Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Tracking.
Takyoung KimHoonsang YoonYukyung LeePilsung KangMisuk KimPublished in: CoRR (2022)
Keyphrases
- evaluation metrics
- human machine
- dialogue system
- dialogue management
- natural language
- spoken dialogue systems
- mixed initiative
- precision and recall
- real time
- conversational agent
- particle filter
- object tracking
- kalman filter
- keyword search
- interactive question answering
- practical reasoning
- average precision
- evaluation measures
- visual tracking
- supervised learning
- state space
- machine learning
- data sets