潜在Dirichlet分配
计算机科学
人工智能
学期
水准点(测量)
词(群论)
序列标记
自然语言处理
主题模型
代表(政治)
序列(生物学)
意义(存在)
任务(项目管理)
情绪分析
词义消歧
机器学习
语言学
WordNet公司
大地测量学
政治
心理学
政治学
心理治疗师
地理
法学
管理
遗传学
经济
生物
哲学
作者
Yang Huang,Yuncheng Jiang,A S M Touhidul Hasan,Qigui Jiang,Chao Li
标识
DOI:10.1145/3194206.3194240
摘要
The Long Short Term Memory (LSTM) network is very effective for capturing sequence information which can help to analyze sentiments. However, it fails to capture the meaning of polysemous word under different contexts. In this paper, we propose topic information-based bidirectional LSTM (BiLSTM) model for sentiment classification. BiLSTM model learns topic information to obtain the sensitive representation of the polysemous word under given circumstance. The topic information is generated through a topic modeling via Latent Dirichlet Allocation (LDA). The topic information-based BiLSTM network allows the model to capture the meaning of the polysemous word and long sequence information automatically. The experimental results on real-world datasets demonstrate that the proposed method outperforms the task of benchmark sentiment classification on SemEval 2013 and IMDB.
科研通智能强力驱动
Strongly Powered by AbleSci AI