Abstract
Accurate dependency parsing requires large treebanks, which are only available for a few languages. We propose a method that takes advantage of shared structure across languages to build a mature parser using less training data. We propose a model for learning a shared "universal" parser that operates over an interlingual continuous representation of language, along with language-specific mapping components. Compared with supervised learning, our methods give a consistent 8-10% improvement across several treebanks in low-resource simulations.
Original language | English |
---|---|
Title of host publication | Conference Proceedings - EMNLP 2015 |
Subtitle of host publication | Conference on Empirical Methods in Natural Language Processing |
Place of Publication | Lisbon, Portugal |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 339-348 |
Number of pages | 10 |
ISBN (Electronic) | 9781941643327 |
Publication status | Published - 2015 |
Externally published | Yes |
Event | Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal Duration: 17 Sept 2015 → 21 Sept 2015 |
Conference
Conference | Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 |
---|---|
Country/Territory | Portugal |
City | Lisbon |
Period | 17/09/15 → 21/09/15 |