Home Aims & Objectives NaCTeM Services Text Mining Tools Text Mining Infrastructures Text Mining for Biodiversity Resources Terms & Conditions FAQ News & Events News What others are saying about us Press and Journal Mentions NaCTeM Seminars People Projects Publications Community External Collaboration Vacancies Teaching & Tutorials Feedback How to find us

NaCTeM announced as the winners of NLP challenge on scholarly discourse and summarisation

2019-08-05

A team of researchers from NaCTeM group were recently announced as the winners of an NLP challenge. Dr. Chrysoula Zerva, Dr. Minh-Quoc Nghiem, Dr. Nhung Nguyen, and Prof. Sophia Ananiadou, achieved first place in the 5th CL-SciSumm Shared Task 2019 challenge.

CL-SciSumm aims to contribute to the development of methods focussing on scholarly discourse and summarisation, focussing on the identification of cited passages across scientific publications, and the subsequent summarisation of scientific articles based on their cited extracts. It consists of three sub-tasks: The identification of cited text spans within a paper (T1A), the classification of these text spans based on a set of discourse facets (T1B) and finally the generation of a scientific summary for the paper (T2) . The NaCTeM team competed against 9 other teams and ranked first in 2 out of 3 tasks, namely Task 1A and Task 2, and third in Task 1B.

The winning system was presented at the BIRNDL workshop, which was co-located with SIGIR 2019 in Paris. The system is described in the workshop proceedings publication, and an extended version will be submitted to the Scientometrics journal.