This repo contains a set of neural transducer, e.g. sequence-to-sequence model, focusing on character-level tasks. It powers the following papars and workshop.
[1] Arya D McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Miikka Silfverberg, Sebastian J Mielke, Jeffrey Heinz, Ryan Cotterell, and Mans Hulden. The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection. ACL. 2019.
[2] Shijie Wu, Ryan Cotterell, and Timothy J O'Donnell. Morphological Irregularity Correlates with Frequency. ACL. 2019.
[3] Shijie Wu, and Ryan Cotterell. Exact Hard Monotonic Attention for Character-Level Transduction. ACL. 2019.
[4] Chaitanya Malaviya *, Shijie Wu *, and Ryan Cotterell. A Simple Joint Model for Improved Contextual Neural Lemmatization. NAACL. 2019.
* Equal contribution. Order has been determined with a coin flip.
[5] Shijie Wu, Pamela Shapiro, and Ryan Cotterell. Hard Non-Monotonic Attention for Character-Level Transduction. EMNLP. 2018.
- python 3
- pytorch==1.4
- numpy
- tqdm
- fire
makeMIT