Delexicalized Word Embeddings for Cross-lingual ...
Document type :
Communication dans un congrès avec actes
DOI :
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]
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
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]
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 >
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 :
Source :
Files
- https://hal.inria.fr/hal-01590639/document
- Open access
- Access the document
- https://doi.org/10.18653/v1/e17-1023
- Open access
- Access the document
- https://hal.inria.fr/hal-01590639/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01590639/document
- Open access
- Access the document
- document
- Open access
- Access the document
- E17-1023.pdf
- Open access
- Access the document
- e17-1023
- Open access
- Access the document