Neural Machine Translation of Rare Words with Subword Units
Sennrich et al., 2016, Neural Machine Translation of Rare Words with Subword Units (Proceedings of the 54th Annual Meeting of ACL (Volume 1: Long Papers))
Subscriber deck — free during early access
1 cards in “5.1 Unigram accuracy” · whole deck
5.1 Unigram accuracy
- Why can a smaller vocabulary with more subword-coded words be better?Words with frequency ranks between 50,000 and 500,000 occur only 2–60 times in training, too sparse to learn as single units; subword units are less sparse. A model representing them as subwords was more stable than one keeping them as whole words.
- Sennrich et al., 2016, Neural Machine Translation of Rare Words with Subword Units (Proceedings of the 54th Annual Meeting of ACL (Volume 1: Long Papers)), §5.1, p. 1721
Source
- Rico Sennrich, Barry Haddow and Alexandra Birch. 2016. Neural Machine Translation of Rare Words with Subword Units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715–1725. License: CC BY 4.0. Flashcards adapted from this work. doi:10.18653/v1/P16-1162 https://aclanthology.org/P16-1162/