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.
Previous item | Next item |
Back to news summary page |
Featured News
- Vacancy for Research Fellow in Natural Language Processing
- Keynote speaker at APBC2021
- BioNLP 2021 - First call for papers
- Outstanding paper designation for NaCTeM paper at Coling 2020
- New article in BMJ Open examining change over time of women’s health in clinical studies
- CfP: Special issue on Semantic Resources and Text Mining
- New article describing neural nested event extraction model
- New article describing syntactically-informed word representations