Automatic extraction of analytical definitions and hyponymy-hypernymy relations with a pattern-based system
Abstract
This work is part of an ongoing project that is focused on the design of a lexicographic automaton. The main objective of the research is the extraction of analytical definitions and semantic relations of terms with data taken exclusively from internet. We present two of the abilities of the system: the extraction of analytical definitions and hypernyms. The methodology consists of the automatic search of that information with manually-built patterns based on the lexical structure of analytic definitions in natural language.
This method has improved the precision reported in the state of the art. Se have reached a precision of 92.5% for the extraction of analytical definitions and for the hypernymy relations.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
