@inproceedings{dua-etal-2021-learning,
title = "Learning with Instance Bundles for Reading Comprehension",
author = "Dua, Dheeru and
Dasigi, Pradeep and
Singh, Sameer and
Gardner, Matt",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.584",
doi = "10.18653/v1/2021.emnlp-main.584",
pages = "7347--7357",
abstract = "When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related questions and their corresponding answers are not independent, and leveraging these relationships could provide a strong supervision signal to a model. Drawing on ideas from contrastive estimation, we introduce several new supervision losses that compare question-answer scores across multiple related instances. Specifically, we normalize these scores across various neighborhoods of closely contrasting questions and/or answers, adding a cross entropy loss term in addition to traditional maximum likelihood estimation. Our techniques require bundles of related question-answer pairs, which we either mine from within existing data or create using automated heuristics. We empirically demonstrate the effectiveness of training with instance bundles on two datasets{---}HotpotQA and ROPES{---}showing up to 9{\%} absolute gains in accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dua-etal-2021-learning">
<titleInfo>
<title>Learning with Instance Bundles for Reading Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dheeru</namePart>
<namePart type="family">Dua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Dasigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Gardner</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 2021 Conference on Empirical Methods in Natural Language Processing</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">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related questions and their corresponding answers are not independent, and leveraging these relationships could provide a strong supervision signal to a model. Drawing on ideas from contrastive estimation, we introduce several new supervision losses that compare question-answer scores across multiple related instances. Specifically, we normalize these scores across various neighborhoods of closely contrasting questions and/or answers, adding a cross entropy loss term in addition to traditional maximum likelihood estimation. Our techniques require bundles of related question-answer pairs, which we either mine from within existing data or create using automated heuristics. We empirically demonstrate the effectiveness of training with instance bundles on two datasets—HotpotQA and ROPES—showing up to 9% absolute gains in accuracy.</abstract>
<identifier type="citekey">dua-etal-2021-learning</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.584</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.584</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>7347</start>
<end>7357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning with Instance Bundles for Reading Comprehension
%A Dua, Dheeru
%A Dasigi, Pradeep
%A Singh, Sameer
%A Gardner, Matt
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F dua-etal-2021-learning
%X When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related questions and their corresponding answers are not independent, and leveraging these relationships could provide a strong supervision signal to a model. Drawing on ideas from contrastive estimation, we introduce several new supervision losses that compare question-answer scores across multiple related instances. Specifically, we normalize these scores across various neighborhoods of closely contrasting questions and/or answers, adding a cross entropy loss term in addition to traditional maximum likelihood estimation. Our techniques require bundles of related question-answer pairs, which we either mine from within existing data or create using automated heuristics. We empirically demonstrate the effectiveness of training with instance bundles on two datasets—HotpotQA and ROPES—showing up to 9% absolute gains in accuracy.
%R 10.18653/v1/2021.emnlp-main.584
%U https://aclanthology.org/2021.emnlp-main.584
%U https://doi.org/10.18653/v1/2021.emnlp-main.584
%P 7347-7357
Markdown (Informal)
[Learning with Instance Bundles for Reading Comprehension](https://aclanthology.org/2021.emnlp-main.584) (Dua et al., EMNLP 2021)
ACL
- Dheeru Dua, Pradeep Dasigi, Sameer Singh, and Matt Gardner. 2021. Learning with Instance Bundles for Reading Comprehension. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7347–7357, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.