A neural joint model for Vietnamese word segmentation, POS tagging and dependency parsing
This addresses the need for integrated NLP tools for Vietnamese, though it is incremental as it combines existing methods.
The authors tackled the problem of joint Vietnamese word segmentation, POS tagging, and dependency parsing by proposing the first multi-task learning model, which achieved state-of-the-art or competitive performances on benchmark datasets.
We propose the first multi-task learning model for joint Vietnamese word segmentation, part-of-speech (POS) tagging and dependency parsing. In particular, our model extends the BIST graph-based dependency parser (Kiperwasser and Goldberg, 2016) with BiLSTM-CRF-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 state-of-the-art or competitive performances.