In this paper, we propose relational position encodings that provide RGAT with sequential information reflecting the relational graph structure. However, graph-based neural networks do not take sequential information 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). Many recent ERC methods use graph-based neural networks to take the relationships between the utterances of the speakers into account. Publisher = "Association for Computational Linguistics",Ībstract = "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.
#GRAPH ATTENTION NETWORKS MODS#
Cite (Informal): Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations (Ishiwatari et al., EMNLP 2020) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: Data DailyDialog, EmoryNLP, IEMOCAP, = "Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations",īooktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", Association for Computational Linguistics. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7360–7370, Online. Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations. Anthology ID: 2020.emnlp-main.597 Volume: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) Month: November Year: 2020 Address: Online Venue: EMNLP SIG: Publisher: Association for Computational Linguistics Note: Pages: 7360–7370 Language: URL: DOI: 10.18653/v1/2020.emnlp-main.597 Bibkey: ishiwatari-etal-2020-relation Cite (ACL): Taichi Ishiwatari, Yuki Yasuda, Taro Miyazaki, and Jun Goto. In addition, our approach empirically outperforms the state-of-the-art on all of the benchmark datasets. Experiments on four ERC datasets show that our model is beneficial to recognizing emotions expressed in conversations. Accordingly, our RGAT model can capture both the speaker dependency and the sequential information. 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.
0 kommentar(er)
