computational Linguistics.