@inproceedings{tagami-bekki-2023-recurrent,
title = "Recurrent Neural Network {CCG} Parser",
author = "Tagami, Sora and
Bekki, Daisuke",
editor = "Chatzikyriakidis, Stergios and
de Paiva, Valeria",
booktitle = "Proceedings of the 4th Natural Logic Meets Machine Learning Workshop",
month = jun,
year = "2023",
address = "Nancy, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.naloma-1.4",
pages = "35--40",
abstract = "The two contrasting approaches are end-to-end neural NLI systems and linguistically-oriented NLI pipelines consisting of modules such as neural CCG parsers and theorem provers. The latter, however, faces the challenge of integrating the neural models used in the syntactic and semantic components. RNNGs are frameworks that can potentially fill this gap, but conventional RNNGs adopt CFG as the syntactic theory. To address this issue, we implemented RNN-CCG, a syntactic parser that replaces CFG with CCG. We then conducted experiments comparing RNN-CCG to RNNGs with/without POS tags and evaluated their behavior as a first step towards building an NLI system based on RNN-CCG.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tagami-bekki-2023-recurrent">
<titleInfo>
<title>Recurrent Neural Network CCG Parser</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sora</namePart>
<namePart type="family">Tagami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Bekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Natural Logic Meets Machine Learning Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stergios</namePart>
<namePart type="family">Chatzikyriakidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeria</namePart>
<namePart type="family">de Paiva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The two contrasting approaches are end-to-end neural NLI systems and linguistically-oriented NLI pipelines consisting of modules such as neural CCG parsers and theorem provers. The latter, however, faces the challenge of integrating the neural models used in the syntactic and semantic components. RNNGs are frameworks that can potentially fill this gap, but conventional RNNGs adopt CFG as the syntactic theory. To address this issue, we implemented RNN-CCG, a syntactic parser that replaces CFG with CCG. We then conducted experiments comparing RNN-CCG to RNNGs with/without POS tags and evaluated their behavior as a first step towards building an NLI system based on RNN-CCG.</abstract>
<identifier type="citekey">tagami-bekki-2023-recurrent</identifier>
<location>
<url>https://aclanthology.org/2023.naloma-1.4</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>35</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recurrent Neural Network CCG Parser
%A Tagami, Sora
%A Bekki, Daisuke
%Y Chatzikyriakidis, Stergios
%Y de Paiva, Valeria
%S Proceedings of the 4th Natural Logic Meets Machine Learning Workshop
%D 2023
%8 June
%I Association for Computational Linguistics
%C Nancy, France
%F tagami-bekki-2023-recurrent
%X The two contrasting approaches are end-to-end neural NLI systems and linguistically-oriented NLI pipelines consisting of modules such as neural CCG parsers and theorem provers. The latter, however, faces the challenge of integrating the neural models used in the syntactic and semantic components. RNNGs are frameworks that can potentially fill this gap, but conventional RNNGs adopt CFG as the syntactic theory. To address this issue, we implemented RNN-CCG, a syntactic parser that replaces CFG with CCG. We then conducted experiments comparing RNN-CCG to RNNGs with/without POS tags and evaluated their behavior as a first step towards building an NLI system based on RNN-CCG.
%U https://aclanthology.org/2023.naloma-1.4
%P 35-40
Markdown (Informal)
[Recurrent Neural Network CCG Parser](https://aclanthology.org/2023.naloma-1.4) (Tagami & Bekki, NALOMA-WS 2023)
ACL
- Sora Tagami and Daisuke Bekki. 2023. Recurrent Neural Network CCG Parser. In Proceedings of the 4th Natural Logic Meets Machine Learning Workshop, pages 35–40, Nancy, France. Association for Computational Linguistics.