Research map / Label-efficient and robust learning / Self-supervised and contrastive
Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues
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 |
|---|---|---|---|
| Add next session prediction (ablation) | BERT-SL · Ubuntu Dialogue Corpus | R10@1: 0.879 -> 0.884 | Helped |
| Add utterance restoration (ablation) | BERT-SL · Ubuntu Dialogue Corpus | R10@1: 0.881 -> 0.884 | Helped |
| Add incoherence detection (ablation) | BERT-SL · Ubuntu Dialogue Corpus | R10@1: 0.877 -> 0.884 | Helped |
| Add consistency discrimination (ablation) | BERT-SL · Ubuntu Dialogue Corpus | R10@1: 0.880 -> 0.884 | Helped |
| Add next session prediction (ablation) | BERT-SL · E-commerce Dialogue Corpus | R10@1: 0.760 -> 0.776 | Helped |
| Add utterance restoration (ablation) | BERT-SL · E-commerce Dialogue Corpus | R10@1: 0.763 -> 0.776 | Helped |
| Add incoherence detection (ablation) | BERT-SL · E-commerce Dialogue Corpus | R10@1: 0.755 -> 0.776 | Helped |
| Add consistency discrimination (ablation) | BERT-SL · E-commerce Dialogue Corpus | R10@1: 0.742 -> 0.776 | Helped |
| Train with the four dialogue self-supervised tasks | DualLSTM · Ubuntu Dialogue Corpus | R10@1: 0.638 -> 0.724 | Helped |
| Train with the four dialogue self-supervised tasks | ESIM · Ubuntu Dialogue Corpus | R10@1: 0.796 -> 0.822 | Helped |
| Train with the four dialogue self-supervised tasks | DualLSTM · E-commerce Dialogue Corpus | R10@1: 0.365 -> 0.518 | Helped |
| Train with the four dialogue self-supervised tasks | ESIM · E-commerce Dialogue Corpus | R10@1: 0.570 -> 0.623 | Helped |
Closest papers by meaning
- An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems (ICML 2024 · similarity 0.87)
- Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (ICLR 2025 · similarity 0.86)
- From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue (AAAI 2024 · similarity 0.85)
- Response Enhanced Semi-supervised Dialogue Query Generation (AAAI 2024 · similarity 0.84)
- Self-Updatable Large Language Models by Integrating Context into Model Parameters (ICLR 2025 · similarity 0.84)
- F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model (AAAI 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.