@inproceedings{roy-etal-2019-leveraging,
title = "Leveraging Past References for Robust Language Grounding",
author = "Roy, Subhro and
Noseworthy, Michael and
Paul, Rohan and
Park, Daehyung and
Roy, Nicholas",
editor = "Bansal, Mohit and
Villavicencio, Aline",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1040",
doi = "10.18653/v1/K19-1040",
pages = "430--440",
abstract = "Grounding referring expressions to objects in an environment has traditionally been considered a one-off, ahistorical task. However, in realistic applications of grounding, multiple users will repeatedly refer to the same set of objects. As a result, past referring expressions for objects can provide strong signals for grounding subsequent referring expressions. We therefore reframe the grounding problem from the perspective of coreference detection and propose a neural network that detects when two expressions are referring to the same object. The network combines information from vision and past referring expressions to resolve which object is being referred to. Our experiments show that detecting referring expression coreference is an effective way to ground objects described by subtle visual properties, which standard visual grounding models have difficulty capturing. We also show the ability to detect object coreference allows the grounding model to perform well even when it encounters object categories not seen in the training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-etal-2019-leveraging">
<titleInfo>
<title>Leveraging Past References for Robust Language Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Subhro</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Noseworthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohan</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daehyung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grounding referring expressions to objects in an environment has traditionally been considered a one-off, ahistorical task. However, in realistic applications of grounding, multiple users will repeatedly refer to the same set of objects. As a result, past referring expressions for objects can provide strong signals for grounding subsequent referring expressions. We therefore reframe the grounding problem from the perspective of coreference detection and propose a neural network that detects when two expressions are referring to the same object. The network combines information from vision and past referring expressions to resolve which object is being referred to. Our experiments show that detecting referring expression coreference is an effective way to ground objects described by subtle visual properties, which standard visual grounding models have difficulty capturing. We also show the ability to detect object coreference allows the grounding model to perform well even when it encounters object categories not seen in the training data.</abstract>
<identifier type="citekey">roy-etal-2019-leveraging</identifier>
<identifier type="doi">10.18653/v1/K19-1040</identifier>
<location>
<url>https://aclanthology.org/K19-1040</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>430</start>
<end>440</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Past References for Robust Language Grounding
%A Roy, Subhro
%A Noseworthy, Michael
%A Paul, Rohan
%A Park, Daehyung
%A Roy, Nicholas
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F roy-etal-2019-leveraging
%X Grounding referring expressions to objects in an environment has traditionally been considered a one-off, ahistorical task. However, in realistic applications of grounding, multiple users will repeatedly refer to the same set of objects. As a result, past referring expressions for objects can provide strong signals for grounding subsequent referring expressions. We therefore reframe the grounding problem from the perspective of coreference detection and propose a neural network that detects when two expressions are referring to the same object. The network combines information from vision and past referring expressions to resolve which object is being referred to. Our experiments show that detecting referring expression coreference is an effective way to ground objects described by subtle visual properties, which standard visual grounding models have difficulty capturing. We also show the ability to detect object coreference allows the grounding model to perform well even when it encounters object categories not seen in the training data.
%R 10.18653/v1/K19-1040
%U https://aclanthology.org/K19-1040
%U https://doi.org/10.18653/v1/K19-1040
%P 430-440
Markdown (Informal)
[Leveraging Past References for Robust Language Grounding](https://aclanthology.org/K19-1040) (Roy et al., CoNLL 2019)
ACL
- Subhro Roy, Michael Noseworthy, Rohan Paul, Daehyung Park, and Nicholas Roy. 2019. Leveraging Past References for Robust Language Grounding. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 430–440, Hong Kong, China. Association for Computational Linguistics.