Towards Automatic Generation of Related Work Reports

Ahmed Ghassan Tawfiq AbuRa'ed (ahmed (point) aburaed <at> upf (point) edu)

LaSTUS Lab @ TALN research group. Universitat Pompeu Fabra (UPF)

Le 4 juillet 2018 à 11 h 30

Salle 3195, Pavillon André-Aisenstadt


Scientific publications contain most of humanity's knowledge, they represent information as relevant as how to cure diseases and create medicaments. They are permanent records of what has been discovered so far. The amount of the scientific papers documented together with the unprecedented growth rates they hold are causing a scientific information overload, with recent estimates indicating that a new research paper is published every 20 seconds. Moreover, scientists are facing a huge challenge to keep on track whether in their own field, related fields or even new developments of new fields that are appearing due to such exponential growth. One way of having a brief overview of a research field is by reading state of the art reports, which usually contain, in condensed form, key information on a topic draw from different sources. Our main objective is to design a methodology that utilizes a set of automatic tools to extract relevant information from scientific papers to generate related work reports. Such reports can be later used as a related work section in a scientific paper or a review of a related work in a study field which serve as a review for scholars.


Pour recevoir les annonces hebdomadaires par courriel, envoyez un message à l'adresse majordomo@iro.umontreal.ca

Liste des autres séminaires