Abstract
This is a work in progress about extracting the sentence tree structures from the encoder’s self-attention weights, when translating into another language using the Transformer neural network architecture. We visualize the structures and discuss their characteristics with respect to the existing syntactic theories and annotations.- Anthology ID:
- W18-5444
- Volume:
- Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
- Month:
- November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Tal Linzen, Grzegorz Chrupała, Afra Alishahi
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 347–349
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/W18-5444/
- DOI:
- 10.18653/v1/W18-5444
- Cite (ACL):
- David Mareček and Rudolf Rosa. 2018. Extracting Syntactic Trees from Transformer Encoder Self-Attentions. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 347–349, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Extracting Syntactic Trees from Transformer Encoder Self-Attentions (Mareček & Rosa, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/W18-5444.pdf
- Data
- Universal Dependencies