The goal of the CWI shared task of 2018 is to predict which words challenge non-native speakers based on the annotations collected from both native and non-native speakers. A labeled training set is provided where words in context were annotated regarding their complexity. Training and test data belong to the same language. The task consists in labeling the target test words in context as complex (1) or simple (0).
Publication
Seid Muhie Yimam, Chris Biemann, Shervin Malmasi, Gustavo Paetzold, Lucia Specia, Sanja Štajner, Anaïs Tack, Marcos Zampieri (2018) A Report on the Complex Word Identification Shared Task 2018. Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 66-78 New Orleans, Louisiana, June 5, 2018.
Competition
Language
Spanish
NLP topic
Abstract task
Dataset
Year
2018
Publication link
Task results
| System | MacroF1 Sort ascending |
|---|---|
| TMU | 0.7699 |
| NLP-CIC | 0.7672 |
| ITEC | 0.7637 |
| NLP-CIC | 0.7468 |
| CoastalCPH | 0.7458 |
