Quantum-Inspired Interactive Networks for Conversational Sentiment Analysis

Conversational sentiment analysis is an emerging, yet challenging Artificial Intelligence (AI) subtask. It aims to discover the affective state of each participant in a conversation. There exists a wealth of interaction information that affects the sentiment of speakers. However, the existing sentiment analysis approaches are insufficient in dealing with this task due to ignoring the interactions and dependency relationships between utterances. In this paper, we aim to address this issue by modeling intrautterance and inter-utterance interaction dynamics. We propose an approach called quantum-inspired interactive networks (QIN), which leverages the mathematical formalism of quantum theory (QT) and the long short term memory (LSTM) network, to learn such interaction dynamics. Specifically, a density matrix based convolutional neural network (DM-CNN) is proposed to capture the interactions within each utterance (i.e., the correlations between words), and a strong-weak influence model inspired by quantum measurement theory is developed to learn the interactions between adjacent utterances (i.e., how one speaker influences another). Extensive experiments are conducted on the MELD and IEMOCAP datasets. The experimental results demonstrate the effectiveness of the QIN model.

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

[2]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[3]  Xiang Li,et al.  Unsupervised Sentiment Analysis of Twitter Posts Using Density Matrix Representation , 2018, ECIR.

[4]  Lee Sael,et al.  Procedia Computer Science , 2015 .

[5]  E. Silerova,et al.  Knowledge and information systems , 2018 .

[6]  Prema Nedungadi,et al.  Hybrid Approach for Emotion Classification of Audio Conversation Based on Text and Speech Mining , 2015 .

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

[8]  Birgitta Ojamaa,et al.  Sentiment analysis on conversational texts , 2015, NODALIDA.

[9]  Rada Mihalcea,et al.  MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations , 2018, ACL.

[10]  Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval , 2018, ICTIR.

[11]  PROCEssIng magazInE.  IEEE Signal Processing Magazine , 2004 .

[12]  Dawei Song,et al.  Modeling Relevance Judgement Inspired by Quantum Weak Measurement , 2018, ECIR.

[13]  A. Gleason.  Measures on the Closed Subspaces of a Hilbert Space , 1957 .

[14]  Santanu Kumar Rath,et al.  Document-level sentiment classification using hybrid machine learning approach , 2017, Knowledge and Information Systems.

[15]  Peng Zhang,et al.  A quantum-inspired multimodal sentiment analysis framework , 2018, Theor. Comput. Sci..

[16]  John von Neumann,et al.  Mathematical Foundations of Quantum Mechanics: New Edition , 2018 .

[17]  Erik Cambria,et al.  Context-Dependent Sentiment Analysis in User-Generated Videos , 2017, ACL.

[18]  Li Zhao,et al.  Attention-based LSTM for Aspect-level Sentiment Classification , 2016, EMNLP.

[19]  Yoshua Bengio,et al.  Modeling term dependencies with quantum language models for IR , 2013, SIGIR.

[20]  Massimo Melucci,et al.  Quantum Language Model-based Query Expansion , 2018, ICTIR.

[21]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.