This portal has been archived. Explore the next generation of this technology.
The SLT-Interactions Parsing System at the CoNLL 2018 Shared Task
lib:aa1b845deb7853b2 (v1.0.0)
Authors: Riyaz A. Bhat,Irshad Bhat,Srinivas Bangalore
Where published: CONLL 2018 10
Document: PDF DOI
Abstract URL: https://www.aclweb.org/anthology/K18-2015/
This paper describes our system (SLT-Interactions) for the CoNLL 2018 shared task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system performs three main tasks: word segmentation (only for few treebanks), POS tagging and parsing. While segmentation is learned separately, we use neural stacking for joint learning of POS tagging and parsing tasks. For all the tasks, we employ simple neural network architectures that rely on long short-term memory (LSTM) networks for learning task-dependent features. At the basis of our parser, we use an arc-standard algorithm with Swap action for general non-projective parsing. Additionally, we use neural stacking as a knowledge transfer mechanism for cross-domain parsing of low resource domains. Our system shows substantial gains against the UDPipe baseline, with an average improvement of 4.18{\%} in LAS across all languages. Overall, we are placed at the 12th position on the official test sets.
Where published: CONLL 2018 10
Document: PDF DOI
Abstract URL: https://www.aclweb.org/anthology/K18-2015/
This paper describes our system (SLT-Interactions) for the CoNLL 2018 shared task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system performs three main tasks: word segmentation (only for few treebanks), POS tagging and parsing. While segmentation is learned separately, we use neural stacking for joint learning of POS tagging and parsing tasks. For all the tasks, we employ simple neural network architectures that rely on long short-term memory (LSTM) networks for learning task-dependent features. At the basis of our parser, we use an arc-standard algorithm with Swap action for general non-projective parsing. Additionally, we use neural stacking as a knowledge transfer mechanism for cross-domain parsing of low resource domains. Our system shows substantial gains against the UDPipe baseline, with an average improvement of 4.18{\%} in LAS across all languages. Overall, we are placed at the 12th position on the official test sets.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)