Skip to Main content Skip to Navigation
Conference papers

A System for Multilingual Dependency Parsing based on Bidirectional LSTM Feature Representations

Abstract : In this paper, we present our multilingual dependency parser developed for the CoNLL 2017 UD Shared Task dealing with " Multilingual Parsing from Raw Text to Universal Dependencies " 1. Our parser extends the monolingual BIST-parser as a multi-source multilingual trainable parser. Thanks to multilingual word embeddings and one hot encodings for languages, our system can use both monolingual and multi-source training. We trained 69 monolingual language models and 13 multilingual models for the shared task. Our multilingual approach making use of different resources yield better results than the monolingual approach for 11 languages. Our system ranked 5 th and achieved 70.93 overall LAS score over the 81 test corpora (macro-averaged LAS F1 score).
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01722370
Contributor : Thierry Poibeau <>
Submitted on : Monday, March 12, 2018 - 12:24:58 AM
Last modification on : Wednesday, May 22, 2019 - 3:46:02 PM
Document(s) archivé(s) le : Wednesday, June 13, 2018 - 12:36:34 PM

File

K17-3006.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01722370, version 1

Collections

Citation

Kyungtae Lim, Thierry Poibeau. A System for Multilingual Dependency Parsing based on Bidirectional LSTM Feature Representations. Computational Natural Language Learning (CoNLL), ACL, Aug 2017, Vancouver, Canada. pp.63 - 70. ⟨hal-01722370⟩

Share

Metrics

Record views

179

Files downloads

297