@inproceedings{jin-schuler-2020-grounded,
title = "Grounded {PCFG} Induction with Images",
author = "Jin, Lifeng and
Schuler, William",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.42/",
doi = "10.18653/v1/2020.aacl-main.42",
pages = "396--408",
abstract = "Recent work in unsupervised parsing has tried to incorporate visual information into learning, but results suggest that these models need linguistic bias to compete against models that only rely on text. This work proposes grammar induction models which use visual information from images for labeled parsing, and achieve state-of-the-art results on grounded grammar induction on several languages. Results indicate that visual information is especially helpful in languages where high frequency words are more broadly distributed. Comparison between models with and without visual information shows that the grounded models are able to use visual information for proposing noun phrases, gathering useful information from images for unknown words, and achieving better performance at prepositional phrase attachment prediction."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-schuler-2020-grounded">
<titleInfo>
<title>Grounded PCFG Induction with Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Schuler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work in unsupervised parsing has tried to incorporate visual information into learning, but results suggest that these models need linguistic bias to compete against models that only rely on text. This work proposes grammar induction models which use visual information from images for labeled parsing, and achieve state-of-the-art results on grounded grammar induction on several languages. Results indicate that visual information is especially helpful in languages where high frequency words are more broadly distributed. Comparison between models with and without visual information shows that the grounded models are able to use visual information for proposing noun phrases, gathering useful information from images for unknown words, and achieving better performance at prepositional phrase attachment prediction.</abstract>
<identifier type="citekey">jin-schuler-2020-grounded</identifier>
<identifier type="doi">10.18653/v1/2020.aacl-main.42</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.42/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>396</start>
<end>408</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounded PCFG Induction with Images
%A Jin, Lifeng
%A Schuler, William
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F jin-schuler-2020-grounded
%X Recent work in unsupervised parsing has tried to incorporate visual information into learning, but results suggest that these models need linguistic bias to compete against models that only rely on text. This work proposes grammar induction models which use visual information from images for labeled parsing, and achieve state-of-the-art results on grounded grammar induction on several languages. Results indicate that visual information is especially helpful in languages where high frequency words are more broadly distributed. Comparison between models with and without visual information shows that the grounded models are able to use visual information for proposing noun phrases, gathering useful information from images for unknown words, and achieving better performance at prepositional phrase attachment prediction.
%R 10.18653/v1/2020.aacl-main.42
%U https://aclanthology.org/2020.aacl-main.42/
%U https://doi.org/10.18653/v1/2020.aacl-main.42
%P 396-408
Markdown (Informal)
[Grounded PCFG Induction with Images](https://aclanthology.org/2020.aacl-main.42/) (Jin & Schuler, AACL 2020)
ACL
- Lifeng Jin and William Schuler. 2020. Grounded PCFG Induction with Images. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 396–408, Suzhou, China. Association for Computational Linguistics.