A neural joint model for Vietnamese word segmentation, POS tagging and dependency parsing
Dat Quoc Nguyen
Proceedings of the 17th Annual Workshop of the Australasian Language Technology Association | Australasian Language Technology Association | Published : 2019
We propose the first multi-task learning model for joint Vietnamese word segmentation, partof- speech (POS) tagging and dependency parsing. In particular, our model extends the BIST graph-based dependency parser (Kiperwasser and Goldberg, 2016) with BiLSTMCRF- based neural layers (Huang et al., 2015) for word segmentation and POS tagging. On Vietnamese benchmark datasets, experimental results show that our joint model obtains stateof- the-art or competitive performances.