This paper describes the ICS PAS system which took part in CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. The system consists of jointly trained tagger, lemmatizer, and dependency parser which are based on features extracted by a biLSTM network. The system uses both fully connected and dilated convolutional neural architectures. The novelty of our approach is the use of an additional loss function, which reduces the number of cycles in the predicted dependency graphs, and the use of self-training to increase the system performance. The proposed system, i.e. ICS PAS (Warszawa), ranked 3th/4th in the official evaluation obtaining the following overall results: 73.02 (LAS), 60.25 (MLAS) and 64.44 (BLEX).
Semi-Supervised Neural System for Tagging, Parsing and Lematization
The ICS PAS system achieves high performance in multilingual parsing using a joint biLSTM-based tagger, lemmatizer, and parser enhanced with additional loss functions and self-training.
- Year
- 2020
- Venue
- semi-supervised-neural-system-for-tagging
- Authors
- 2
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2004.12450ARXIV-DEFAULT
- TL;DR
- Semantic Scholar