One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words

Prafulla Kumar Choubey, Ruihong Huang


Abstract
Most supervised word sense disambiguation (WSD) systems build word-specific classifiers by leveraging labeled data. However, when using word-specific classifiers, the sparseness of annotations leads to inferior sense disambiguation performance on less frequently seen words. To combat data sparsity, we propose to learn a single model that derives sense representations and meanwhile enforces congruence between a word instance and its right sense by using both sense-annotated data and lexical resources. The model is shared across words that allows utilizing sense correlations across words, and therefore helps to transfer common disambiguation rules from annotation-rich words to annotation-lean words. Empirical evaluation on benchmark datasets shows that the proposed shared model outperforms the equivalent classifier-based models by 1.7%, 2.5% and 3.8% in F1-score when using GloVe, ELMo and BERT word embeddings respectively.
Anthology ID:
2020.lrec-1.732
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
5978–5985
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.732
DOI:
Bibkey:
Cite (ACL):
Prafulla Kumar Choubey and Ruihong Huang. 2020. One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5978–5985, Marseille, France. European Language Resources Association.
Cite (Informal):
One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words (Choubey & Huang, LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.732.pdf