14 基于ERNIE和BiLSTM的中文名词隐喻识别

高永兵;马宁;

• 1:内蒙古科技大学信息工程学院

•  

摘要(Abstract)：

隐喻普遍存在于自然语言中,精确的识别隐喻可以促进自然语言处理具体任务中语义的理解.为了提高中文名词隐喻识别效果,提出一种基于知识增强的语义表示(ERNIE)和双向长短期记忆网络(BiLSTM)的分类模型ERNIE_BiLSTM.该模型使用ERNIE进行编码,获取上下文相关的语义表示;并利用双向LSTM再次训练词向量,捕获文本长距离的语义关系.实验结果表明,ERNIE_BiLSTM模型在中文名词隐喻识别数据集上表现良好,准确率达到90.34%.

关键词(KeyWords)： 隐喻识别;名词性隐喻;ERNIE模型;BiLSTM模型

基金项目(Foundation): 内蒙古自治区自然科学基金资助项目(2015MS0621)

作者(Author): 高永兵;马宁;

Email:

DOI: 10.16559/j.cnki.2095-2295.2021.03.014

参考文献(References)：

• [1]Lakoff G,Johnson M.Conceptual metaphor in everyday language[J].The Journal of Philosophy,1980,77(8):453．

• [2]Sun Y,Wang S H,Li K,et al.ERNIE:enhanced representation through knowledge integration[EB/OL].(2019-04-19)[2019-12-23].https://ar Xiv.org/abs/1904.09223v1．

• [3]Fass D.Met*:A method for discriminating metonymy and metaphor by computer[J].Computational Linguistics,1991,17(1):49．

• [4]Mohler M,Bracewell D,Tomlinson M,et al.Semantic signatures for example-based linguistic metaphor detection[C]//Proceedings of the First Workshop on metaphor in NLP.Atlanta,Georgia,USA:Association for Computational Linguistics,2013:27．

• [5]Heintz I,Gabbard R,Srivastava M,et al.Automatic extraction of linguistic metaphors with lda topic modeling[C]//:Proceedings of the First Workshop on Metaphor in NLP.Atlanta,Georgia,USA:Association for Computational Linguistics,2013:58．

• [6]Rai S,Chakraverty S,Tayal D K.Supervised metaphor detection using conditional random fields[C]//Proceedings of the Fourth Workshop on Metaphor in NLP.San Diego,California,USA:Association for Computational Linguistics,2016:18．

• [7]Do Dinh E L,Gurevych I.Token-level metaphor detection using neural networks[C]//Proceedings of the 4th Workshop on Metaphor in NLP,San Diego,California,USA:2016:28．

• [8]Rei M,Bulat L,Kiela D,et al.Grasping the finer point:A supervised similarity network for rmetaphor detection[C]//Proceeding of the 2017 conference on empirical methods in NLP.Copenhageh,Denmark:Assocqiation for Computational Linguistics,2017,1536．

• [9]Bizzoni Y,Ghanimifard M.Bigrams and Bi LSTMs two neural networks for sequential metaphor detection[C]//Proceedings of the Workshop on Figurative Language Processing,Louisiana,USA:Association for Computational Linguistics,2018:91．

• [10]Gao G,Choi E,Choi Y,et al.Neural metaphor detection in context[C]//Proceedings of the 2018 conference on empirical methods in natural,Brussels,Belgium:Association for Computational Linguistics,2018:607．

• [11]Wu C H,Wu F Z.Chen Y B,et al.Neural metaphor detecting with CNN-LSTM model.[C]//Proceedings of the workshop on figurative language processing,Louisiana,USA:Association for Computational Linguistics,2018:110．

• [12]Leong C W,Klebanov B B,Hamill C,et al.Areport on the 2020 vua and toefl metaphor detection shared task[C]//Proceedings of the Second Workshop on Figurative Language Processing.Online:Association for Computational Linguistics,2020:18．

• [13]贾玉祥，俞士汶．基于词典的名词性隐喻识别[J]．中文信息学报，2011,25(2):99．

• [14]白振凯，黄孝喜，王荣波，等．基于主题模型的汉语动词隐喻识别[J]．计算机技术与发展，2016(11):67．

• [15]黄孝喜，李晗雨，王荣波，等．基于卷积神经网络与SVM分类器的隐喻识别[J]．数据分析与知识发现，2018,2(10):77．

• [16]王晓梅．汉语句子隐喻的识别和理解关键技术研究[D]．厦门:厦门大学，2019．

• [17]张冬瑜，崔紫娟，李映夏，等．基于Transformer和BERT的名词隐喻识别[J]．数据分析与知识发现，2020,4(4):100．

• [18]Devlin J,Chang M W,Lee K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics:Human language technologies,USA:Association for Computational Linguistics,2019．

• [19]Graves A.Supervised Sequence Labelling[M].Berlin,Germany:Springer,2012.