Abstract
This paper describes SimpleNER, a model developed for the sentence simplification task at GEM-2021. Our system is a monolingual Seq2Seq Transformer architecture that uses control tokens pre-pended to the data, allowing the model to shape the generated simplifications according to user desired attributes. Additionally, we show that NER-tagging the training data before use helps stabilize the effect of the control tokens and significantly improves the overall performance of the system. We also employ pretrained embeddings to reduce data sparsity and allow the model to produce more generalizable outputs.- Anthology ID:
- 2021.gem-1.14
- Volume:
- Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Antoine Bosselut, Esin Durmus, Varun Prashant Gangal, Sebastian Gehrmann, Yacine Jernite, Laura Perez-Beltrachini, Samira Shaikh, Wei Xu
- Venue:
- GEM
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 155–160
- Language:
- URL:
- https://aclanthology.org/2021.gem-1.14
- DOI:
- 10.18653/v1/2021.gem-1.14
- Cite (ACL):
- K V Aditya Srivatsa, Monil Gokani, and Manish Shrivastava. 2021. SimpleNER Sentence Simplification System for GEM 2021. In Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021), pages 155–160, Online. Association for Computational Linguistics.
- Cite (Informal):
- SimpleNER Sentence Simplification System for GEM 2021 (Srivatsa et al., GEM 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.gem-1.14.pdf
- Data
- ASSET, TurkCorpus, WikiLarge