Abstract
We propose a new unsupervised lexical simplification method that uses only monolingual data and pre-trained language models. Given a target word and its context, our method generates substitutes based on the target context and also additional contexts sampled from monolingual data. We conduct experiments in English, Portuguese, and Spanish on the TSAR-2022 shared task, and show that our model substantially outperforms other unsupervised systems across all languages. We also establish a new state-of-the-art by ensembling our model with GPT-3.5. Lastly, we evaluate our model on the SWORDS lexical substitution data set, achieving a state-of-the-art result.- Anthology ID:
- 2023.findings-emnlp.627
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9368–9379
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.627
- DOI:
- 10.18653/v1/2023.findings-emnlp.627
- Cite (ACL):
- Takashi Wada, Timothy Baldwin, and Jey Lau. 2023. Unsupervised Lexical Simplification with Context Augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9368–9379, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Unsupervised Lexical Simplification with Context Augmentation (Wada et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.627.pdf