Research map / Large language models / Language, safety and interpretability
A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context
Takuma Udagawa, Akiko Aizawa
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 dialogue embeddings to context-only prediction with an MLP | Target selection model · Target selection, Full testset | accuracy: 27.90 $\pm$ 0.6 -> 40.27 $\pm$ 1.3 | Improved |
| Add dialogue embeddings to context-only prediction with a Relation Network | Target selection model · Target selection, Full testset | accuracy: 31.94 $\pm$ 0.9 -> 43.09 $\pm$ 0.8 | Improved |
| Replace MLP context embedding with a Relation Network | Context-only target selection model · Target selection, Full testset | accuracy: 27.90 $\pm$ 0.6 -> 31.94 $\pm$ 0.9 | No clear effect |
| Replace MLP context embedding with a Relation Network | Context + Dialogue target selection model · Target selection, Full testset | accuracy: 40.27 $\pm$ 1.3 -> 43.09 $\pm$ 0.8 | No clear effect |
| Add dialogue embeddings to context-only prediction with an MLP | Target selection model · Target selection, Uncorrelated testset | accuracy: 28.74 -> 40.89 | Improved |
| Add dialogue embeddings to context-only prediction with a Relation Network | Target selection model · Target selection, Uncorrelated testset | accuracy: 30.22 -> 44.00 | Improved |
| Replace MLP context embedding with a Relation Network | Context-only target selection model · Target selection, Uncorrelated testset | accuracy: 28.74 -> 30.22 | No clear effect |
| Replace MLP context embedding with a Relation Network | Context + Dialogue target selection model · Target selection, Uncorrelated testset | accuracy: 40.89 -> 44.00 | No clear effect |
| Add dialogue embeddings to context-only prediction with an MLP | Target selection model · Target selection, Success Only testset | accuracy: 29.59 -> 43.82 | Improved |
| Add dialogue embeddings to context-only prediction with a Relation Network | Target selection model · Target selection, Success Only testset | accuracy: 32.40 -> 49.44 | Improved |
Closest papers by meaning
- An Annotated Corpus of Reference Resolution for Interpreting Common Grounding (AAAI 2020 · similarity 0.93)
- F-LMM: Grounding Frozen Large Multimodal Models (CVPR 2025 · similarity 0.86)
- ChatterBox: Multimodal Referring and Grounding with Chain-of-Questions (AAAI 2025 · similarity 0.86)
- Improving Open-Domain Dialogue Response Generation with Multi-Source Multilingual Commonsense Knowledge (AAAI 2024 · similarity 0.85)
- CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models (AAAI 2024 · similarity 0.85)
- SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words (NeurIPS 2024 · similarity 0.85)
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.
