Attitude Detection for One-Round Conversation: Jointly Extracting Target-Polarity Pairs

We tackle Attitude Detection, which we define as the task of extracting the replier's attitude, i.e., a target-polarity pair, from a given one-round conversation. While previous studies considered Target Extraction and Polarity Classification separately, we regard them as subtasks of Attitude Detection. Our experimental results show that treating the two subtasks independently is not the optimal solution for Attitude Detection, as achieving high performance in each subtask is not sufficient for obtaining correct target-polarity pairs. Our jointly trained model AD-NET substantially outperforms the separately trained models by alleviating the target-polarity mismatch problem. Moreover, we proposed a method utilising the attitude detection model to improve retrieval-based chatbots by re-ranking the response candidates with attitude features. Human evaluation indicates that with attitude detection integrated, the new responses to the sampled queries from are statistically significantly more consistent, coherent, engaging and informative than the original ones obtained from a commercial chatbot.

[1]  Shuohang Wang,et al.  Machine Comprehension Using Match-LSTM and Answer Pointer , 2016, ICLR.

[2]  Claire Cardie,et al.  Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization , 2014, ACL.

[3]  Yue Zhang,et al.  Gated Neural Networks for Targeted Sentiment Analysis , 2016, AAAI.

[4]  Xiaoyan Zhu,et al.  Generating Informative Responses with Controlled Sentence Function , 2018, ACL.

[5]  Daling Wang,et al.  Attention based hierarchical LSTM network for context-aware microblog sentiment classification , 2018, World Wide Web.

[6]  Erik Cambria,et al.  Aspect extraction for opinion mining with a deep convolutional neural network , 2016, Knowl. Based Syst..

[7]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[8]  Ting Liu,et al.  Aspect Level Sentiment Classification with Deep Memory Network , 2016, EMNLP.

[9]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[10]  Philip S. Yu,et al.  A holistic lexicon-based approach to opinion mining , 2008, WSDM '08.

[11]  Nikos Pelekis,et al.  DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis , 2017, *SEMEVAL.

[12]  Xiaoyan Zhu,et al.  Assigning personality/identity to a chatting machine for coherent conversation generation , 2017, ArXiv.

[13]  Cheng Li,et al.  Deep Memory Networks for Attitude Identification , 2017, WSDM.

[14]  Wanxiang Che,et al.  LTP: A Chinese Language Technology Platform , 2010, COLING.

[15]  Xiaoyan Zhu,et al.  Assigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation , 2018, IJCAI.

[16]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[17]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[18]  Xiaokui Xiao,et al.  Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis , 2016, EMNLP.

[19]  Suresh Manandhar,et al.  SemEval-2014 Task 4: Aspect Based Sentiment Analysis , 2014, *SEMEVAL.

[20]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[21]  Iryna Gurevych,et al.  Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields , 2010, EMNLP.

[22]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[23]  Lidong Bing,et al.  Recurrent Attention Network on Memory for Aspect Sentiment Analysis , 2017, EMNLP.

[24]  Mike Wells,et al.  Structured Models for Fine-to-Coarse Sentiment Analysis , 2007, ACL.

[25]  Xiaocheng Feng,et al.  Effective LSTMs for Target-Dependent Sentiment Classification , 2015, COLING.

[26]  Saif Mohammad,et al.  NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews , 2014, *SEMEVAL.

[27]  Phil Blunsom,et al.  Reasoning about Entailment with Neural Attention , 2015, ICLR.

[28]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[29]  Tetsuya Sakai,et al.  Overview of the NTCIR-12 Short Text Conversation Task , 2016, NTCIR.

[30]  Zhiqiang Toh,et al.  DLIREC: Aspect Term Extraction and Term Polarity Classification System , 2014, *SEMEVAL.

[31]  Haris Papageorgiou,et al.  SemEval-2016 Task 5: Aspect Based Sentiment Analysis , 2016, *SEMEVAL.

[32]  Ming Zhou,et al.  Gated Self-Matching Networks for Reading Comprehension and Question Answering , 2017, ACL.

[33]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[34]  Roberto Basili,et al.  A context-based model for Sentiment Analysis in Twitter , 2014, COLING.

[35]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.