1 |
Delexicalized Word Embeddings for Cross-lingual Dependency Parsing
|
|
|
|
In: EACL ; https://hal.inria.fr/hal-01590639 ; EACL, Apr 2017, Valencia, Spain. pp.241 - 250, ⟨10.18653/v1/E17-1023⟩ ; http://eacl2017.org/ (2017)
|
|
Abstract:
International audience ; 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.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing; Cross-Lingual; Dependency Parsing; Learning; Representation; Word Embedding
|
|
URL: https://doi.org/10.18653/v1/E17-1023 https://hal.inria.fr/hal-01590639/document https://hal.inria.fr/hal-01590639 https://hal.inria.fr/hal-01590639/file/E17-1023.pdf
|
|
BASE
|
|
Hide details
|
|
2 |
IRISA at DeFT2017 : classification systems of increasing complexity ; Participation de l'IRISA à DeFT2017 : systèmes de classification de complexité croissante
|
|
|
|
In: DeFT 2017 - Défi Fouille de texte ; https://hal.archives-ouvertes.fr/hal-01643993 ; DeFT 2017 - Défi Fouille de texte, Jun 2017, Orléans, France. pp.1-10 (2017)
|
|
BASE
|
|
Show details
|
|
3 |
Invariance: a Theoretical Approach for Coding Sets of Words Modulo Literal (Anti)Morphisms
|
|
|
|
In: Springer, LNCS. ; https://hal-normandie-univ.archives-ouvertes.fr/hal-02117030 ; Springer, LNCS., 2017, pp.214-227 (2017)
|
|
BASE
|
|
Show details
|
|
4 |
Things and Strings and More: Improving Place Name Disambiguation from Short Texts by Combining Entity Co-Occurrence, Topic Modeling, and Word Embedding
|
|
Ju, Yiting. - : eScholarship, University of California, 2017
|
|
In: Ju, Yiting. (2017). Things and Strings and More: Improving Place Name Disambiguation from Short Texts by Combining Entity Co-Occurrence, Topic Modeling, and Word Embedding. 0035: Geography. Retrieved from: http://www.escholarship.org/uc/item/4w60s702 (2017)
|
|
BASE
|
|
Show details
|
|
5 |
An empirical study of the Algerian dialect of Social network
|
|
|
|
In: ICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing ; https://hal.inria.fr/hal-01659997 ; ICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, Dec 2017, Casablanca, Morocco ; http://icnlssp.isga.ma (2017)
|
|
BASE
|
|
Show details
|
|
7 |
Linguistic Knowledge Transfer for Enriching Vector Representations
|
|
|
|
In: http://rave.ohiolink.edu/etdc/view?acc_num=osu1500571436042414 (2017)
|
|
BASE
|
|
Show details
|
|
11 |
Induction de lexiques bilingues à partir de corpus comparables et parallèles
|
|
|
|
BASE
|
|
Show details
|
|
|
|