BomJi at SemEval-2018 Task 10: Combining Vector-, Pattern-and Graph-based Information to Identify Discriminative Attributes

Enrico Santus (1) , Chris Biemann (2) , Emmanuele Chersoni (3, 4)

1 MIT - Massachusetts Institute of Technology
2 UHH - Universität Hamburg
3 AMU - Aix Marseille Université
4 LPL - Laboratoire Parole et Langage

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.

Domaines: Informatique [cs]; Informatique et langage [cs.CL]

Enrico Santus, Chris Biemann, Emmanuele Chersoni. BomJi at SemEval-2018 Task 10: Combining Vector-, Pattern-and Graph-based Information to Identify Discriminative Attributes. International Workshop on Semantic Evaluation (SemEval), Jun 2018, New Orleans, United States. ⟨hal-01758923⟩