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

Abstract

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-ofthe-art on all of the benchmark datasets.

Directed Acyclic Graph Network for Conversational Emotion Recognition

“…We compared our model with the following baselines in our experiments: Recurrence-based methods: DialogueRNN (Majumder et al, 2019), DialogRNN-RoBERTa , and COSMIC without external knowledge 3 . Graph-based methods: DialogurGCN (Ghosal et al, 2019), KET (Zhong et al, 2019), DialogXL (Shen et al, 2020) and RGAT (Ishiwatari et al, 2020). Feature extractor: RoBERTa (Liu et al, 2019).…”

“…We utilize only the textual modality of the above datasets for the experiments. For evaluation metrics, we follow Ishiwatari et al (2020) and Shen et al (2020) and choose micro-averaged F1 excluding the majority class (neutral) for DailyDialog and weighted-average F1 for the other datasets.…”

“…Numerous efforts have been devoted to the modeling of conversation context. Basically, they can be divided into two categories: graph-based methods (Zhang et al, 2019a;Ghosal et al, 2019;Zhong et al, 2019;Ishiwatari et al, 2020;Shen et al, 2020) and recurrence-based methods (Hazarika et al, 2018a;Hazarika et al, 2018b;. For the graphbased methods, they concurrently gather information of the surrounding utterances within a certain window, while neglecting the distant utterances and the sequential information.…”

COSY: COunterfactual SYntax for Cross-Lingual Understanding

“…To achieve this learning objective in deep models, we design syntax-aware networks that incorporate the encodings of dependency relations and POS tags into the encoding of semantics. However, we find that empirically the conventional attention-based incorporation of syntax, e.g., relational graph attention networks (Ishiwatari et al, 2020), has little effect on improving the model. One possible reason is that the learning process may be dominated by the pre-trained language models due to their strength in semantic representation learning, which leads to an overfitted model.…”

NHK_STRL at WNUT-2020 Task 2: GATs with Syntactic Dependencies as Edges and CTC-based Loss for Text Classification

“…Lu et al (2020) use 5 https://competitions.codalab.org/ competitions/25845#results a network on a vocabulary graph, which is based on word co-occurrence information, and Huang and Carley (2019) and Xu and Yang (2019) use syntactic features as a graph. Also, there are several methods that use positional encoding into GATs (Ingraham et al, 2019;Ishiwatari et al, 2020). Our method uses GATs to consider syntactic features with positional features in combination, which is distinguishable from conventional methods.…”