1 |
Détermination et quantification
|
|
|
|
In: Grande grammaire du français ; https://hal.archives-ouvertes.fr/hal-03277356 ; Grande grammaire du français, 2021 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Les constructions comparatives, superlatives et consécutives
|
|
|
|
In: La grande grammaire du français ; https://hal.archives-ouvertes.fr/hal-03361511 ; Anne Abeillé; Danièle Godard. La grande grammaire du français, 2, Actes Sud; Imprimerie nationale, pp.1641-1648, 2021, 978-2-330-14239-1 (2021)
|
|
BASE
|
|
Show details
|
|
3 |
The Acquisition of Noun and Verb Categories by Bootstrapping From a Few Known Words: A Computational Model
|
|
|
|
In: Front Psychol (2021)
|
|
Abstract:
While many studies have shown that toddlers are able to detect syntactic regularities in speech, the learning mechanism allowing them to do this is still largely unclear. In this article, we use computational modeling to assess the plausibility of a context-based learning mechanism for the acquisition of nouns and verbs. We hypothesize that infants can assign basic semantic features, such as “is-an-object” and/or “is-an-action,” to the very first words they learn, then use these words, the semantic seed, to ground proto-categories of nouns and verbs. The contexts in which these words occur, would then be exploited to bootstrap the noun and verb categories: unknown words are attributed to the class that has been observed most frequently in the corresponding context. To test our hypothesis, we designed a series of computational experiments which used French corpora of child-directed speech and different sizes of semantic seed. We partitioned these corpora in training and test sets: the model extracted the two-word contexts of the seed from the training sets, then used them to predict the syntactic category of content words from the test sets. This very simple algorithm demonstrated to be highly efficient in a categorization task: even the smallest semantic seed (only 8 nouns and 1 verb known) yields a very high precision (~90% of new nouns; ~80% of new verbs). Recall, in contrast, was low for small seeds, and increased with the seed size. Interestingly, we observed that the contexts used most often by the model featured function words, which is in line with what we know about infants' language development. Crucially, for the learning method we evaluated here, all initialization hypotheses are plausible and fit the developmental literature (semantic seed and ability to analyse contexts). While this experiment cannot prove that this learning mechanism is indeed used by infants, it demonstrates the feasibility of a realistic learning hypothesis, by using an algorithm that relies on very little computational and memory resources. Altogether, this supports the idea that a probabilistic, context-based mechanism can be very efficient for the acquisition of syntactic categories in infants.
|
|
Keyword:
Psychology
|
|
URL: https://doi.org/10.3389/fpsyg.2021.661479 http://www.ncbi.nlm.nih.gov/pubmed/34489784 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8416756/
|
|
BASE
|
|
Hide details
|
|
4 |
The Acquisition of Noun and Verb Categories by Bootstrapping From a Few Known Words: A Computational Model
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Missing Antecedents Found
|
|
|
|
In: Proceedings of the Linguistic Society of America ; https://halshs.archives-ouvertes.fr/halshs-03100870 ; Proceedings of the Linguistic Society of America, 2020, 5 (1), pp.822. ⟨10.3765/plsa.v5i1.4795⟩ (2020)
|
|
BASE
|
|
Show details
|
|
6 |
VerNom : une base de paires morphologiques acquise sur très gros corpus
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles ; https://hal.archives-ouvertes.fr/hal-02784780 ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles, 2020, Nancy, France. pp.305-313 (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Missing antecedents found
|
|
|
|
In: Proceedings of the Linguistic Society of America; Vol 5, No 1 (2020): Proceedings of the Linguistic Society of America; 822–834 ; 2473-8689 (2020)
|
|
BASE
|
|
Show details
|
|
8 |
Neural coreference resolution : a head-based approach ; Résolution des coréférences neuronale : une approche basée sur les têtes
|
|
|
|
In: Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) - PFIA 2019 - Volume II : Articles courts ; https://hal.archives-ouvertes.fr/hal-02567783 ; Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) - PFIA 2019 - Volume II : Articles courts, Jul 2019, Toulouse, France. pp.409-416 (2019)
|
|
BASE
|
|
Show details
|
|
9 |
Language Models applied to French Winograd Schemas ; Modèles de langue appliqués aux schémas Winograd français
|
|
|
|
In: Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) - PFIA 2019 - Volume II : Articles courts ; Conférence sur le Traitement Automatique des Langues Naturelles (TALN) - PFIA 2019 ; https://hal.archives-ouvertes.fr/hal-02567776 ; Conférence sur le Traitement Automatique des Langues Naturelles (TALN) - PFIA 2019, Jul 2019, Toulouse, France. pp.343-350 (2019)
|
|
BASE
|
|
Show details
|
|
10 |
A Cost Metric for Pronoun Resolution: Uncertainty Increases Processing Cost
|
|
|
|
In: Rational Approaches in Language Science ; https://hal.archives-ouvertes.fr/hal-03273385 ; Rational Approaches in Language Science, Oct 2019, Saarbrücken, Germany (2019)
|
|
BASE
|
|
Show details
|
|
13 |
The Time Course of Pronoun Resolution in Natural Text Reading
|
|
|
|
In: Linguistic Evidence ; https://halshs.archives-ouvertes.fr/halshs-01957375 ; Linguistic Evidence, Feb 2018, Tübingen, Germany (2018)
|
|
BASE
|
|
Show details
|
|
14 |
A Gold Anaphora Annotation Layer on an Eye Movement Corpus
|
|
|
|
In: the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) ; https://halshs.archives-ouvertes.fr/halshs-01957366 ; the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018, pp.3518-3522 (2018)
|
|
BASE
|
|
Show details
|
|
15 |
A Computational Model of Human Preferences for Pronoun Resolution
|
|
|
|
In: Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics ; https://halshs.archives-ouvertes.fr/halshs-01955078 ; Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017 (2017)
|
|
BASE
|
|
Show details
|
|
16 |
Schémas Winograd en français: une étude statistique et comportementale
|
|
|
|
In: Actes de TALN 2017 ; TALN 2017 ; https://hal.archives-ouvertes.fr/hal-01628342 ; TALN 2017, Jun 2017, Orléans, France (2017)
|
|
BASE
|
|
Show details
|
|
17 |
Predicting Processing Cost of Anaphora Resolution
|
|
|
|
In: Jahrestagung der Deutschen Gesellschaft für Sprachwissenschaft (DGfS) ; https://halshs.archives-ouvertes.fr/halshs-01955104 ; Jahrestagung der Deutschen Gesellschaft für Sprachwissenschaft (DGfS), Mar 2017, Saarbrücken, Germany (2017)
|
|
BASE
|
|
Show details
|
|
18 |
A Google-Proof Collection of French Winograd Schemas
|
|
|
|
In: Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), co-located with EACL 2017 ; https://halshs.archives-ouvertes.fr/halshs-01955086 ; Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), co-located with EACL 2017, 2017, pp.24-29 (2017)
|
|
BASE
|
|
Show details
|
|
19 |
Le même ou un autre : l'expression de l'identité et de la différence en discours
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-01425407 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
20 |
Some specificities of the n-word plus in French
|
|
|
|
In: GLOW ; https://halshs.archives-ouvertes.fr/halshs-01678666 ; GLOW, Dec 2017, Bucarest, Romania (2017)
|
|
BASE
|
|
Show details
|
|
|
|