@inproceedings{maillard-clark-2018-latent,
title = "Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing",
author = "Maillard, Jean and
Clark, Stephen",
editor = "Dinu, Georgiana and
Ballesteros, Miguel and
Sil, Avirup and
Bowman, Sam and
Hamza, Wael and
Sogaard, Anders and
Naseem, Tahira and
Goldberg, Yoav",
booktitle = "Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for {NLP}",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2903",
doi = "10.18653/v1/W18-2903",
pages = "13--18",
abstract = "Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the composition order. This work contributes (a) a new latent tree learning model based on shift-reduce parsing, with competitive downstream performance and non-trivial induced trees, and (b) an analysis of the trees learned by our shift-reduce model and by a chart-based model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maillard-clark-2018-latent">
<titleInfo>
<title>Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Maillard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georgiana</namePart>
<namePart type="family">Dinu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ballesteros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avirup</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sam</namePart>
<namePart type="family">Bowman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wael</namePart>
<namePart type="family">Hamza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Sogaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tahira</namePart>
<namePart type="family">Naseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the composition order. This work contributes (a) a new latent tree learning model based on shift-reduce parsing, with competitive downstream performance and non-trivial induced trees, and (b) an analysis of the trees learned by our shift-reduce model and by a chart-based model.</abstract>
<identifier type="citekey">maillard-clark-2018-latent</identifier>
<identifier type="doi">10.18653/v1/W18-2903</identifier>
<location>
<url>https://aclanthology.org/W18-2903</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>13</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing
%A Maillard, Jean
%A Clark, Stephen
%Y Dinu, Georgiana
%Y Ballesteros, Miguel
%Y Sil, Avirup
%Y Bowman, Sam
%Y Hamza, Wael
%Y Sogaard, Anders
%Y Naseem, Tahira
%Y Goldberg, Yoav
%S Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F maillard-clark-2018-latent
%X Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the composition order. This work contributes (a) a new latent tree learning model based on shift-reduce parsing, with competitive downstream performance and non-trivial induced trees, and (b) an analysis of the trees learned by our shift-reduce model and by a chart-based model.
%R 10.18653/v1/W18-2903
%U https://aclanthology.org/W18-2903
%U https://doi.org/10.18653/v1/W18-2903
%P 13-18
Markdown (Informal)
[Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing](https://aclanthology.org/W18-2903) (Maillard & Clark, ACL 2018)
ACL