300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes
This paper describes 300-sparsians{'}s participation in SemEval-2018 Task 9: Hypernym Discovery, with a system based on sparse coding and a formal concept hierarchy obtained from word embeddings. Our system took first place in subtasks (1B) Italian (all and entities), (1C) Spanish entities, and (2B) music entities.
PDF AbstractDatasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Hypernym Discovery | General | 300-sparsans | MAP | 8.95 | # 4 | |
MRR | 19.44 | # 4 | ||||
P@5 | 8.63 | # 4 | ||||
Hypernym Discovery | Medical domain | 300-sparsans | MAP | 20.75 | # 3 | |
MRR | 40.60 | # 4 | ||||
P@5 | 21.43 | # 3 | ||||
Hypernym Discovery | Music domain | 300-sparsans | MAP | 29.54 | # 3 | |
MRR | 46.43 | # 3 | ||||
P@5 | 28.86 | # 3 |