@inproceedings{arodi-cheung-2021-textual-time,
title = "Textual Time Travel: A Temporally Informed Approach to Theory of Mind",
author = "Arodi, Akshatha and
Cheung, Jackie Chi Kit",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.351",
doi = "10.18653/v1/2021.findings-emnlp.351",
pages = "4162--4172",
abstract = "Natural language processing systems such as dialogue agents should be able to reason about other people{'}s beliefs, intentions and desires. This capability, called theory of mind (ToM), is crucial, as it allows a model to predict and interpret the needs of users based on their mental states. A recent line of research evaluates the ToM capability of existing memory-augmented neural models through question-answering. These models perform poorly on false belief tasks where beliefs differ from reality, especially when the dataset contains distracting sentences. In this paper, we propose a new temporally informed approach for improving the ToM capability of memory-augmented neural models. Our model incorporates priors about the entities{'} minds and tracks their mental states as they evolve over time through an extended passage. It then responds to queries through textual time travel{--}i.e., by accessing the stored memory of an earlier time step. We evaluate our model on ToM datasets and find that this approach improves performance, particularly by correcting the predicted mental states to match the false belief.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arodi-cheung-2021-textual-time">
<titleInfo>
<title>Textual Time Travel: A Temporally Informed Approach to Theory of Mind</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshatha</namePart>
<namePart type="family">Arodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackie</namePart>
<namePart type="given">Chi</namePart>
<namePart type="given">Kit</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language processing systems such as dialogue agents should be able to reason about other people’s beliefs, intentions and desires. This capability, called theory of mind (ToM), is crucial, as it allows a model to predict and interpret the needs of users based on their mental states. A recent line of research evaluates the ToM capability of existing memory-augmented neural models through question-answering. These models perform poorly on false belief tasks where beliefs differ from reality, especially when the dataset contains distracting sentences. In this paper, we propose a new temporally informed approach for improving the ToM capability of memory-augmented neural models. Our model incorporates priors about the entities’ minds and tracks their mental states as they evolve over time through an extended passage. It then responds to queries through textual time travel–i.e., by accessing the stored memory of an earlier time step. We evaluate our model on ToM datasets and find that this approach improves performance, particularly by correcting the predicted mental states to match the false belief.</abstract>
<identifier type="citekey">arodi-cheung-2021-textual-time</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.351</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.351</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4162</start>
<end>4172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Textual Time Travel: A Temporally Informed Approach to Theory of Mind
%A Arodi, Akshatha
%A Cheung, Jackie Chi Kit
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F arodi-cheung-2021-textual-time
%X Natural language processing systems such as dialogue agents should be able to reason about other people’s beliefs, intentions and desires. This capability, called theory of mind (ToM), is crucial, as it allows a model to predict and interpret the needs of users based on their mental states. A recent line of research evaluates the ToM capability of existing memory-augmented neural models through question-answering. These models perform poorly on false belief tasks where beliefs differ from reality, especially when the dataset contains distracting sentences. In this paper, we propose a new temporally informed approach for improving the ToM capability of memory-augmented neural models. Our model incorporates priors about the entities’ minds and tracks their mental states as they evolve over time through an extended passage. It then responds to queries through textual time travel–i.e., by accessing the stored memory of an earlier time step. We evaluate our model on ToM datasets and find that this approach improves performance, particularly by correcting the predicted mental states to match the false belief.
%R 10.18653/v1/2021.findings-emnlp.351
%U https://aclanthology.org/2021.findings-emnlp.351
%U https://doi.org/10.18653/v1/2021.findings-emnlp.351
%P 4162-4172
Markdown (Informal)
[Textual Time Travel: A Temporally Informed Approach to Theory of Mind](https://aclanthology.org/2021.findings-emnlp.351) (Arodi & Cheung, Findings 2021)
ACL