Research map / Vision-language and multimodal / Visual question answering
Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use semantic-parsing dialog-to-action model instead of memory-network encoder-decoder | D2A vs HRED+KVmem · CSQA overall | recall: 18.40% -> 64.04% | Helped |
| add dialog memory (entities, predicates, action subsequences) (ablation) | D2A · CSQA overall | recall: 42.18% -> 64.04% | Helped |
| add dialog memory (ablation) | D2A · CSQA Simple Question (Direct) | recall: 94.04% -> 93.67% | No clear effect |
| add entity memory (ablation) | D2A · CSQA Simple Question (Co-referenced) | recall: 37.95% -> 71.31% | Helped |
| add entity memory (ablation) | D2A · CSQA Verification (Boolean) | accuracy: 18.44% -> 45.05% | Helped |
| add predicate memory (ablation) | D2A · CSQA Simple Question (Ellipsis) | recall: 15.35% -> 86.58% | Helped |
| add action subsequence memory (ablation) | D2A · CSQA Logical Reasoning (All) | recall: 38.69% -> 42.49% | Helped |
| add action subsequence memory (ablation) | D2A · CSQA overall | recall: 64.02% -> 64.04% | No clear effect |
| add action subsequence memory (ablation) | D2A · CSQA Verification (Boolean) | accuracy: 50.84% -> 45.05% | Hurt |
| add dialog memory | D2A vs HRED+KVmem · CSQA Clarification | recall: 25.09% -> 19.36% | Hurt |
Closest papers by meaning
- From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs (ICLR 2025 · similarity 0.88)
- From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue (AAAI 2024 · similarity 0.88)
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025 · similarity 0.87)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (NeurIPS 2026 · similarity 0.87)
- TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling (AAAI 2024 · similarity 0.87)
- PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents (ICML 2026 · similarity 0.87)
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.