SEx BiST: A Multi-Source Trainable Parser with Deep Contextualized Lexical Representations - Université Sorbonne Nouvelle - Paris 3 Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

SEx BiST: A Multi-Source Trainable Parser with Deep Contextualized Lexical Representations

Résumé

We describe the SEx BiST parser (Seman-tically EXtended Bi-LSTM parser) developed at Lattice for the CoNLL 2018 Shared Task (Multilingual Parsing from Raw Text to Universal Dependencies). The main characteristic of our work is the encoding of three different modes of con-textual information for parsing: (i) Tree-bank feature representations, (ii) Multilingual word representations, (iii) ELMo representations obtained via unsupervised learning from external resources. Our parser performed well in the official end-to-end evaluation (73.02 LAS-4 th /26 teams, and 78.72 UAS-2 nd /26); remarkably , we achieved the best UAS scores on all the English corpora by applying the three suggested feature representations. Finally, we were also ranked 1 st at the optional event extraction task, part of the 2018 Extrinsic Parser Evaluation campaign .
Fichier principal
Vignette du fichier
K18-2014.pdf (286.62 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02977455 , version 1 (25-10-2020)

Identifiants

Citer

Kyungtae Lim, Cheoneum Park, Changki Lee, Thierry Poibeau. SEx BiST: A Multi-Source Trainable Parser with Deep Contextualized Lexical Representations. Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Oct 2018, Bruxelles, Belgium. pp.143-152, ⟨10.18653/v1/K18-2014⟩. ⟨hal-02977455⟩
586 Consultations
177 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More