Abstract
Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we investigate other forms of sharing in between no sharing and hard equality of parameters. In particular, we propose a structure-aware output layer which captures the semantic structure of the output space of words within a joint input-output embedding. The model is a generalized form of weight tying which shares parameters but allows learning a more flexible relationship with input word embeddings and allows the effective capacity of the output layer to be controlled. In addition, the model shares weights across output classifiers and translation contexts which allows it to better leverage prior knowledge about them. Our evaluation on English-to-Finnish and English-to-German datasets shows the effectiveness of the method against strong encoder-decoder baselines trained with or without weight tying.- Anthology ID:
- W18-6308
- Volume:
- Proceedings of the Third Conference on Machine Translation: Research Papers
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 73–83
- Language:
- URL:
- https://aclanthology.org/W18-6308
- DOI:
- 10.18653/v1/W18-6308
- Cite (ACL):
- Nikolaos Pappas, Lesly Miculicich, and James Henderson. 2018. Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 73–83, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation (Pappas et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W18-6308.pdf
- Code
- idiap/joint-embedding-nmt