Title :

Delexicalized Word Embeddings for Cross-lingual Dependency Parsing

Author(s) :

Dehouck, Mathieu [Auteur]
Machine Learning in Information Networks [MAGNET]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Denis, Pascal [Auteur]
Machine Learning in Information Networks [MAGNET]

Conference title :

EACL

City :

Valencia

Country :

Espagne

Start date of the conference :

2017-04-03

Book title :

EACL

Journal title :

EACL 2017

Publication date :

2017-04

English keyword(s) :

Word Embedding
Dependency Parsing
Cross-Lingual
Representation
Learning

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Informatique et langage [cs.CL]
Informatique [cs]/Apprentissage [cs.LG]

English abstract : [en]

This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language. Specifically , this approach ...
Show more >This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language. Specifically , this approach first constructs word vector representations that exploit structural (i.e., dependency-based) contexts but only considering the morpho-syntactic information associated with each word and its contexts. These delexicalized word em-beddings, which can be trained on any set of languages and capture features shared across languages, are then used in combination with standard language-specific features to train a lexicalized parser in the target language. We evaluate our approach through experiments on a set of eight different languages that are part the Universal Dependencies Project. Our main results show that using such delexicalized embeddings, either trained in a monolin-gual or multilingual fashion, achieves significant improvements over monolingual baselines.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL