Speakers
Description
Understanding the semantic value of linguistic utterances is crucial for linguistics, lexicography, automatic text interpretation, and various NLP tasks. To address subtle variations within the semantic level, as is well known, machines retrieve stored data from corpora, lexicons and terminologies, and are equipped with taggers and rule-based systems. We already have tools for the development of new lexical resources. Alongside dictionaries, which are excellent repositories of information, corpus managers allow for the retrieval and statistical measurement of the distributive properties of vocabulary and the encoding of its syntagmatic properties. However, by using these tools, it is not always possible to simultaneously search for semantic, formal, and statistical data related to relational and/or categorial meaning, since most of these lack semantic annotation. To address this gap, we initiated a research project, ESMASES+, in September 2023. The main goal of this project is to create an automatic, sustainable, and multilingual semantic annotator. The tagger is conceived to automatically delineate the ontological meaning of nouns in Spanish, French, Galician, and German and resorts to lexical data of previous projects.
