Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-Task Deep Learning for User Intention Understanding in Speech Interaction Systems
Yishuang Ning, Jia Jia, Zhiyong Wu, Runnan Li, Yongsheng An, Yanfeng Wang, Helen Meng
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 Bayesian network on top of LSTM outputs (ablation) | LSTM · Sogou intention prominence | F1: 0.797 -> 0.866 | Improved |
| use LSTM instead of CRF | intention prominence model · Sogou focus detection | F1: 0.739 -> 0.759 | Improved |
| use LSTM instead of CRF | emphasis detection · Sogou emphasis detection | F1: 0.066 -> 0.575 | Improved |
| add emphasis by speech to focus by text (ablation) | LSTM+BN · Sogou intention prominence | F1: +2.8% | Improved |
| add location information to focus and emphasis (ablation) | LSTM+BN · Sogou intention prominence | F1: +3% | Improved |
| multi-task learning for focus and emphasis detection (ablation) | LSTM · Sogou focus and emphasis detection | F1 | Improved |
| add more unlabeled data for SAE pretraining (ablation) | LSTM+BN · Sogou intention prominence | F1 | Improved |
| feed intention prominence rather than original utterances into search | Sogou search · 32 utterances | top-10 coverage ratio: 65.25% -> 72.25% | Improved |
| use LSTM+BN instead of BN | intention prominence model · CPU training time | CPU time (s): 6.8 -> 1.7520 x10^4 | Hurt |
Closest papers by meaning
- Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport (AAAI 2024 · similarity 0.85)
- MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations (ICLR 2024 · similarity 0.85)
- AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head (AAAI 2024 · similarity 0.85)
- Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction (AAAI 2024 · similarity 0.85)
- Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding (AAAI 2026 · similarity 0.84)
- Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment (AAAI 2024 · 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.
