@inproceedings{jiang-riloff-2022-identifying,
title = "Identifying Physical Object Use in Sentences",
author = "Jiang, Tianyu and
Riloff, Ellen",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.781",
doi = "10.18653/v1/2022.emnlp-main.781",
pages = "11362--11372",
abstract = "Commonsense knowledge about the typicalfunctions of physical objects allows people tomake inferences during sentence understanding.For example, we infer that {``}Sam enjoyedthe book{''} means that Sam enjoyed reading thebook, even though the action is implicit. Priorresearch has focused on learning the prototypicalfunctions of physical objects in order toenable inferences about implicit actions. Butmany sentences refer to objects even when theyare not used (e.g., {``}The book fell{''}). We arguethat NLP systems need to recognize whether anobject is being used before inferring how theobject is used. We define a new task called ObjectUse Classification that determines whethera physical object mentioned in a sentence wasused or likely will be used. We introduce a newdataset for this task and present a classificationmodel that exploits data augmentation methodsand FrameNet when fine-tuning a pre-trainedlanguage model. We also show that object useclassification combined with knowledge aboutthe prototypical functions of objects has thepotential to yield very good inferences aboutimplicit and anticipated actions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-riloff-2022-identifying">
<titleInfo>
<title>Identifying Physical Object Use in Sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Commonsense knowledge about the typicalfunctions of physical objects allows people tomake inferences during sentence understanding.For example, we infer that “Sam enjoyedthe book” means that Sam enjoyed reading thebook, even though the action is implicit. Priorresearch has focused on learning the prototypicalfunctions of physical objects in order toenable inferences about implicit actions. Butmany sentences refer to objects even when theyare not used (e.g., “The book fell”). We arguethat NLP systems need to recognize whether anobject is being used before inferring how theobject is used. We define a new task called ObjectUse Classification that determines whethera physical object mentioned in a sentence wasused or likely will be used. We introduce a newdataset for this task and present a classificationmodel that exploits data augmentation methodsand FrameNet when fine-tuning a pre-trainedlanguage model. We also show that object useclassification combined with knowledge aboutthe prototypical functions of objects has thepotential to yield very good inferences aboutimplicit and anticipated actions.</abstract>
<identifier type="citekey">jiang-riloff-2022-identifying</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.781</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.781</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11362</start>
<end>11372</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Physical Object Use in Sentences
%A Jiang, Tianyu
%A Riloff, Ellen
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F jiang-riloff-2022-identifying
%X Commonsense knowledge about the typicalfunctions of physical objects allows people tomake inferences during sentence understanding.For example, we infer that “Sam enjoyedthe book” means that Sam enjoyed reading thebook, even though the action is implicit. Priorresearch has focused on learning the prototypicalfunctions of physical objects in order toenable inferences about implicit actions. Butmany sentences refer to objects even when theyare not used (e.g., “The book fell”). We arguethat NLP systems need to recognize whether anobject is being used before inferring how theobject is used. We define a new task called ObjectUse Classification that determines whethera physical object mentioned in a sentence wasused or likely will be used. We introduce a newdataset for this task and present a classificationmodel that exploits data augmentation methodsand FrameNet when fine-tuning a pre-trainedlanguage model. We also show that object useclassification combined with knowledge aboutthe prototypical functions of objects has thepotential to yield very good inferences aboutimplicit and anticipated actions.
%R 10.18653/v1/2022.emnlp-main.781
%U https://aclanthology.org/2022.emnlp-main.781
%U https://doi.org/10.18653/v1/2022.emnlp-main.781
%P 11362-11372
Markdown (Informal)
[Identifying Physical Object Use in Sentences](https://aclanthology.org/2022.emnlp-main.781) (Jiang & Riloff, EMNLP 2022)
ACL
- Tianyu Jiang and Ellen Riloff. 2022. Identifying Physical Object Use in Sentences. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11362–11372, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.