Abstract
Sequence generation models trained with teacher-forcing suffer from issues related to exposure bias and lack of differentiability across timesteps. Our proposed method, Teacher-Forcing with N-grams (TeaForN), addresses both these problems directly, through the use of a stack of N decoders trained to decode along a secondary time axis that allows model-parameter updates based on N prediction steps. TeaForN can be used with a wide class of decoder architectures and requires minimal modifications from a standard teacher-forcing setup. Empirically, we show that TeaForN boosts generation quality on one Machine Translation benchmark, WMT 2014 English-French, and two News Summarization benchmarks, CNN/Dailymail and Gigaword.- Anthology ID:
- 2020.emnlp-main.702
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8704–8717
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.702
- DOI:
- 10.18653/v1/2020.emnlp-main.702
- Cite (ACL):
- Sebastian Goodman, Nan Ding, and Radu Soricut. 2020. TeaForN: Teacher-Forcing with N-grams. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8704–8717, Online. Association for Computational Linguistics.
- Cite (Informal):
- TeaForN: Teacher-Forcing with N-grams (Goodman et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.emnlp-main.702.pdf