Research map / Graph learning / Knowledge and temporal graphs
Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding
Bowen Xing, Ivor Wai-Hung Tsang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add label embeddings (prediction-level interactions) (ablation) | DARER · Mastodon DSC | F1: 56.76 -> 59.59 | Improved |
| add constraint loss (ablation) | DARER · Mastodon DSC | F1: 56.22 -> 59.59 | Improved |
| add SAT-RSGT (ablation) | DARER · Mastodon DSC | F1: 57.37 -> 59.59 | Improved |
| add DTR-RSGT (ablation) | DARER · Mastodon DSC | F1: 56.69 -> 59.59 | Improved |
| add TS-LSTMs (ablation) | DARER · Mastodon DSC | F1: 56.30 -> 59.59 | Improved |
| add temporal relations in SATG (ablation) | DARER · Mastodon DSC | F1: 58.23 -> 59.59 | Improved |
| add temporal relations in DRTG (ablation) | DARER · Mastodon DSC | F1: 57.22 -> 59.59 | Improved |
| replace RGCN with ReTeFormer in both graphs (ablation) | DARER · Mastodon DSC | F1: 59.59 -> 62.38 | Improved |
| replace RGCN with ReTeFormer in both graphs (ablation) | DARER · DailyDialog DSC | F1: 53.42 -> 54.34 | Improved |
| stack DARER on BERT encoder | BERT + Linear · Mastodon DSC | F1: 60.60 -> 66.42 | Improved |
| stack Co-GAT on BERT encoder | BERT + Linear · Mastodon DSC | F1: 60.60 -> 61.56 | No clear effect |
| increase reasoning step T from 0 to 1 | DARER · Mastodon | F1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Co-GAT — Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification (AAAI 2021) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GraphMemDialog: Optimizing End-to-End Task-Oriented Dialog Systems Using Graph Memory Networks (AAAI 2022 · similarity 0.89)
- Iterative Context-Aware Graph Inference for Visual Dialog (CVPR 2020 · similarity 0.89)
- Context-Aware Graph Inference With Knowledge Distillation for Visual Dialog (TPAMI 2021 · similarity 0.89)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.86)
- TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling (AAAI 2024 · similarity 0.85)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
