A Fast and Lightweight System for Multilingual Dependency Parsing
2017
Following Kiperwasser and Goldberg (2016), we present a multilingual dependency parser with a bidirectional LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier.
We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multi-
lingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system
Mengest is 61.33%.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
10
References
2
Citations
NaN
KQI