A neural joint model for Vietnamese word segmentation, POS tagging and dependency parsing
share
We propose the first joint model for Vietnamese word segmentation, part-of-speech (POS) tagging and dependency parsing. 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 benchmark Vietnamese datasets, experimental results show that our joint model obtains state-of-the-art or competitive performances.
READ FULL TEXT