Research map / Vision-language and multimodal / Human and embodied modeling
Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes
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 SuTaT-LSTM instead of Copycat | unsupervised abstractive dialogue summarization · MultiWOZ Customer | ROUGE-1: 26.86 -> 28.51 | Helped |
| Use SuTaT-LSTM instead of Copycat | unsupervised abstractive dialogue summarization · MultiWOZ Agent | ROUGE-1: 26.92 -> 28.71 | Helped |
| Use SuTaT-LSTM instead of Copycat | unsupervised abstractive dialogue summarization · Taskmaster Customer | ROUGE-1: 24.86 -> 26.61 | Helped |
| Use SuTaT-LSTM instead of Copycat | unsupervised abstractive dialogue summarization · Taskmaster Agent | ROUGE-1: 25.05 -> 26.67 | Helped |
| Add variational latent spaces (ablation) | SuTaT-LSTM · MultiWOZ and Taskmaster, customer and agent summaries | ROUGE-1: 24.78 -> 28.51; 25.11 -> 28.71; 23.05 -> 26.61; 23.41 -> 26.67 | Helped |
| Add sentence-level self-attention (ablation) | SuTaT-LSTM · MultiWOZ and Taskmaster, customer and agent summaries | ROUGE-1: 26.69 -> 28.51; 27.00 -> 28.71; 25.08 -> 26.61; 25.25 -> 26.67 | Helped |
| Add partial copy mechanism (ablation) | SuTaT-LSTM · MultiWOZ and Taskmaster, customer and agent summaries | ROUGE-1: 27.65 -> 28.51; 27.67 -> 28.71; 25.28 -> 26.61; 25.15 -> 26.67 | Helped |
| Use Transformer encoders and decoders instead of LSTM encoders and decoders | SuTaT · MultiWOZ and Taskmaster dialogue summarization | ROUGE-1: 28.51 -> 26.82; 28.71 -> 27.11; 26.61 -> 25.20; 26.67 -> 25.19 | Hurt |
Closest papers by meaning
- DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization (AAAI 2022 · similarity 0.88)
- Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders (AAAI 2021 · similarity 0.87)
- Joint Parsing and Generation for Abstractive Summarization (AAAI 2020 · similarity 0.85)
- From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue (AAAI 2024 · similarity 0.83)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.83)
- Unsupervised Extractive Summarization with Learnable Length Control Strategies (AAAI 2024 · similarity 0.83)
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.