| 1 |
Quantifying training challenges of dependency parsers
|
|
|
|
In: Proceedings of the 27th International Conference on Computational Linguistics, ; International Conference on Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-01907772 ; International Conference on Computational Linguistics, Aug 2018, Santa Fe, New Mexico, United States. pp.3191 - 3202 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees
|
|
|
|
In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; https://hal.archives-ouvertes.fr/hal-01813394 ; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, ACL, Jun 2018, New Orleans, United States. pp.413 - 419 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
PanParser: a Modular Implementation for Efficient Transition-Based Dependency Parsing
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 111, Iss 1, Pp 57-86 (2018) (2018)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
LIMSI@CoNLL'17: UD Shared Task
|
|
|
|
In: Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, ; Conference on Computational Natural Language Learning ; https://hal.archives-ouvertes.fr/hal-01622880 ; Conference on Computational Natural Language Learning, Association for computational linguistics, Aug 2017, Vancouver, Canada. pp.163-173, ⟨10.18653/v1/K17-3017⟩ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Don't Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers
|
|
|
|
In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics ; Conference of the European Chapter of the ACL ; https://hal.archives-ouvertes.fr/hal-01618377 ; Conference of the European Chapter of the ACL, Jan 2017, Valencia, Spain. pp.318 - 323, ⟨10.18653/v1/E17-2051⟩ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
LIMSI@WMT16: Machine Translation of News
|
|
|
|
In: First Conference on Machine Translation ; https://hal.archives-ouvertes.fr/hal-01388659 ; First Conference on Machine Translation, Aug 2016, Berlin, Germany. pp.239--245, ⟨10.18653/v1/W16-2304⟩ ; https://statmt.org/wmt16 (2016)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Cross-lingual alignment transfer: a chicken-and-egg story?
|
|
|
|
In: Workshop on Multilingual and Cross-lingual Methods in NLP ; https://hal.archives-ouvertes.fr/hal-01622815 ; Workshop on Multilingual and Cross-lingual Methods in NLP , Jun 2016, San Diego, CA, United States. pp.35-44, ⟨10.18653/v1/W16-1205⟩ ; https://aclanthology.coli.uni-saarland.de/volumes/proceedings-of-the-workshop-on-multilingual-and-cross-lingual-methods-in-nlp (2016)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Zero-resource Dependency Parsing: Boosting Delexicalized Cross-lingual Transfer with Linguistic Knowledge
|
|
|
|
In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers ; COLING 2016, the 26th International Conference on Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-01592335 ; COLING 2016, the 26th International Conference on Computational Linguistics, 2016, Osaka, Japan. pp.119--130 (2016)
|
|
Abstract:
International audience ; This paper studies cross-lingual transfer for dependency parsing, focusing on very low-resource settings where delexicalized transfer is the only fully automatic option. We show how to boost parsing performance by rewriting the source sentences so as to better match the linguistic regularities of the target language. We contrast a data-driven approach with an approach relying on linguistically motivated rules automatically extracted from the World Atlas of Language Structures. Our findings are backed up by experiments involving 40 languages. They show that both approaches greatly outperform the baseline, the knowledge-driven method yielding the best accuracies, with average improvements of +2.9 UAS, and up to +90 UAS (absolute) on some frequent PoS configurations.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal.archives-ouvertes.fr/hal-01592335/file/C16-1012.pdf
https://hal.archives-ouvertes.fr/hal-01592335/document
https://hal.archives-ouvertes.fr/hal-01592335
|
|
BASE
|
|
Hide details
|
|
|
|
|
