From raw text to universal dependencies – Look, no tags!
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
We present the Uppsala submission to the CoNLL 2017 shared task on parsing from raw text to universal dependencies. Our system is a simple pipeline consisting of two components. The first performs joint word and sentence segmentation on raw text; the second predicts dependency trees from raw words. The parser bypasses the need for part-of-speech tagging, but uses word embeddings based on universal tag distributions. We achieved a macro-averaged LAS F1 of 65.11 in the official test run and obtained the 2nd best result for sentence segmentation with a score of 89.03. After fixing two bugs, we obtained an unofficial LAS F1 of 70.49.
Originalsprog | Engelsk |
---|---|
Titel | Rediger CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies |
Antal sider | 11 |
Forlag | Association for Computational Linguistics (ACL) |
Publikationsdato | 2017 |
Sider | 207-217 |
DOI | |
Status | Udgivet - 2017 |
Eksternt udgivet | Ja |
Begivenhed | 2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017 - Vancouver, Canada Varighed: 3 aug. 2017 → 4 aug. 2017 |
Konference
Konference | 2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017 |
---|---|
Land | Canada |
By | Vancouver |
Periode | 03/08/2017 → 04/08/2017 |
Sponsor | CRACKER project, DFKI Berlin, et al., Google, Inc., text and form, UFAL |
Bibliografisk note
Publisher Copyright:
© 2017 Association for Computational Linguistics.
ID: 379728064