1 |
Prosodic Morphology: Constraint Interaction and Satisfaction ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Quantification of Mutual Understanding in Task-Based Human-Human Interactions
|
|
Reverdy, Justine. - : Trinity College Dublin. School of Computer Science & Statistics. Discipline of Computer Science, 2021
|
|
BASE
|
|
Show details
|
|
3 |
Avoiding conflict : when speaker coordination does not require conceptual agreement
|
|
|
|
In: ISSN: 2624-8212 ; Frontiers in Artificial Intelligence, Vol. 3, No 523920 (2021) P. 24 (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Speakers Align With Their Partner's Overspecification During Interaction
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A Parallel Approach to Mobile Affixation in Huave
|
|
|
|
In: Proceedings of the Annual Meetings on Phonology; Proceedings of the 2020 Annual Meeting on Phonology ; 2377-3324 (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Junctural Alignment in Kyoto Japanese Compound Nouns
|
|
|
|
In: Proceedings of the Annual Meetings on Phonology; Proceedings of the 2020 Annual Meeting on Phonology ; 2377-3324 (2021)
|
|
BASE
|
|
Show details
|
|
8 |
MEDIAPI-SKEL -A 2D-Skeleton Video Database of French Sign Language With Aligned French Subtitles
|
|
|
|
In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) ; Proceedings of the 12th Language Resources and Evaluation Conference ; 12th Conference on Language Resources and Evaluation (LREC 2020) ; https://hal.archives-ouvertes.fr/hal-02952340 ; 12th Conference on Language Resources and Evaluation (LREC 2020), Jun 2020, Marseille, France. pp.6063-6068 (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Development of interactional competence in Spanish-language service learning ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Comparação de Métodos para Inferência em Linguagem Natural ; Comparison of Methods for Natural Language Inference
|
|
Souza, Rodrigo Aparecido da Silva. - : Biblioteca Digital de Teses e Dissertações da USP, 2020. : Universidade de São Paulo, 2020. : Faculdade de Filosofia, Letras e Ciências Humanas, 2020
|
|
BASE
|
|
Show details
|
|
11 |
Gesture, Prosody and Information Structure Synchronisation in Turkish
|
|
Turk, Olcay. - : Victoria University of Wellington, 2020
|
|
BASE
|
|
Show details
|
|
12 |
HEADLESS RELATIVE CLAUSES IN PESH ; Proposition relative sans noyau en pesh
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-02021454 ; 2019 (2019)
|
|
BASE
|
|
Show details
|
|
13 |
HEADLESS RELATIVE CLAUSES IN PESH ; Proposition relative sans noyau en pesh
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-02021454 ; 2019 (2019)
|
|
BASE
|
|
Show details
|
|
14 |
The CogSIS Project: Examining the Cognitive Effects of Speech Interface Synthesis
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Development of interactional competence in Spanish-language service learning
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Syntax-Prosody Mismatches in Optimality Theory
|
|
|
|
In: Kalivoda, Nicholas. (2018). Syntax-Prosody Mismatches in Optimality Theory. UC Santa Cruz: Linguistics. Retrieved from: http://www.escholarship.org/uc/item/6wb134g5 (2018)
|
|
BASE
|
|
Show details
|
|
17 |
Automatic Evaluation of Alignments without using a Gold-Corpus ; Automatic Evaluation of Alignments without using a Gold-Corpus: Example with French-Japanese Aligned Corpora
|
|
|
|
In: Conference on Language Resources and Evaluation (LREC 2018) ; https://hal.archives-ouvertes.fr/hal-01789350 ; Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), May 2018, Miyazaki, Japan ; http://lrec-conf.org (2018)
|
|
BASE
|
|
Show details
|
|
18 |
Formalization of the semantics of iconic languages: An ontology-based method and four semantic-powered applications
|
|
|
|
In: ISSN: 0950-7051 ; EISSN: 1872-7409 ; Knowledge-Based Systems ; https://hal.archives-ouvertes.fr/hal-01592749 ; Knowledge-Based Systems, Elsevier, 2017, 135, pp.159 - 179. ⟨10.1016/j.knosys.2017.08.011⟩ (2017)
|
|
BASE
|
|
Show details
|
|
19 |
Measuring Synchrony in Task-based Dialogues ; Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH2017)
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Induction de lexiques bilingues à partir de corpus comparables et parallèles
|
|
|
|
Abstract:
Les modèles statistiques tentent de généraliser la connaissance à partir de la fréquence des événements probabilistes présents dans les données. Si plus de données sont disponibles, les événements sont plus souvent observés et les modèles sont plus performants. Les approches du Traitement Automatique de la Langue basées sur ces modèles sont donc dépendantes de la disponibilité et de la quantité des ressources à disposition. Cette dépendance aux données touche en particulier la Traduction Automatique Statistique qui, de surcroît, requiert des ressources de type multilingue. Cette thèse rapporte quatre articles sur deux tâches qui contribuent de près à cette dépendance : l’Alignement de Documents Bilingues (ADB) et l’Induction de Lexiques Bilingues (ILB). La première publication décrit le système soumis à la tâche partagée d’ADB de la conférence WMT16. Développé sur un moteur de recherche, notre système indexe des sites web bilingues et tente d’identifier les pages anglaises-françaises qui sont en relation de traduction. L’alignement est réalisé grâce à la représentation "sac de mots" et un lexique bilingue. L’outil développé nous a permis d’évaluer plus de 1000 configurations et d’en identifier une qui fournit des performances respectables sur la tâche. Les trois autres articles concernent la tâche d’ILB. Le premier revient sur l’approche dite "standard" et propose une exploration en largeur des paramètres dans le contexte du Web Sémantique. Le deuxième article compare l’approche standard avec les plus récentes techniques basées sur les représentations interlingues de mots (embeddings en anglais) issues de réseaux de neurones. La dernière contribution reporte des performances globales améliorées sur la tâche en combinant, par reclassement supervisée, les sorties des deux types d’approches précédemment étudiées. ; Statistical models try to generalize knowledge starting from the frequency of probabilistic events in the data. If more data is available, events are more often observed and models are more e cient. Natural Language Processing approaches based on those models are therefore dependant on the quantity and availability of these resources. Thus, there is a permanent need for generating and updating the learning data. This dependency touches Statistical Machine Translation, which requires multilingual resources. This thesis refers to four articles tackling two tasks that contribute signi - cantly to this dependency: the Bilingual Documents Alignment (BDA) and the Bilingual Lexicons Induction (BLI). The rst publication describes the system submitted for the BDA shared task of the WMT16 conference. Developed on a search engine, our system indexes bilingual web sites and tries to identify the English-French pages linked by translation. The alignment is realized using a "bag of words" representation and a bilingual lexicon. The tool we have developed allowed us to evaluate more than 1,000 con gurations and identify one yielding decent performances on this particular task. The three other articles are concerned with the BLI task. The rst one focuses on the so-called standard approach, and proposes a breadth parameter exploration in the Semantic Web context. The second article compares the standard approach with more recent techniques based on interlingual representation of words, or the so-called embeddings, issued from neural networks. The last contribution reports the enhanced global performances on the task, combining the outputs of the two studied approaches through supervised reclassification.
|
|
Keyword:
alignement; Alignment; Applied Sciences - Artificial Intelligence / Sciences appliqués et technologie - Intelligence artificielle (UMI : 0800); Bilingual lexicons induction; Comparable corpus; corpus comparable; corpus parallèle; embedding; induction lexique bilingue; Parallel corpus; reclassement supervisé; représentation de mots; Supervised reclassification; Word representation
|
|
URL: http://hdl.handle.net/1866/20488
|
|
BASE
|
|
Hide details
|
|
|
|