@inproceedings{murty-etal-2021-dreca,
title = "{DR}e{C}a: A General Task Augmentation Strategy for Few-Shot Natural Language Inference",
author = "Murty, Shikhar and
Hashimoto, Tatsunori B. and
Manning, Christopher",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.88",
doi = "10.18653/v1/2021.naacl-main.88",
pages = "1113--1125",
abstract = "Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training. However, we believe meta-learning has not yet succeeded in NLP due to the lack of a well-defined task distribution, leading to attempts that treat datasets as tasks. Such an ad hoc task distribution causes problems of quantity and quality. Since there{'}s only a handful of datasets for any NLP problem, meta-learners tend to overfit their adaptation mechanism and, since NLP datasets are highly heterogeneous, many learning episodes have poor transfer between their support and query sets, which discourages the meta-learner from adapting. To alleviate these issues, we propose DReCA (Decomposing datasets into Reasoning Categories), a simple method for discovering and using latent reasoning categories in a dataset, to form additional high quality tasks. DReCA works by splitting examples into label groups, embedding them with a finetuned BERT model and then clustering each group into reasoning categories. Across four few-shot NLI problems, we demonstrate that using DReCA improves the accuracy of meta-learners by 1.5-4{\%}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murty-etal-2021-dreca">
<titleInfo>
<title>DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Murty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsunori</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training. However, we believe meta-learning has not yet succeeded in NLP due to the lack of a well-defined task distribution, leading to attempts that treat datasets as tasks. Such an ad hoc task distribution causes problems of quantity and quality. Since there’s only a handful of datasets for any NLP problem, meta-learners tend to overfit their adaptation mechanism and, since NLP datasets are highly heterogeneous, many learning episodes have poor transfer between their support and query sets, which discourages the meta-learner from adapting. To alleviate these issues, we propose DReCA (Decomposing datasets into Reasoning Categories), a simple method for discovering and using latent reasoning categories in a dataset, to form additional high quality tasks. DReCA works by splitting examples into label groups, embedding them with a finetuned BERT model and then clustering each group into reasoning categories. Across four few-shot NLI problems, we demonstrate that using DReCA improves the accuracy of meta-learners by 1.5-4%</abstract>
<identifier type="citekey">murty-etal-2021-dreca</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.88</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.88</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1113</start>
<end>1125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference
%A Murty, Shikhar
%A Hashimoto, Tatsunori B.
%A Manning, Christopher
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F murty-etal-2021-dreca
%X Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training. However, we believe meta-learning has not yet succeeded in NLP due to the lack of a well-defined task distribution, leading to attempts that treat datasets as tasks. Such an ad hoc task distribution causes problems of quantity and quality. Since there’s only a handful of datasets for any NLP problem, meta-learners tend to overfit their adaptation mechanism and, since NLP datasets are highly heterogeneous, many learning episodes have poor transfer between their support and query sets, which discourages the meta-learner from adapting. To alleviate these issues, we propose DReCA (Decomposing datasets into Reasoning Categories), a simple method for discovering and using latent reasoning categories in a dataset, to form additional high quality tasks. DReCA works by splitting examples into label groups, embedding them with a finetuned BERT model and then clustering each group into reasoning categories. Across four few-shot NLI problems, we demonstrate that using DReCA improves the accuracy of meta-learners by 1.5-4%
%R 10.18653/v1/2021.naacl-main.88
%U https://aclanthology.org/2021.naacl-main.88
%U https://doi.org/10.18653/v1/2021.naacl-main.88
%P 1113-1125
Markdown (Informal)
[DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference](https://aclanthology.org/2021.naacl-main.88) (Murty et al., NAACL 2021)
ACL