| Title: |
BERTrade: Using Contextual Embeddings to Parse Old French |
| Authors: |
Grobol, Loïc; Regnault, Mathilde; Ortiz Suarez, Pedro; Sagot, Benoît; Romary, Laurent; Crabbé, Benoît |
| Contributors: |
Modèles, Dynamiques, Corpus (MoDyCo); Université Paris Nanterre (UPN)-Centre National de la Recherche Scientifique (CNRS); Laboratoire d'Informatique Fondamentale d'Orléans (LIFO); Université d'Orléans (UO)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL); Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA); Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094 (Lattice); Université Sorbonne Nouvelle - Paris 3-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Sciences et Lettres (PSL)-Département Littératures et langage - ENS-PSL (LILA); École normale supérieure - Paris (ENS-PSL); Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-École normale supérieure - Paris (ENS-PSL); Université Paris Sciences et Lettres (PSL); Automatic Language Modelling and ANAlysis & Computational Humanities (ALMAnaCH); Centre Inria de Paris; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria); Sorbonne Université (SU); Direction générale déléguée à la science (DGD-S); Inria Siège; Laboratoire de Linguistique Formelle (LLF - UMR7110); Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité); European Language Resources Association; ANR-18-CE38-0003,BASNUM,Numérisation et analyse du Dictionnaire universel de Basnage de Beauval: lexicographie et réseaux scientifiques(2018); ANR-16-CE38-0010,PROFITEROLE,Modélisation de l'évolution de la langue à partir de textes d'ancien français instrumentés(2016) |
| Source: |
Proceedings of the 13th Language Resources and Evaluation Conference ; 13th Language Resources and Evaluation Conference ; https://hal.science/hal-03736840 ; 13th Language Resources and Evaluation Conference, European Language Resources Association, Jun 2022, Marseille, France |
| Publisher Information: |
CCSD |
| Publication Year: |
2022 |
| Collection: |
Université Paris Lumières: HAL |
| Subject Terms: |
Old French; Contextual word embeddings; Dependency Parsing; Part of Speech Tagging; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] |
| Subject Geographic: |
Marseille; France |
| Description: |
International audience ; The successes of contextual word embeddings learned by training large-scale language models, while remarkable, have mostly occurred for languages where significant amounts of raw texts are available and where annotated data in downstream tasks have a relatively regular spelling. Conversely, it is not yet completely clear if these models are also well suited for lesser-resourced and more irregular languages. We study the case of Old French, which is in the interesting position of having relatively limited amount of available raw text, but enough annotated resources to assess the relevance of contextual word embedding models for downstream NLP tasks. In particular, we use POS-tagging and dependency parsing to evaluate the quality of such models in a large array of configurations, including models trained from scratch from small amounts of raw text and models pre-trained on other languages but fine-tuned on Medieval French data. |
| Document Type: |
conference object |
| Language: |
English |
| Relation: |
https://doi.org/10.5281/zenodo.6461220 |
| Availability: |
https://hal.science/hal-03736840; https://hal.science/hal-03736840v1/document; https://hal.science/hal-03736840v1/file/Bertrade_LREC_2022.pdf |
| Rights: |
http://creativecommons.org/licenses/by-nc/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.2CD6949A |
| Database: |
BASE |