1 |
GeSERA: General-domain Summary Evaluation by Relevance Analysis
|
|
|
|
In: RANLP 2021 Recent Advances in Natural Language Processing ; https://hal-cnrs.archives-ouvertes.fr/hal-03408902 ; RANLP 2021 Recent Advances in Natural Language Processing, Sep 2021, Online, Bulgaria (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Deep Learning Enhanced with Graph Knowledge for Sentiment Analysis
|
|
|
|
In: 6th International Workshop on eXplainable SENTIment Mining and EmotioN deTection co-located with 18th Extended Semantic Web Conference 2021 (X-SENTIMENT 2021) ; https://hal.archives-ouvertes.fr/hal-03558933 ; 6th International Workshop on eXplainable SENTIment Mining and EmotioN deTection co-located with 18th Extended Semantic Web Conference 2021 (X-SENTIMENT 2021), Jun 2021, Hersonissos, Greece. pp.74-86 ; http://ceur-ws.org/Vol-2918/ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Strength in Numbers: Averaging and Clustering Effects in Mixture of Experts for Graph-Based Dependency Parsing
|
|
|
|
In: 17th International Conference on Parsing Technologies (IWPT 2021) ; https://hal.archives-ouvertes.fr/hal-03558605 ; 17th International Conference on Parsing Technologies (IWPT 2021), Aug 2021, Online, United States. p. 106-118 ; https://aclanthology.org/volumes/2021.iwpt-1/ (2021)
|
|
Abstract:
International audience ; We review two features of mixture of experts (MoE) models which we call averaging and clustering effects in the context of graph-based dependency parsers learned in a supervised probabilistic framework. Averaging corresponds to the ensemble combination of parsers and is responsible for variance reduction which helps stabilizing and improving parsing accuracy. Clustering describes the capacity of MoE models to give more credit to experts believed to be more accurate given an input. Although promising, this is difficult to achieve, especially without additional data. We design an experimental set-up to study the impact of these effects. Whereas averaging is always beneficial, clustering requires good initialization and stabilization techniques, but its advantages over mere averaging seem to eventually vanish when enough experts are present. As a by product, we show how this leads to state-of-the-art results on the PTB and the CoNLL09 Chinese treebank, with low variance across experiments.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; [INFO]Computer Science [cs]
|
|
URL: https://hal.archives-ouvertes.fr/hal-03558605
|
|
BASE
|
|
Hide details
|
|
4 |
Strength in Numbers: Averaging and Clustering Effects in Mixture of Experts for Graph-Based Dependency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
GeSERA: General-domain Summary Evaluation by Relevance Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Integrating Dependency Parses with Sequential Patterns to Improve Relation Extraction ; Apport des dépendances syntaxiques et des patrons séquentiels à l'extraction de relations
|
|
|
|
In: TALN 2018 ; https://hal.inria.fr/hal-02079719 ; TALN 2018, May 2018, Rennes, France (2018)
|
|
BASE
|
|
Show details
|
|
9 |
The balance between quantitative and qualitative literary stylistics: How the method of "motifs" can help
|
|
|
|
In: The Grammar of Genres and styles ; https://hal.archives-ouvertes.fr/hal-03546266 ; Legallois, Charnois, Larjavaara. The Grammar of Genres and styles, De Gruyter Mouton, 2018, 9783110589689. ⟨10.1515/9783110595864-008⟩ ; https://www-degruyter-com.ezproxy.univ-paris3.fr/document/doi/10.1515/9783110595864/html (2018)
|
|
BASE
|
|
Show details
|
|
10 |
Approaching French theatrical characters by syntactical analysis: a study with motifs and correspondence analysis
|
|
|
|
In: The Grammar of Genres and Styles. From Discrete to Non-Discrete Units ; https://hal.archives-ouvertes.fr/hal-03482615 ; Dominique Legallois; Thierry Charnois; Meri Larjavaara. The Grammar of Genres and Styles. From Discrete to Non-Discrete Units, 320, De Gruyter Mouton, pp.118-139, 2018, Trends in Linguistics. Studies and Monographs [TiLSM], 978-3-11-058968-9. ⟨10.1515/9783110595864-006⟩ (2018)
|
|
BASE
|
|
Show details
|
|
12 |
An Experimental Approach For Information Extraction in Multi-Party Dialogue Discourse
|
|
|
|
In: CICLing 2018 - 19th International Conference on Computational Linguistics and Intelligent Text Processing ; https://hal.archives-ouvertes.fr/hal-01804147 ; CICLing 2018 - 19th International Conference on Computational Linguistics and Intelligent Text Processing, Mar 2018, Hanoi, Vietnam. pp.1-14 (2018)
|
|
BASE
|
|
Show details
|
|
13 |
The Grammar of Genres and Styles : From Discrete to Non-Discrete Units
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03540351 ; 2018, 9783110589689 (2018)
|
|
BASE
|
|
Show details
|
|
14 |
Linguistic features of genre and method variation in translation: A computational perspective
|
|
|
|
In: 92 ; 117 (2018)
|
|
BASE
|
|
Show details
|
|
15 |
Combining Syntactic and Sequential Patterns for Unsupervised Semantic Relation Extraction.
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01591501 ; CEUR-WS.org. Macedonia. 1881, pp.81-84, 2017, Interactions between Data Mining and Natural Language Processing 2017 (2017)
|
|
BASE
|
|
Show details
|
|
16 |
Identifying clichés in romance novels using the "motifs" method ; Repérer les clichés dans les romans sentimentaux grâce à la méthode des « motifs »
|
|
|
|
In: ISSN: 1146-6480 ; EISSN: 1960-6052 ; LIDIL - Revue de linguistique et de didactique des langues ; https://hal.archives-ouvertes.fr/hal-01956486 ; LIDIL - Revue de linguistique et de didactique des langues, UGA Editions, 2016 (2016)
|
|
BASE
|
|
Show details
|
|
17 |
Semantic Annotation of the ACL Anthology Corpus for the Automatic Analysis of Scientific Literature
|
|
|
|
In: LREC 2016 ; https://hal.archives-ouvertes.fr/hal-01360407 ; LREC 2016, May 2016, Portoroz, Slovenia (2016)
|
|
BASE
|
|
Show details
|
|
18 |
Pattern mining and CRF for symptoms recognition in biomedical texts ; Fouille de motifs et CRF pour la reconnaissance de symptômes dans les textes biomédicaux
|
|
|
|
In: 23e conférence sur le Traitement Automatique des Langues Naturelles (TALN’16) ; https://halshs.archives-ouvertes.fr/halshs-01727081 ; 23e conférence sur le Traitement Automatique des Langues Naturelles (TALN’16), Jul 2016, Paris, France. pp.194-206 (2016)
|
|
BASE
|
|
Show details
|
|
19 |
Weakly-supervised Symptom Recognition for Rare Diseases in Biomedical Text
|
|
|
|
In: 15th International Symposium on Intelligent Data Analysis ; https://halshs.archives-ouvertes.fr/halshs-01727071 ; 15th International Symposium on Intelligent Data Analysis, Oct 2016, Stockholm, Sweden (2016)
|
|
BASE
|
|
Show details
|
|
20 |
Identification of Shell Nouns, Signals of Discourse Organisation ; Identification des noms sous-spécifiés, signaux de l’organisation discursive
|
|
|
|
In: Proceedings of TALN 2014 (Volume 1: Long Papers) ; 21ème conférence sur le Traitement Automatique des Langues Naturelles ; https://hal.archives-ouvertes.fr/hal-01076760 ; 21ème conférence sur le Traitement Automatique des Langues Naturelles, Jul 2014, Marseille, France. pp.377-388 ; https://www.aclweb.org/anthology/F14-1033 (2014)
|
|
BASE
|
|
Show details
|
|
|
|