BomJi at SemEval-2018 Task 10: Combining Vector-, Pattern- and Graph-based Information to Identify Discriminative Attributes
This work addresses a specific natural language processing task for researchers and practitioners, but it is incremental as it combines existing feature types without introducing a fundamentally new approach.
The paper tackled the problem of identifying discriminative attributes in word pairs, such as 'yellow' for banana over watermelon, by developing BomJi, a supervised system that achieved an F1 score of 0.73 and ranked 2nd out of 26 systems in SemEval-2018 Task 10.
This paper describes BomJi, a supervised system for capturing discriminative attributes in word pairs (e.g. yellow as discriminative for banana over watermelon). The system relies on an XGB classifier trained on carefully engineered graph-, pattern- and word embedding based features. It participated in the SemEval- 2018 Task 10 on Capturing Discriminative Attributes, achieving an F1 score of 0:73 and ranking 2nd out of 26 participant systems.