UMR 8135 CNRS - INaLCO

Contrats européens (EU Horizon 2020)

Discourse reporting in African storytelling (01.02.2018-31.01.2023)

PI : Tatiana Nikitina

The project explores the role of discourse reporting in West African storytelling and the grammatical strategies used by storytellers to achieve their goals. It focuses on three phenomena characteristic of the narrative grammar of a number of West African languages: (i) logophoricity, or the use of special markers to signal self-reference by characters other than the current narrator; (ii) the use of quotative markers and (iii) the use of foreign language or modified versions of the native language to represent the speech of certain characters.

En savoir plus...


DReaM – The Dictionary/Grammar Reading Machine: Computational Tools for Accessing the World’s Linguistic Heritage (01.02.2018-31.01.2021)

PI 1 : Harald Hammarström (U Uppsala) / PI 2 : Marian Klamer (U Leiden) / PI 3 : Stéphane Robert (LLACAN)

The diversity of the world's 6,500 languages embodies a wealth of information on human cognition and the history of populations. As languages go extinct, the linguistic heritage of human kind increasingly resides in grammars and dictionaries, which are rapidly accumulating. Accessing this heritage entails that the descriptions are available – which is, however, often a problem.
In this project we aim to enhance access to the world’s linguistic heritage by making an existing collection of more than 9,000 PDF documents no longer protected by to copyright available in a stable archive enriched by added metadata and computational tools developed to search information within the texts.
Moreover, a number of dictionaries will be converted to apps for mobile devices that can be distributed to speakers of minority languages, handing back to these speakers some of their linguistic heritage.
The third aim of the project is to develop information-extraction tools specifically tailored to the task of dealing with language descriptions. Using cutting-edge methods from Machine Learning and Natural Language Processing we intend to build a system that can extract millions of snippets of information and link them in ways such that it is possible to construct individual language profiles from a variety of sources and to output comparative databases for the purpose of typological and historical linguistics.