Papers by Clamença Poujade
Desvolopar una metodologia d’enquista per descriure la fonologia de l’occitan
Publications de l'Association Internationale d'Etudes Occitanes, 2022
Linguatec Tolosa Treebank
<strong>Linguatec Tolosa Treebank for Occitan</strong> Linguatec Tolosa Treebank is t... more <strong>Linguatec Tolosa Treebank for Occitan</strong> Linguatec Tolosa Treebank is the first dependency treebank for Occitan, developed as part of the EFA 227/16 LINGUATEC Project, financed by the POCTEFA Interreg European funds. The current version of the treebank contains 13K tokens annotated for PoS tags, lemmas and syntactic dependencies. Linguistic annotation follows Universal Dependencies guidelines (https://universaldependencies.org/#language-u). A detailed corpus description is provided in the description file. A subset of texts was doubly annotated and these annotations were adjudicated in order to provide the final annotation. These texts are therefore the most suited to be used as test files in NLP experiments. The corpus files are stored in the ConLL-U format. Each sentence is preceded by a sentence ID and the original, non-tokenized text of the sentence. The annotation is provided in a column-based format defined as follows: 1. ID: Word index, integer starting at 1 for each new sentence; may be a range for multiword tokens.<br> 2. FORM: Word form or punctuation symbol.<br> 3. LEMMA: Lemma or stem of word form.<br> 4. UPOS: Universal part-of-speech tag.<br> 5. XPOS: Language-specific part-of-speech tag; underscore if not available.<br> 6. FEATS: List of morphological features from the universal feature inventory or from a defined language-specific extension; underscore if not available.<br> 7. HEAD: Head of the current word, which is either a value of ID or zero (0).<br> 8. DEPREL: Universal dependency relation to the HEAD<br> 9. DEPS: Enhanced dependency graph in the form of a list of head-deprel pairs.<br> 10. MISC: Any other annotation. The texts are distributed under the Creative Commons BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en).
This paper outlines the ongoing effort of creating the first treebank for Occitan, a low-ressourc... more This paper outlines the ongoing effort of creating the first treebank for Occitan, a low-ressourced regional language spoken mainly in the south of France. We briefly present the global context of the project and report on its current status. We adopt the Universal Dependencies framework for this project. Our methodology is based on two main principles. Firstly, in order to guarantee the annotation quality, we use the agile annotation approach. Secondly, we rely on pre-processing using existing tools (taggers and parsers) to facilitate the work of human annotators, mainly through a delexicalized cross-lingual parsing approach. We present the results available at this point (annotation guidelines and a sub-corpus annotated with PoS tags and lemmas) and give the timeline for the rest of the work.
Occitan is a Romance language spoken mainly in the south of France. It has no official status in ... more Occitan is a Romance language spoken mainly in the south of France. It has no official status in the country, it is not standardized and displays important diatopic variation resulting in a rich system of dialects. Recently, a first treebank for this language was created. However, this corpus is based exclusively on texts in the Lengadocian dialect. Our paper describes the work aimed at extending the existing corpus with content in three new dialects, namely Gascon, Provençau and Lemosin. We describe both the annotation of initial content in these new varieties of Occitan and experiments allowing us to identify the most efficient method for further enrichment of the corpus. We observe that parsing models trained on Occitan dialects achieve better results than a delexicalized model trained on other Romance languages despite the latter training corpus being much larger (20K vs 900K tokens). The results of the native Occitan models show an important impact of cross-dialectal lexical va...
Langue française, 2021
Vers un corpus de textes d'élèves annoté en relations de discours Towards a corpus of learner tex... more Vers un corpus de textes d'élèves annoté en relations de discours Towards a corpus of learner texts annotated with discourse relations
La phonologie et la morphologie du parler occitan du bassin de l'Hers
Ce memoire se concentre sur l’etude d’un parler occitan, celui du bassin de l’Hers, en Ariege. Ce... more Ce memoire se concentre sur l’etude d’un parler occitan, celui du bassin de l’Hers, en Ariege. Ce parler se trouve sur une aire qui est le passage de plusieurs isoglosses qui separent le languedocien du gascon. L’etude de l’etat de l’art a permis de faire ressortir dix questions de recherches interessantes, d’un point de vue phonologique et morphologique pour le parler en question, decrites dans ce memoire. Parmi ces dix questions, trois seront selectionnees pour une etude plus approfondie. Ces trois questions sont l’alternance de la realisation vocalique pour l’adverbe « pas » et les pronoms « las, la » selon l’accentuation de la syllabe qui precede, les differentes realisations de « s » suivant le contexte phonetique et les realisations des nasales egalement selon le contexte phonetique. Des enquetes ont ete menees aupres de sept locuteurs afin d’etudier ces phenomenes. Environs 5 heures d’enregistrement ont servi pour l’etude des phenomenes. Tous ces enregistrements ont ete codes...
Uploads
Papers by Clamença Poujade