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

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 903–908 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings Zhuosheng Zhang1,2, Jiangtong Li3, Hai Zhao1,2,∗, Bingjie Tang4 1Department of Computer Science and Engineering, Shanghai Jiao Tong University 2Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China 3College of Zhiyuan, Shanghai Jiao Tong University, China 4School of Computer, Huazhong University of Science and Technology, China {zhangzs, keep moving-lee}@sjtu.edu.cn, zhaohai@cs.sjtu.edu.cn, alexistang@foxmail.com 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 con- cepts or entities, given the search space of a pre-defined vocabulary. We introduce a neu- ral 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 re- current unit and recurrent convolutional neural network. We also explore different embedding methods, including word embedding and sense embedding for better performance. 1 Introduction Hypernym-hyponym relationship is an is-a se- mantic relation between terms as shown in Ta- ble 1. Various natural language processing (NLP) tasks, especially those semantically intensive ones aiming for inference and reasoning with gen- eralization capability, such as question answer- ing (Harabagiu and Hickl, 2006; Yahya et al., 2013) and textual entailment (Dagan et al., 2013; Roller and Erk, 2016), can benefit from identify- ing semantic relations between words beyond syn- onymy. The hypernym discovery task (Camacho- Collados et al., 2018) aims to discover the most appropriate hypernym(s) for input concepts or entities from a pre-defined corpus. A relevant well-known scenario is hypernym detection, ∗ Corresponding author. This paper was partially sup- ported by National Key Research and Development Program of China (No. 2017YFB0304100), National Natural Science Foundation of China (No. 61672343 and No. 61733011), Key Project of National Society Science Foundation of China (No. 15-ZDA041), The Art and Science Interdisciplinary Funds of Shanghai Jiao Tong University (No. 14JCRZ04). which is a binary task to decide whether a hypernymic relationship holds between a pair of words or not. A hypernym detection system should be capable of learning taxonomy and lex- ical semantics, including pattern-based methods (Boella and Caro, 2013; Espinosa-Anke et al., 2016b) and graph-based approaches (Fountain and Lapata, 2012; Velardi et al., 2013; Kang et al., 2016). However, our concerned task, hypernym discovery, is rather more challenging since it requires the systems to explore the semantic connection with all the exhausted candidates in the latent space and rank a candidate set instead of a binary classification in previous work. The other challenge is representation for terms, including words and phrases, where the phrase embedding could not be obtained by word embeddings directly. A simple method is to average the inner word embeddings to form the phrase embedding. However, …

Content truncated to 500 words