@inproceedings{melamud-etal-2019-combining,
title = "Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification",
author = "Melamud, Oren and
Bornea, Mihaela and
Barker, Ken",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1401",
doi = "10.18653/v1/D19-1401",
pages = "3884--3893",
abstract = "Supervised learning models often perform poorly at low-shot tasks, i.e. tasks for which little labeled data is available for training. One prominent approach for improving low-shot learning is to use unsupervised pre-trained neural models. Another approach is to obtain richer supervision by collecting annotator rationales (explanations supporting label annotations). In this work, we combine these two approaches to improve low-shot text classification with two novel methods: a simple bag-of-words embedding approach; and a more complex context-aware method, based on the BERT model. In experiments with two English text classification datasets, we demonstrate substantial performance gains from combining pre-training with rationales. Furthermore, our investigation of a range of train-set sizes reveals that the simple bag-of-words approach is the clear top performer when there are only a few dozen training instances or less, while more complex models, such as BERT or CNN, require more training data to shine.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="melamud-etal-2019-combining">
<titleInfo>
<title>Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Melamud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihaela</namePart>
<namePart type="family">Bornea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ken</namePart>
<namePart type="family">Barker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Supervised learning models often perform poorly at low-shot tasks, i.e. tasks for which little labeled data is available for training. One prominent approach for improving low-shot learning is to use unsupervised pre-trained neural models. Another approach is to obtain richer supervision by collecting annotator rationales (explanations supporting label annotations). In this work, we combine these two approaches to improve low-shot text classification with two novel methods: a simple bag-of-words embedding approach; and a more complex context-aware method, based on the BERT model. In experiments with two English text classification datasets, we demonstrate substantial performance gains from combining pre-training with rationales. Furthermore, our investigation of a range of train-set sizes reveals that the simple bag-of-words approach is the clear top performer when there are only a few dozen training instances or less, while more complex models, such as BERT or CNN, require more training data to shine.</abstract>
<identifier type="citekey">melamud-etal-2019-combining</identifier>
<identifier type="doi">10.18653/v1/D19-1401</identifier>
<location>
<url>https://aclanthology.org/D19-1401</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3884</start>
<end>3893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification
%A Melamud, Oren
%A Bornea, Mihaela
%A Barker, Ken
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F melamud-etal-2019-combining
%X Supervised learning models often perform poorly at low-shot tasks, i.e. tasks for which little labeled data is available for training. One prominent approach for improving low-shot learning is to use unsupervised pre-trained neural models. Another approach is to obtain richer supervision by collecting annotator rationales (explanations supporting label annotations). In this work, we combine these two approaches to improve low-shot text classification with two novel methods: a simple bag-of-words embedding approach; and a more complex context-aware method, based on the BERT model. In experiments with two English text classification datasets, we demonstrate substantial performance gains from combining pre-training with rationales. Furthermore, our investigation of a range of train-set sizes reveals that the simple bag-of-words approach is the clear top performer when there are only a few dozen training instances or less, while more complex models, such as BERT or CNN, require more training data to shine.
%R 10.18653/v1/D19-1401
%U https://aclanthology.org/D19-1401
%U https://doi.org/10.18653/v1/D19-1401
%P 3884-3893
Markdown (Informal)
[Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification](https://aclanthology.org/D19-1401) (Melamud et al., EMNLP-IJCNLP 2019)
ACL