@inproceedings{kim-etal-2022-cosim,
title = "{C}o{SI}m: Commonsense Reasoning for Counterfactual Scene Imagination",
author = "Kim, Hyounghun and
Zala, Abhay and
Bansal, Mohit",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.66/",
doi = "10.18653/v1/2022.naacl-main.66",
pages = "911--923",
abstract = "As humans, we can modify our assumptions about a scene by imagining alternative objects or concepts in our minds. For example, we can easily anticipate the implications of the sun being overcast by rain clouds (e.g., the street will get wet) and accordingly prepare for that. In this paper, we introduce a new dataset called Commonsense Reasoning for Counterfactual Scene Imagination (CoSIm) which is designed to evaluate the ability of AI systems to reason about scene change imagination. To be specific, in this multimodal task/dataset, models are given an image and an initial question-response pair about the image. Next, a counterfactual imagined scene change (in textual form) is applied, and the model has to predict the new response to the initial question based on this scene change. We collect 3.5K high-quality and challenging data instances, with each instance consisting of an image, a commonsense question with a response, a description of a counterfactual change, a new response to the question, and three distractor responses. Our dataset contains various complex scene change types (such as object addition/removal/state change, event description, environment change, etc.) that require models to imagine many different scenarios and reason about the changed scenes. We present a baseline model based on a vision-language Transformer (i.e., LXMERT) and ablation studies. Through human evaluation, we demonstrate a large human-model performance gap, suggesting room for promising future work on this challenging, counterfactual multimodal task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2022-cosim">
<titleInfo>
<title>CoSIm: Commonsense Reasoning for Counterfactual Scene Imagination</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyounghun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhay</namePart>
<namePart type="family">Zala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As humans, we can modify our assumptions about a scene by imagining alternative objects or concepts in our minds. For example, we can easily anticipate the implications of the sun being overcast by rain clouds (e.g., the street will get wet) and accordingly prepare for that. In this paper, we introduce a new dataset called Commonsense Reasoning for Counterfactual Scene Imagination (CoSIm) which is designed to evaluate the ability of AI systems to reason about scene change imagination. To be specific, in this multimodal task/dataset, models are given an image and an initial question-response pair about the image. Next, a counterfactual imagined scene change (in textual form) is applied, and the model has to predict the new response to the initial question based on this scene change. We collect 3.5K high-quality and challenging data instances, with each instance consisting of an image, a commonsense question with a response, a description of a counterfactual change, a new response to the question, and three distractor responses. Our dataset contains various complex scene change types (such as object addition/removal/state change, event description, environment change, etc.) that require models to imagine many different scenarios and reason about the changed scenes. We present a baseline model based on a vision-language Transformer (i.e., LXMERT) and ablation studies. Through human evaluation, we demonstrate a large human-model performance gap, suggesting room for promising future work on this challenging, counterfactual multimodal task.</abstract>
<identifier type="citekey">kim-etal-2022-cosim</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.66</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.66/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>911</start>
<end>923</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoSIm: Commonsense Reasoning for Counterfactual Scene Imagination
%A Kim, Hyounghun
%A Zala, Abhay
%A Bansal, Mohit
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F kim-etal-2022-cosim
%X As humans, we can modify our assumptions about a scene by imagining alternative objects or concepts in our minds. For example, we can easily anticipate the implications of the sun being overcast by rain clouds (e.g., the street will get wet) and accordingly prepare for that. In this paper, we introduce a new dataset called Commonsense Reasoning for Counterfactual Scene Imagination (CoSIm) which is designed to evaluate the ability of AI systems to reason about scene change imagination. To be specific, in this multimodal task/dataset, models are given an image and an initial question-response pair about the image. Next, a counterfactual imagined scene change (in textual form) is applied, and the model has to predict the new response to the initial question based on this scene change. We collect 3.5K high-quality and challenging data instances, with each instance consisting of an image, a commonsense question with a response, a description of a counterfactual change, a new response to the question, and three distractor responses. Our dataset contains various complex scene change types (such as object addition/removal/state change, event description, environment change, etc.) that require models to imagine many different scenarios and reason about the changed scenes. We present a baseline model based on a vision-language Transformer (i.e., LXMERT) and ablation studies. Through human evaluation, we demonstrate a large human-model performance gap, suggesting room for promising future work on this challenging, counterfactual multimodal task.
%R 10.18653/v1/2022.naacl-main.66
%U https://aclanthology.org/2022.naacl-main.66/
%U https://doi.org/10.18653/v1/2022.naacl-main.66
%P 911-923
Markdown (Informal)
[CoSIm: Commonsense Reasoning for Counterfactual Scene Imagination](https://aclanthology.org/2022.naacl-main.66/) (Kim et al., NAACL 2022)
ACL
- Hyounghun Kim, Abhay Zala, and Mohit Bansal. 2022. CoSIm: Commonsense Reasoning for Counterfactual Scene Imagination. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 911–923, Seattle, United States. Association for Computational Linguistics.