Výsledky vyhledávání

Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations

Autor: Joseph Le Roux, Nizar Habash, Yash Kankanampati, Dima Taji, Nadi Tomeh

Publikováno v: Proceedings of the 28th International Conference on Computational Linguistics
28th International Conference on Computational Linguistics
28th International Conference on Computational Linguistics, Dec 2020, Barcelona (on line), Spain. ⟨10.18653/v1/2020.coling-main.225⟩
COLING

International audience; We present a parsing model for projective dependency trees which takes advantage of the existence of complementary dependency annotations for a language. This is the case for Arabic with the availability of CATiB and UD treeba

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::437bdc6ba72d4170c2ff1cdbec3fd31a
https://hal.archives-ouvertes.fr/hal-03168039

Zobrazit plný text záznamu

Maximum-entropy word alignment and posterior-based phrase extraction for machine translation

Autor: Nadi Tomeh, Alexandre Allauzen, François Yvon

Publikováno v: Machine Translation. 28:19-56

One of the fundamental assumptions in statistical machine translation (SMT) is that the correspondence between a sentence and its translation can be explained in terms of an alignment between their words. Such alignment information is typically not o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4ee75d487e356ea4f05b1cc148f15a93
https://doi.org/10.1007/s10590-013-9146-4

Zobrazit plný text záznamu

Weakly-supervised Symptom Recognition for Rare Diseases in Biomedical Text

Autor: Marie-Christine Jaulent, Pierre Holat, Delphine Battistelli, Thierry Charnois, Nadi Tomeh, Jean-Philippe Métivier

Publikováno v: 15th International Symposium on Intelligent Data Analysis
15th International Symposium on Intelligent Data Analysis, Oct 2016, Stockholm, Sweden
HAL
Advances in Intelligent Data Analysis XV
Advances in Intelligent Data Analysis XV, 9897, Springer International Publishing, pp.192-203, 2016, Lecture Notes in Computer Science, ⟨10.1007/978-3-319-46349-0_17⟩
Lecture Notes in Computer Science ISBN: 9783319463483
IDA

International audience; In this paper, we tackle the issue of symptom recognition for rare diseases in biomedical texts. Symptoms typically have more complex and ambiguous structure than other biomedical named entities. Furthermore , existing resourc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::664ca0a584a035a61c4907c1620d6b0c
https://shs.hal.science/halshs-01727071/document

Zobrazit plný text záznamu

Deep Lexical Segmentation and Syntactic Parsing in the Easy-First Dependency Framework

Autor: Joseph Le Roux, Nadi Tomeh, Matthieu Constant

Publikováno v: NAACL
NAACL, 2016, San Diego, United States
HLT-NAACL

We explore the consequences of representing token segmentations as hierarchical structures (trees) for the task of Multiword Expression (MWE) recognition, in isolation or in combination with dependency parsing. We propose a novel representation of to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3538c4b3a615d0a0eff54bddb0dd49bb
https://hal.archives-ouvertes.fr/hal-01494125

Zobrazit plný text záznamu

Sequential pattern mining for text classification

Autor: Pierre Holat, Nadi Tomeh, Thierry Charnois

Publikováno v: TALN 2015
TALN 2015, Jun 2015, Caen, France
HAL

International audience; Sequential pattern mining for text classification Most methods in text classification rely on contiguous sequences of words as features. Indeed, if we want to take non-contiguous (gappy) patterns into account, the number of fe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0ed5f5ae60aa4a0b68a591225123bdae
https://hal.archives-ouvertes.fr/hal-01168500/document

Zobrazit plný text záznamu

Generalized Character-Level Spelling Error Correction

Autor: Nadi Tomeh, Nizar Habash, Alla Rozovskaya, Noura Farra

Publikováno v: ACL (2)

We present a generalized discriminative model for spelling error correction which targets character-level transformations. While operating at the character level, the model makes use of wordlevel and contextual information. In contrast to previous wo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01b9a5445be77a9185ad583f86fa49d8

Zobrazit plný text záznamu

LIPN: Introducing a new Geographical Context Similarity Measure and a Statistical Similarity Measure based on the Bhattacharyya coefficient

Autor: Nadi Tomeh, Davide Buscaldi, Belém Priego Sánchez, Joseph Le Roux, Jorge García Flores

Publikováno v: HAL
SemEval@COLING
SemEval 2014
SemEval 2014, Aug 2014, Dublin, Ireland. pp.400-405

International audience; This paper describes the system used by the LIPN team in the task 10, Multilingual Semantic Textual Similarity, at SemEval 2014, in both the English and Spanish sub-tasks. The system uses a support vector regression model, com

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2653c97ea454c18609bef77fefe1df8
https://hal.science/hal-01068277

Zobrazit plný text záznamu

Ontology-based Technical Text Annotation

Autor: François Lévy, Yue Ma, Nadi Tomeh

Publikováno v: COLING Workshop on Synchronic and Diachronic Approaches to Analyzing Technical Language (SADAATL)
COLING Workshop on Synchronic and Diachronic Approaches to Analyzing Technical Language (SADAATL), Adam Meyers, Yifan He, Ralph Grishman, Aug 2014, Dublin, Ireland. pp.21-30

International audience; Powerful tools could help users explore and maintain domain specific documentations, provided that documents have been semantically annotated. For that, the annotations must be sufficiently specialized and rich, relying on som

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7be3843dd4c57a746f3b0aecc2c89da8
https://doi.org/10.3115/v1/w14-6003

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání