BrainMap

Mrs. Mihaela Cristescu

Dr.

Assistant Professor - UNIVERSITATEA BUCURESTI

Researcher | Teaching staff

Web of Science ResearcherID: T-9173-2019

Curriculum Vitae (13/07/2024)

Expertise & keywords

Learner Corpus of Romanian (LECOR). Collection, Annotation and Applications Call name: P 1 - SP 1.1 - Proiecte de cercetare pentru stimularea tinerelor echipe independente
PN-III-P1-1.1-TE-2019-1066 2020 - 2024

Role in this project:

Coordinating institution: UNIVERSITATEA BUCURESTI

Project partners: UNIVERSITATEA BUCURESTI (RO)

Affiliation:

Project website: https://unibuc.ro/cercetare/promovarea-rezultatelor-cercetarii/proiecte-de-cercetare/proiecte-cu-finantare-nationala/learner-corpus-of-romanian-lecor-collection-annotation-and-applications-pn-iii-p1-1-1-te-2019-1066-funding-agreement-nr-te-30-2020/?lang=en

Abstract:

The main goal of the LECOR project is to build and exploit the first digitalised learner corpus for Romanian, available in open-access format. A learner corpus is an electronic collection of authentic FL (Foreign Language)/SL (Second Language) textual data conforming to explicit design criteria for particular SLA (Second Language Acquisition)/FLT (Foreign Language Teaching) purposes, encoded in a standardised and homogeneous way and documented as to its origin. The main objectives are: 1) to collect a rich raw learner corpus of Romanian, complying with relevant legal regulations and fulfilling current scientific requirements; 2) to automatically annotate with morpho-syntactical and syntactical labels the whole corpus and to manually annotate learners’ errors for 3,500 sentences; 3) to develop an interface that makes LECOR available to anyone and that allows diverse queries; 4) to carry out studies in learner corpus, FLT and SLA fields; 5) to develop our human resources' experience and to increase the international visibility of Romanian research in this specific domain.

LECOR will be scalable and will have many possible end-uses in language teaching and in natural language processing. Learners, teachers and researchers interested in RFL/RSL will benefit from the outputs of the project and from the scientific events organised during the project. LECOR will be a general reference source for information (e.g. the frequency a certain word, phrase or type of error, etc.), it will serve to test research hypotheses and exemplify them, and it will help to provide accurate statistical analysis on interlanguage. LECOR will be explored for analyses of both a quantitative (i.e. statistics) and a qualitative nature (i.e. broad social and psychological context of language learning; connections between variables etc.). LECOR will be used cross-sectionally and longitudinally.

The project team has seven members (2 IT specialist and 5 linguists who also teach RFL).

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects