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 .
Origine : Fichiers produits par l'(les) auteur(s)
Loading...