Papers by Jun Goto
Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent research on emotion recognition in conversations (ERC) does not take self-dependency or inter-speaker dependency into account. |
| Approach: | They propose a relational graph attention network (RGAT) model that takes speaker dependency and sequential information into account by encoding the relational Graph structure. |
| Outcome: | The proposed model outperforms the state-of-the-art on four ERC datasets. |
Label Embedding using Hierarchical Structure of Labels for Twitter Classification (D19-1)
Copied to clipboard
| Challenge: | Twitter is used for disaster monitoring and news material gathering . we propose a method that can consider the hierarchical structure of labels and labels themselves . |
| Approach: | They propose a method that can consider the hierarchical structure of labels and label texts themselves. |
| Outcome: | The proposed method outperforms the methods of the conference participants over the text REtrieval Conference (TREC) 2018 Incident Streams (IS) dataset. |