What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts
Finch, James D., Finch, Sarah E., Choi, Jinho D.
–arXiv.org Artificial Intelligence
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to automated analysis of conversation logs that learns the relationship between user-system interactions and overall dialogue quality. Unlike prior work on utterance-level quality prediction, our approach learns the impact of each interaction from the overall user rating without utterance-level annotation, allowing resultant model conclusions to be derived on the basis of empirical evidence and at low cost. Our model identifies interactions that have a strong correlation with the overall dialogue quality in a chatbot setting. Experiments show that the automated analysis from our model agrees with expert judgments, making this work the first to show that such weakly-supervised learning of utterance-level quality prediction is highly achievable.
arXiv.org Artificial Intelligence
Oct-31-2021
- Country:
- North America > United States
- Georgia > Fulton County > Atlanta (0.05)
- Asia > China
- North America > United States
- Genre:
- Research Report (1.00)
- Technology: