Semi-Supervised and Unsupervised Sense Annotation via Translations

Bradley Hauer, Grzegorz Kondrak, Yixing Luan, Arnob Mallik, Lili Mou


Abstract
Acquisition of multilingual training data continues to be a challenge in word sense disambiguation (WSD). To address this problem, unsupervised approaches have been proposed to automatically generate sense annotations for training supervised WSD systems. We present three new methods for creating sense-annotated corpora which leverage translations, parallel bitexts, lexical resources, as well as contextual and synset embeddings. Our semi-supervised method applies machine translation to transfer existing sense annotations to other languages. Our two unsupervised methods refine sense annotations produced by a knowledge-based WSD system via lexical translations in a parallel corpus. We obtain state-of-the-art results on standard WSD benchmarks.
Anthology ID:
2021.ranlp-1.57
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
504–513
Language:
URL:
https://aclanthology.org/2021.ranlp-1.57
DOI:
Bibkey:
Cite (ACL):
Bradley Hauer, Grzegorz Kondrak, Yixing Luan, Arnob Mallik, and Lili Mou. 2021. Semi-Supervised and Unsupervised Sense Annotation via Translations. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 504–513, Held Online. INCOMA Ltd..
Cite (Informal):
Semi-Supervised and Unsupervised Sense Annotation via Translations (Hauer et al., RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.57.pdf
Data
Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison