@inproceedings{bansal-etal-2020-learning,
title = "Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks",
author = "Bansal, Trapit and
Jha, Rishikesh and
McCallum, Andrew",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.448",
doi = "10.18653/v1/2020.coling-main.448",
pages = "5108--5123",
abstract = "Pre-trained transformer models have shown enormous success in improving performance on several downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labeled data to achieve good performance. We consider this problem of learning to generalize to new tasks, with a few examples, as a meta-learning problem. While meta-learning has shown tremendous progress in recent years, its application is still limited to simulated problems or problems with limited diversity across tasks. We develop a novel method, LEOPARD, which enables optimization-based meta-learning across tasks with a different number of classes, and evaluate different methods on generalization to diverse NLP classification tasks. LEOPARD is trained with the state-of-the-art transformer architecture and shows better generalization to tasks not seen at all during training, with as few as 4 examples per label. Across 17 NLP tasks, including diverse domains of entity typing, natural language inference, sentiment analysis, and several other text classification tasks, we show that LEOPARD learns better initial parameters for few-shot learning than self-supervised pre-training or multi-task training, outperforming many strong baselines, for example, yielding 14.6{\%} average relative gain in accuracy on unseen tasks with only 4 examples per label.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bansal-etal-2020-learning">
<titleInfo>
<title>Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishikesh</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained transformer models have shown enormous success in improving performance on several downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labeled data to achieve good performance. We consider this problem of learning to generalize to new tasks, with a few examples, as a meta-learning problem. While meta-learning has shown tremendous progress in recent years, its application is still limited to simulated problems or problems with limited diversity across tasks. We develop a novel method, LEOPARD, which enables optimization-based meta-learning across tasks with a different number of classes, and evaluate different methods on generalization to diverse NLP classification tasks. LEOPARD is trained with the state-of-the-art transformer architecture and shows better generalization to tasks not seen at all during training, with as few as 4 examples per label. Across 17 NLP tasks, including diverse domains of entity typing, natural language inference, sentiment analysis, and several other text classification tasks, we show that LEOPARD learns better initial parameters for few-shot learning than self-supervised pre-training or multi-task training, outperforming many strong baselines, for example, yielding 14.6% average relative gain in accuracy on unseen tasks with only 4 examples per label.</abstract>
<identifier type="citekey">bansal-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.448</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.448</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5108</start>
<end>5123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks
%A Bansal, Trapit
%A Jha, Rishikesh
%A McCallum, Andrew
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F bansal-etal-2020-learning
%X Pre-trained transformer models have shown enormous success in improving performance on several downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labeled data to achieve good performance. We consider this problem of learning to generalize to new tasks, with a few examples, as a meta-learning problem. While meta-learning has shown tremendous progress in recent years, its application is still limited to simulated problems or problems with limited diversity across tasks. We develop a novel method, LEOPARD, which enables optimization-based meta-learning across tasks with a different number of classes, and evaluate different methods on generalization to diverse NLP classification tasks. LEOPARD is trained with the state-of-the-art transformer architecture and shows better generalization to tasks not seen at all during training, with as few as 4 examples per label. Across 17 NLP tasks, including diverse domains of entity typing, natural language inference, sentiment analysis, and several other text classification tasks, we show that LEOPARD learns better initial parameters for few-shot learning than self-supervised pre-training or multi-task training, outperforming many strong baselines, for example, yielding 14.6% average relative gain in accuracy on unseen tasks with only 4 examples per label.
%R 10.18653/v1/2020.coling-main.448
%U https://aclanthology.org/2020.coling-main.448
%U https://doi.org/10.18653/v1/2020.coling-main.448
%P 5108-5123
Markdown (Informal)
[Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks](https://aclanthology.org/2020.coling-main.448) (Bansal et al., COLING 2020)
ACL