@inproceedings{tan-etal-2021-causal,
title = "Causal Augmentation for Causal Sentence Classification",
author = "Tan, Fiona Anting and
Hazarika, Devamanyu and
Ng, See-Kiong and
Poria, Soujanya and
Zimmermann, Roger",
editor = "Feder, Amir and
Keith, Katherine and
Manzoor, Emaad and
Pryzant, Reid and
Sridhar, Dhanya and
Wood-Doughty, Zach and
Eisenstein, Jacob and
Grimmer, Justin and
Reichart, Roi and
Roberts, Molly and
Shalit, Uri and
Stewart, Brandon and
Veitch, Victor and
Yang, Diyi",
booktitle = "Proceedings of the First Workshop on Causal Inference and NLP",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.cinlp-1.1",
doi = "10.18653/v1/2021.cinlp-1.1",
pages = "1--20",
abstract = "Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification. In particular, we found that models misclassify on augmented sentences that have been negated or strengthened with respect to its causal meaning. This is worrying since minor linguistic differences in causal sentences can have disparate meanings. Therefore, we propose the generation of counterfactual causal sentences by creating contrast sets (Gardner et al., 2020) to be included during model training. We experimented on two model architectures and predicted on two out-of-domain corpora. While our strengthening schemes proved useful in improving model performance, for negation, regular edits were insufficient. Thus, we also introduce heuristics like shortening or multiplying root words of a sentence. By including a mixture of edits when training, we achieved performance improvements beyond the baseline across both models, and within and out of corpus{'} domain, suggesting that our proposed augmentation can also help models generalize.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2021-causal">
<titleInfo>
<title>Causal Augmentation for Causal Sentence Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devamanyu</namePart>
<namePart type="family">Hazarika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">See-Kiong</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="family">Zimmermann</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>Proceedings of the First Workshop on Causal Inference and NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Feder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emaad</namePart>
<namePart type="family">Manzoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reid</namePart>
<namePart type="family">Pryzant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhanya</namePart>
<namePart type="family">Sridhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zach</namePart>
<namePart type="family">Wood-Doughty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Eisenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Grimmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uri</namePart>
<namePart type="family">Shalit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brandon</namePart>
<namePart type="family">Stewart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Veitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</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>Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification. In particular, we found that models misclassify on augmented sentences that have been negated or strengthened with respect to its causal meaning. This is worrying since minor linguistic differences in causal sentences can have disparate meanings. Therefore, we propose the generation of counterfactual causal sentences by creating contrast sets (Gardner et al., 2020) to be included during model training. We experimented on two model architectures and predicted on two out-of-domain corpora. While our strengthening schemes proved useful in improving model performance, for negation, regular edits were insufficient. Thus, we also introduce heuristics like shortening or multiplying root words of a sentence. By including a mixture of edits when training, we achieved performance improvements beyond the baseline across both models, and within and out of corpus’ domain, suggesting that our proposed augmentation can also help models generalize.</abstract>
<identifier type="citekey">tan-etal-2021-causal</identifier>
<identifier type="doi">10.18653/v1/2021.cinlp-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.cinlp-1.1</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Causal Augmentation for Causal Sentence Classification
%A Tan, Fiona Anting
%A Hazarika, Devamanyu
%A Ng, See-Kiong
%A Poria, Soujanya
%A Zimmermann, Roger
%Y Feder, Amir
%Y Keith, Katherine
%Y Manzoor, Emaad
%Y Pryzant, Reid
%Y Sridhar, Dhanya
%Y Wood-Doughty, Zach
%Y Eisenstein, Jacob
%Y Grimmer, Justin
%Y Reichart, Roi
%Y Roberts, Molly
%Y Shalit, Uri
%Y Stewart, Brandon
%Y Veitch, Victor
%Y Yang, Diyi
%S Proceedings of the First Workshop on Causal Inference and NLP
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F tan-etal-2021-causal
%X Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification. In particular, we found that models misclassify on augmented sentences that have been negated or strengthened with respect to its causal meaning. This is worrying since minor linguistic differences in causal sentences can have disparate meanings. Therefore, we propose the generation of counterfactual causal sentences by creating contrast sets (Gardner et al., 2020) to be included during model training. We experimented on two model architectures and predicted on two out-of-domain corpora. While our strengthening schemes proved useful in improving model performance, for negation, regular edits were insufficient. Thus, we also introduce heuristics like shortening or multiplying root words of a sentence. By including a mixture of edits when training, we achieved performance improvements beyond the baseline across both models, and within and out of corpus’ domain, suggesting that our proposed augmentation can also help models generalize.
%R 10.18653/v1/2021.cinlp-1.1
%U https://aclanthology.org/2021.cinlp-1.1
%U https://doi.org/10.18653/v1/2021.cinlp-1.1
%P 1-20
Markdown (Informal)
[Causal Augmentation for Causal Sentence Classification](https://aclanthology.org/2021.cinlp-1.1) (Tan et al., CINLP 2021)
ACL
- Fiona Anting Tan, Devamanyu Hazarika, See-Kiong Ng, Soujanya Poria, and Roger Zimmermann. 2021. Causal Augmentation for Causal Sentence Classification. In Proceedings of the First Workshop on Causal Inference and NLP, pages 1–20, Punta Cana, Dominican Republic. Association for Computational Linguistics.