Directed Acyclic Graph Network for Conversational Emotion Recognition

The modeling of conversational context plays a vital role in emotion recognition from conversation (ERC). In this paper, we put forward a novel idea of encoding the utterances with a directed acyclic graph (DAG) to better model the intrinsic structure within a conversation, and design a directed acyclic neural network, namely DAG-ERC1, to implement this idea. In an attempt to combine the strengths of conventional graph-based neural models and recurrence-based neural models, DAG-ERC provides a more intuitive way to model the information flow between long-distance conversation background and nearby context. Extensive experiments are conducted on four ERC benchmarks with state-of-the-art models employed as baselines for comparison. The empirical results demonstrate the superiority of this new model and confirm the motivation of the directed acyclic graph architecture for ERC.

[1]  Kedhar Nath Narahari,et al.  SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text , 2019, *SEMEVAL.

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

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

[4]  Taro Miyazaki,et al.  Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations , 2020, EMNLP.

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

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

[7]  Achille Fokoue,et al.  Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling , 2019, ArXiv.

[8]  Premkumar T. Devanbu,et al.  A Survey of Machine Learning for Big Code and Naturalness , 2017, ACM Comput. Surv..

[9]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

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

[11]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[12]  Xiaojun Quan,et al.  DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition , 2020, AAAI.

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

[14]  Björn W. Schuller,et al.  AVEC 2012: the continuous audio/visual emotion challenge , 2012, ICMI '12.

[15]  Rada Mihalcea,et al.  MIME: MIMicking Emotions for Empathetic Response Generation , 2020, EMNLP.

[16]  Rada Mihalcea,et al.  COSMIC: COmmonSense knowledge for eMotion Identification in Conversations , 2020, FINDINGS.

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

[18]  Guodong Zhou,et al.  Modeling both Context- and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations , 2019, IJCAI.

[19]  Eduard Hovy,et al.  Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances , 2019, IEEE Access.

[20]  Gang Wang,et al.  DAG-Recurrent Neural Networks for Scene Labeling , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Michael R. Lyu,et al.  HiGRU: Hierarchical Gated Recurrent Units for Utterance-Level Emotion Recognition , 2019, NAACL.

[22]  Lun-Wei Ku,et al.  EmotionLines: An Emotion Corpus of Multi-Party Conversations , 2018, LREC.

[23]  Jie Chen,et al.  Directed Acyclic Graph Neural Networks , 2021, ICLR.

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

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

[26]  Roman Garnett,et al.  D-VAE: A Variational Autoencoder for Directed Acyclic Graphs , 2019, NeurIPS.

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

[28]  Yiming Yang,et al.  XLNet: Generalized Autoregressive Pretraining for Language Understanding , 2019, NeurIPS.

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

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

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