SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings

This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a pre-defined vocabulary. We introduce a neural network architecture for the concerned task and empirically study various neural network models to build the representations in latent space for words and phrases. The evaluated models include convolutional neural network, long-short term memory network, gated recurrent unit and recurrent convolutional neural network. We also explore different embedding methods, including word embedding and sense embedding for better performance.

PDF Abstract SEMEVAL 2018 PDF SEMEVAL 2018 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Hypernym Discovery General SJTU BCMI MAP 5.77 # 6
MRR 10.56 # 6
P@5 5.96 # 6
Hypernym Discovery Medical domain SJTU BCMI MAP 11.69 # 6
MRR 25.95 # 6
P@5 11.69 # 6
Hypernym Discovery Music domain SJTU BCMI MAP 4.71 # 5
MRR 9.15 # 5
P@5 4.91 # 5

Methods


No methods listed for this paper. Add relevant methods here