@inproceedings{rajagopal-etal-2020-ask,
title = "What-if {I} ask you to explain: Explaining the effects of perturbations in procedural text",
author = "Rajagopal, Dheeraj and
Tandon, Niket and
Clark, Peter and
Dalvi, Bhavana and
Hovy, Eduard",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.300/",
doi = "10.18653/v1/2020.findings-emnlp.300",
pages = "3345--3355",
abstract = "Our goal is to explain the effects of perturbations in procedural text, e.g., given a passage describing a rabbit`s life cycle, explain why illness (the perturbation) may reduce the rabbit population (the effect). Although modern systems are able to solve the original prediction task well (e.g., illness results in less rabbits), the explanation task - identifying the causal chain of events from perturbation to effect - remains largely unaddressed, and is the goal of this research. We present QUARTET, a system that constructs such explanations from paragraphs, by modeling the explanation task as a multitask learning problem. QUARTET constructs explanations from the sentences in the procedural text, achieving {\textasciitilde}18 points better on explanation accuracy compared to several strong baselines on a recent process comprehension benchmark. On an end task on this benchmark, we show a surprising finding that good explanations do not have to come at the expense of end task performance, in fact leading to a 7{\%} F1 improvement over SOTA."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajagopal-etal-2020-ask">
<titleInfo>
<title>What-if I ask you to explain: Explaining the effects of perturbations in procedural text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dheeraj</namePart>
<namePart type="family">Rajagopal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhavana</namePart>
<namePart type="family">Dalvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our goal is to explain the effects of perturbations in procedural text, e.g., given a passage describing a rabbit‘s life cycle, explain why illness (the perturbation) may reduce the rabbit population (the effect). Although modern systems are able to solve the original prediction task well (e.g., illness results in less rabbits), the explanation task - identifying the causal chain of events from perturbation to effect - remains largely unaddressed, and is the goal of this research. We present QUARTET, a system that constructs such explanations from paragraphs, by modeling the explanation task as a multitask learning problem. QUARTET constructs explanations from the sentences in the procedural text, achieving ~18 points better on explanation accuracy compared to several strong baselines on a recent process comprehension benchmark. On an end task on this benchmark, we show a surprising finding that good explanations do not have to come at the expense of end task performance, in fact leading to a 7% F1 improvement over SOTA.</abstract>
<identifier type="citekey">rajagopal-etal-2020-ask</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.300</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.300/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3345</start>
<end>3355</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What-if I ask you to explain: Explaining the effects of perturbations in procedural text
%A Rajagopal, Dheeraj
%A Tandon, Niket
%A Clark, Peter
%A Dalvi, Bhavana
%A Hovy, Eduard
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F rajagopal-etal-2020-ask
%X Our goal is to explain the effects of perturbations in procedural text, e.g., given a passage describing a rabbit‘s life cycle, explain why illness (the perturbation) may reduce the rabbit population (the effect). Although modern systems are able to solve the original prediction task well (e.g., illness results in less rabbits), the explanation task - identifying the causal chain of events from perturbation to effect - remains largely unaddressed, and is the goal of this research. We present QUARTET, a system that constructs such explanations from paragraphs, by modeling the explanation task as a multitask learning problem. QUARTET constructs explanations from the sentences in the procedural text, achieving ~18 points better on explanation accuracy compared to several strong baselines on a recent process comprehension benchmark. On an end task on this benchmark, we show a surprising finding that good explanations do not have to come at the expense of end task performance, in fact leading to a 7% F1 improvement over SOTA.
%R 10.18653/v1/2020.findings-emnlp.300
%U https://aclanthology.org/2020.findings-emnlp.300/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.300
%P 3345-3355
Markdown (Informal)
[What-if I ask you to explain: Explaining the effects of perturbations in procedural text](https://aclanthology.org/2020.findings-emnlp.300/) (Rajagopal et al., Findings 2020)
ACL