Papers with automatic evaluation of dialogue response generation models
Speaker Sensitive Response Evaluation Model (2020.acl-main)
Copied to clipboard
| Challenge: | Existing evaluation models rate appropriate responses if they deviate from the ground truth . a limited range of appropriate responses for a given context is needed to evaluate dialogue . |
| Approach: | They propose an automatic evaluation model that considers similarity of generated responses with conversational context and learns parameters from an unlabeled conversation corpus. |
| Outcome: | The proposed model outperforms existing evaluation metrics in terms of correlation with human annotation scores. |