@inproceedings{guenoune-lafourcade-2024-symbolic,
    title = "Symbolic Learning of Rules for Semantic Relation Types Identification in {F}rench Genitive Postnominal Prepositional Phrases",
    author = "Guenoune, Hani  and
      Lafourcade, Mathieu",
    editor = "Zock, Michael  and
      Chersoni, Emmanuele  and
      Hsu, Yu-Yin  and
      de Deyne, Simon",
    booktitle = "Proceedings of the Workshop on Cognitive Aspects of the Lexicon @ LREC-COLING 2024",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.cogalex-1.4/",
    pages = "32--41",
    abstract = "We are interested in the semantic relations conveyed by polylexical entities in the postnominal prepositional noun phrases form {\textquotedblleft}A de B{\textquotedblright} (A of B). After identifying a relevant set of semantic relations types, we proceed, using generative AI, to build a collection of phrases, for each semantic relation type identified. We propose an algorithm for creating rules that allow the selection of the relation between A and B in noun phrases of each type. These rules correspond to selecting from a knowledge base the appropriate neighborhood of a given term. For the phrase {\textquotedblleft}d{\'e}sert d`Alg{\'e}rie{\textquotedblright} carrying the location relation, the term {\textquotedblleft}d{\'e}sert{\textquotedblright} is identified as a geographical location, and {\textquotedblleft}Alg{\'e}rie{\textquotedblright} as a country. These constraints are used to automatically learn a set of rules for selecting the location relation for this type of example. Rules are not exclusive as there may be instances that fall under multiple relations. In the phrase {\textquotedblleft}portrait de sa m{\`e}re - the portrait of his/her mother{\textquotedblright}, all of depiction, possession, and producer types are a possible match."
}