| 4 |
Controllable Sentence Simplification
|
|
|
|
In: LREC 2020 - 12th Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-02678214 ; LREC 2020 - 12th Language Resources and Evaluation Conference, May 2020, Marseille, France ; http://www.lrec-conf.org/proceedings/lrec2020/index.html (2020)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
CamemBERT: a Tasty French Language Model
|
|
|
|
In: ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics ; https://hal.inria.fr/hal-02889805 ; ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Jul 2020, Seattle / Virtual, United States. ⟨10.18653/v1/2020.acl-main.645⟩ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
French Contextualized Word-Embeddings with a sip of CaBeRnet: a New French Balanced Reference Corpus
|
|
|
|
In: CMLC-8 - 8th Workshop on the Challenges in the Management of Large Corpora ; https://hal.inria.fr/hal-02678358 ; CMLC-8 - 8th Workshop on the Challenges in the Management of Large Corpora, May 2020, Marseille, France ; https://lrec2020.lrec-conf.org/media/proceedings/Workshops/Books/CMLC-8book.pdf (2020)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Controllable Sentence Simplification
|
|
|
|
In: https://hal.inria.fr/hal-02445874 ; 2019 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
CamemBERT: a Tasty French Language Model
|
|
|
|
In: https://hal.inria.fr/hal-02445946 ; 2019 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Reference-less Quality Estimation of Text Simplification Systems
|
|
|
|
In: 1st Workshop on Automatic Text Adaptation (ATA) ; https://hal.inria.fr/hal-01959054 ; 1st Workshop on Automatic Text Adaptation (ATA), Nov 2018, Tilburg, Netherlands ; https://www.ida.liu.se/~evere22/ATA-18/ (2018)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
ELMoLex: Connecting ELMo and Lexicon features for Dependency Parsing
|
|
|
|
In: CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies ; https://hal.inria.fr/hal-01959045 ; CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Oct 2018, Brussels, Belgium. ⟨10.18653/v1/K18-2023⟩ (2018)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer
|
|
|
|
In: Eleventh International Conference on Language Resources and Evaluation (LREC 2018) ; https://hal.inria.fr/hal-01798801 ; Eleventh International Conference on Language Resources and Evaluation (LREC 2018), May 2018, Miyazaki, Japan (2018)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy
|
|
|
|
In: Conference on Computational Natural Language Learning ; https://hal.inria.fr/hal-01584168 ; Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, ⟨10.18653/v1/K17-3026⟩ ; http://universaldependencies.org/conll17/ (2017)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Universal Dependencies 2.1
|
|
|
|
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Paris and Stanford at EPE 2017: Downstream Evaluation of Graph-based Dependency Representations
|
|
|
|
In: EPE 2017 - The First Shared Task on Extrinsic Parser Evaluation ; https://hal.inria.fr/hal-01592051 ; EPE 2017 - The First Shared Task on Extrinsic Parser Evaluation, Sep 2017, Pisa, Italy. pp.47-59 ; http://epe.nlpl.eu (2017)
|
|
Abstract:
International audience ; We describe the STANFORD-PARIS and PARIS-STANFORD submissions to the 2017 Extrinsic Parser Evaluation (EPE) Shared Task. The purpose of this shared task was to evaluate dependency graphs on three downstream tasks. Through our submissions, we evaluated the usability of several representations derived from English Universal Dependencies (UD), as well as the Stanford Dependencies (SD), Predicate Argument Structure (PAS), and DM representations. We further compared two parsing strategies: Directly parsing to graph-based dependency representations and a two-stage process of first parsing to surface syntax trees and then applying rule-based augmentations to obtain the final graphs. Overall, our systems performed very well and our submissions ranked first and third. In our analysis, we find that the two-stage parsing process leads to better downstream performance, and that enhanced UD, a graph-based representation, consistently outperforms basic UD, a strict surface syntax representation, suggesting an advantage of enriched representations for downstream tasks.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal.inria.fr/hal-01592051/file/epe17.pdf
https://hal.inria.fr/hal-01592051/document
https://hal.inria.fr/hal-01592051
|
|
BASE
|
|
Hide details
|
|
|
|
|
