Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations

Interest in emotion recognition in conversations (ERC) has been increasing in various fields, because it can be used to analyze user behaviors and detect fake news. Many recent ERC methods use graph-based neural networks to take the relationships between the utterances of the speakers into account. In particular, the state-of-the-art method considers self- and inter-speaker dependencies in conversations by using relational graph attention networks (RGAT). However, graph-based neural networks do not take sequential information into account. In this paper, we propose relational position encodings that provide RGAT with sequential information reflecting the relational graph structure. Accordingly, our RGAT model can capture both the speaker dependency and the sequential information. Experiments on four ERC datasets show that our model is beneficial to recognizing emotions expressed in conversations. In addition, our approach empirically outperforms the state-of-the-art on all of the benchmark datasets.

[1]  Carlos Busso,et al.  IEMOCAP: interactive emotional dyadic motion capture database , 2008, Lang. Resour. Evaluation.

[2]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[3]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[4]  Chunyan Miao,et al.  Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations , 2019, EMNLP.

[5]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[6]  Regina Barzilay,et al.  Generative Models for Graph-Based Protein Design , 2019, DGS@ICLR.

[7]  Xiaoyu Shen,et al.  DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset , 2017, IJCNLP.

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

[9]  Erik Cambria,et al.  Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos , 2018, NAACL.

[10]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[11]  Richard Socher,et al.  Quasi-Recurrent Neural Networks , 2016, ICLR.

[12]  Xuanjing Huang,et al.  Recurrent Neural Network for Text Classification with Multi-Task Learning , 2016, IJCAI.

[13]  Jinho D. Choi,et al.  Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks , 2017, AAAI Workshops.

[14]  Alexander Gelbukh,et al.  DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation , 2019, EMNLP.

[15]  Taesun Whang,et al.  EmotionX-KU: BERT-Max based Contextual Emotion Classifier , 2019, ArXiv.

[16]  Xing Wang,et al.  Self-Attention with Structural Position Representations , 2019, EMNLP.

[17]  I. Hong,et al.  Predicting positive user responses to social media advertising: The roles of emotional appeal, informativeness, and creativity , 2016, Int. J. Inf. Manag..

[18]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[19]  Rosalind W. Picard.  Affective Computing: From Laughter to IEEE , 2010 .

[20]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[21]  Rada Mihalcea,et al.  DialogueRNN: An Attentive RNN for Emotion Detection in Conversations , 2018, AAAI.

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

[23]  Juan Cao,et al.  DEAN: Learning Dual Emotion for Fake News Detection on Social Media , 2019 .

[24]  Ashish Vaswani,et al.  Self-Attention with Relative Position Representations , 2018, NAACL.

[25]  Yue Wang,et al.  EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification , 2019, ArXiv.

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

[27]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[29]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[30]  Rada Mihalcea,et al.  ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection , 2018, EMNLP.

[31]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[32]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.