Módulo D

Módulo D: Tratamiento de la ambigüedad en el significado (Resp. M. Palomar)

Various lines of research in the state of the art of processing ambiguity in meaning are relevant to the project. These include related work in three main areas: anaphora and coreference resolution, the processing of word sense ambiguity, and the processing of non-literal language.

Task D.1: Coreference resolution (Resp. M. Palomar)

One important process in the conversion of documents into a form facilitating reading comprehension is coreference resolution, in which links between pronouns and noun phrases referring to the same concept are automatically identified.

Task D.2: Word sense disambiguation (Resp. A. Suárez)

One prevalent source of ambiguity in language is word sense ambiguity, when a single word may have any one of several meanings depending on the context in which it is used.

Task D.3: Processing of difficult words (Resp. P. Martínez-Barco)

The language used in public sector documents tends to be that of a sophisticated and technical nature. These documents usually contain archaisms, highly technical language, acronyms or aphorisms. The objective addressed by this task, via constructing or adapting a complex word processing tool, will be the detection and evaluation of the degree of complexity of these terms and their substitution by other equivalent words that are more easily understood.

 

Resultados de este módulo: 

  • State of the art coreference resolution.
  • State of the art word sense desambiguation.
  • State of the art for processing non-literal language.
  • Tool for Coreference resolution.
  • Tool for WSD.
  • Tool for processing of difficult words.