@article{ouchi-etal-2021-instance,
title = "Instance-Based Neural Dependency Parsing",
author = "Ouchi, Hiroki and
Suzuki, Jun and
Kobayashi, Sosuke and
Yokoi, Sho and
Kuribayashi, Tatsuki and
Yoshikawa, Masashi and
Inui, Kentaro",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "9",
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.tacl-1.89/",
doi = "10.1162/tacl_a_00439",
pages = "1493--1507",
abstract = "Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouchi-etal-2021-instance">
<titleInfo>
<title>Instance-Based Neural Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sosuke</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Yokoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuki</namePart>
<namePart type="family">Kuribayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masashi</namePart>
<namePart type="family">Yoshikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.</abstract>
<identifier type="citekey">ouchi-etal-2021-instance</identifier>
<identifier type="doi">10.1162/tacl_a_00439</identifier>
<location>
<url>https://aclanthology.org/2021.tacl-1.89/</url>
</location>
<part>
<date>2021</date>
<detail type="volume"><number>9</number></detail>
<extent unit="page">
<start>1493</start>
<end>1507</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Instance-Based Neural Dependency Parsing
%A Ouchi, Hiroki
%A Suzuki, Jun
%A Kobayashi, Sosuke
%A Yokoi, Sho
%A Kuribayashi, Tatsuki
%A Yoshikawa, Masashi
%A Inui, Kentaro
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F ouchi-etal-2021-instance
%X Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.
%R 10.1162/tacl_a_00439
%U https://aclanthology.org/2021.tacl-1.89/
%U https://doi.org/10.1162/tacl_a_00439
%P 1493-1507
Markdown (Informal)
[Instance-Based Neural Dependency Parsing](https://aclanthology.org/2021.tacl-1.89/) (Ouchi et al., TACL 2021)
ACL
- Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, and Kentaro Inui. 2021. Instance-Based Neural Dependency Parsing. Transactions of the Association for Computational Linguistics, 9:1493–1507.