@inproceedings{jo-cinarel-2019-delta,
title = "Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings",
author = "Jo, Hwiyeol and
Cinarel, Ceyda",
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/D19-1347",
doi = "10.18653/v1/D19-1347",
pages = "3458--3463",
abstract = "We propose a novel and simple method for semi-supervised text classification. The method stems from the hypothesis that a classifier with pretrained word embeddings always outperforms the same classifier with randomly initialized word embeddings, as empirically observed in NLP tasks. Our method first builds two sets of classifiers as a form of model ensemble, and then initializes their word embeddings differently: one using random, the other using pretrained word embeddings. We focus on different predictions between the two classifiers on unlabeled data while following the self-training framework. We also use early-stopping in meta-epoch to improve the performance of our method. Our method, Delta-training, outperforms the self-training and the co-training framework in 4 different text classification datasets, showing robustness against error accumulation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jo-cinarel-2019-delta">
<titleInfo>
<title>Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hwiyeol</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ceyda</namePart>
<namePart type="family">Cinarel</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>We propose a novel and simple method for semi-supervised text classification. The method stems from the hypothesis that a classifier with pretrained word embeddings always outperforms the same classifier with randomly initialized word embeddings, as empirically observed in NLP tasks. Our method first builds two sets of classifiers as a form of model ensemble, and then initializes their word embeddings differently: one using random, the other using pretrained word embeddings. We focus on different predictions between the two classifiers on unlabeled data while following the self-training framework. We also use early-stopping in meta-epoch to improve the performance of our method. Our method, Delta-training, outperforms the self-training and the co-training framework in 4 different text classification datasets, showing robustness against error accumulation.</abstract>
<identifier type="citekey">jo-cinarel-2019-delta</identifier>
<identifier type="doi">10.18653/v1/D19-1347</identifier>
<location>
<url>https://aclanthology.org/D19-1347</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3458</start>
<end>3463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings
%A Jo, Hwiyeol
%A Cinarel, Ceyda
%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 jo-cinarel-2019-delta
%X We propose a novel and simple method for semi-supervised text classification. The method stems from the hypothesis that a classifier with pretrained word embeddings always outperforms the same classifier with randomly initialized word embeddings, as empirically observed in NLP tasks. Our method first builds two sets of classifiers as a form of model ensemble, and then initializes their word embeddings differently: one using random, the other using pretrained word embeddings. We focus on different predictions between the two classifiers on unlabeled data while following the self-training framework. We also use early-stopping in meta-epoch to improve the performance of our method. Our method, Delta-training, outperforms the self-training and the co-training framework in 4 different text classification datasets, showing robustness against error accumulation.
%R 10.18653/v1/D19-1347
%U https://aclanthology.org/D19-1347
%U https://doi.org/10.18653/v1/D19-1347
%P 3458-3463
Markdown (Informal)
[Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings](https://aclanthology.org/D19-1347) (Jo & Cinarel, EMNLP-IJCNLP 2019)
ACL