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

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

26 May 2018SEMEVAL 2018 6arXiv:1805.10465archive 2025-07-28

Zhuosheng Zhang, Jiangtong Li, Hai Zhao, Bingjie Tang

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.

PaperPDFConference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Hypernym Discovery

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hypernym Discovery General SJTU BCMI MAP 5.77 #6 of 8 Archive leaderboard report
Hypernym Discovery General SJTU BCMI MRR 10.56 #6 of 8 Archive leaderboard report
Hypernym Discovery General SJTU BCMI P@5 5.96 #6 of 8 Archive leaderboard report
Hypernym Discovery Medical domain SJTU BCMI MAP 11.69 #6 of 8 Archive leaderboard report
Hypernym Discovery Medical domain SJTU BCMI MRR 25.95 #6 of 8 Archive leaderboard report
Hypernym Discovery Medical domain SJTU BCMI P@5 11.69 #6 of 8 Archive leaderboard report
Hypernym Discovery Music domain SJTU BCMI MAP 4.71 #5 of 7 Archive leaderboard report
Hypernym Discovery Music domain SJTU BCMI MRR 9.15 #5 of 7 Archive leaderboard report
Hypernym Discovery Music domain SJTU BCMI P@5 4.91 #5 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections