# SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings Source: [SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:57:57.772Z Authors: Zhuosheng Zhang, Jiangtong Li, Hai Zhao, Bingjie Tang Published: 2018-05-26T11:55:59.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Hypernym discovery on medical Gold standard domain-specific (test)](): Hypernym discovery; medical Gold standard domain-specific (test); MRR: 24.52. - [Hypernym discovery on music Gold standard domain-specific (test)](): Hypernym discovery; music Gold standard domain-specific (test); MRR: 27.15. - [Hypernym Discovery on SemEval Task 9 English general-purpose subtask 2018](): Hypernym discovery; SemEval Task 9 English general-purpose subtask 2018 (gold standard evaluation); MRR: 0.1622. ## Original sources and implementation [Original paper]() [PDF]()