Generalised Zero-shot Learning for Entailment-based Text Classification with External Knowledge

Yuqi Wang, Wei Wang, Qi Chen, Kaizhu Huang, Anh Nguyen, Suparna De

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

4 Citations (Scopus)

Abstract

Text classification techniques have been substantially important to many smart computing applications, e.g. topic extraction and event detection. However, classification is always challenging when only insufficient amount of labelled data for model training is available. To mitigate this issue, zero-shot learning (ZSL) has been introduced for models to recognise new classes that have not been observed during the training stage. We propose an entailment-based zero-shot text classification model, named as S-BERT-CAM, to better capture the relationship between the premise and hypothesis in the BERT embedding space. Two widely used textual datasets are utilised to conduct the experiments. We fine-tune our model using 50% of the labels for each dataset and evaluate it on the label space containing all labels (including both seen and unseen labels). The experimental results demonstrate that our model is more robust to the generalised ZSL and significantly improves the overall performance against baselines.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE International Conference on Smart Computing, SMARTCOMP 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages19-25
Number of pages7
ISBN (Electronic)9781665481526
DOIs
Publication statusPublished - 2022
Event8th IEEE International Conference on Smart Computing, SMARTCOMP 2022 - Espoo, Finland
Duration: 20 Jun 202224 Jun 2022

Publication series

NameProceedings - 2022 IEEE International Conference on Smart Computing, SMARTCOMP 2022

Conference

Conference8th IEEE International Conference on Smart Computing, SMARTCOMP 2022
Country/TerritoryFinland
CityEspoo
Period20/06/2224/06/22

Keywords

  • BERT
  • Zero-shot learning
  • deep learning
  • natural language processing

Fingerprint

Dive into the research topics of 'Generalised Zero-shot Learning for Entailment-based Text Classification with External Knowledge'. Together they form a unique fingerprint.

Cite this