SALNet: Semi-Supervised Few-Shot Text Classification with Attention-based Lexicon Construction

Ju Hyoung Lee, Sang Ki Ko, Yo Sub Han

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Scopus citations

Abstract

We propose a semi-supervised bootstrap learning framework for few-shot text classification. From a small number of the initial data, our framework obtains a larger set of reliable training data by using the attention weights from an LSTMbased trained classifier. We first train an LSTM-based text classifier from a given labeled dataset using the attention mechanism. Then, we collect a set of words for each class called a lexicon, which is supposed to be a representative set of words for each class based on the attention weights calculated for the classification task. We bootstrap the classifier using the new data that are labeled by the combination of the classifier and the constructed lexicons to improve the prediction accuracy. As a result, our approach outperforms the previous state-of-the-art methods including semisupervised learning algorithms and pretraining algorithms for few-shot text classification task on four publicly available benchmark datasets. Moreover, we empirically confirm that the constructed lexicons are reliable enough and substantially improve the performance of the original classifier.

Original languageEnglish
Title of host publication35th AAAI Conference on Artificial Intelligence, AAAI 2021
PublisherAssociation for the Advancement of Artificial Intelligence
Pages13189-13197
Number of pages9
ISBN (Electronic)9781713835974
StatePublished - 2021
Event35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
Duration: 2 Feb 20219 Feb 2021

Publication series

Name35th AAAI Conference on Artificial Intelligence, AAAI 2021
Volume14B

Conference

Conference35th AAAI Conference on Artificial Intelligence, AAAI 2021
CityVirtual, Online
Period2/02/219/02/21

Fingerprint

Dive into the research topics of 'SALNet: Semi-Supervised Few-Shot Text Classification with Attention-based Lexicon Construction'. Together they form a unique fingerprint.

Cite this