|
|
 |
|
Lundi 18 Décembre
| Heure: |
12:30 - 14:00 |
| Lieu: |
Salle B107, bâtiment B, Université de Villetaneuse |
| Résumé: |
Semantic similarity on transcriptional regulation literature |
| Description: |
Oscar Lithgow Experimentally generated biological information needs to be organized and structured in order to become meaningful knowledge. However, the rate at which new information is being published makes manual curation increasingly unable to cope. Therefore, new curation strategies based on natural language processing are promising alternatives.
Particularly, nowadays is improbable to consider all related research and reference every single piece of knowledge contained in the publication. Here is where we believe that computers and specifically, automatic natural language processing can help to inter-connect similar conveyed ideas among a collection of articles through discover ing semantically related sentences within a set of scientific articles and delivering those meaningful relations to the end user.
Given our interest in applying such approaches to the benefit of curation of the biomedical literature, specifically about gene regulation in microbial organisms, we decided to also build a corpus with graded textual similarity evaluated by curators, and designed specifically oriented to our purposes. |
|
|
