Papers by Sanae Yamashita
Optimal Summaries for Enabling a Smooth Handover in Chat-Oriented Dialogue (2022.aacl-srw)
Copied to clipboard
| Challenge: | In dialogue systems, it is difficult to provide fully autonomous dialogue . to ensure a good dialogue experience, human operators sometimes need to intervene . |
| Approach: | They conducted large-scale experiments on chat dialogues to determine which type of summary is most useful for handover . abstractive summary plus one utterance immediately before handover and extractive summary consisting of five utterrances immediately before the handover were found to be the most useful . |
| Outcome: | The best summaries were abstractive summary plus one utterance before handover and extractive summary consisting of five utterrances before hand over. |
Data Collection for Empirically Determining the Necessary Information for Smooth Handover in Dialogue (2022.lrec-1)
Copied to clipboard
| Challenge: | Despite advances in deep learning, dialogue systems struggle to achieve fully autonomous transactions with users. |
| Approach: | They conducted an experiment in which two operators switched periodically while performing chat, consultation, and sales tasks in dialogue. |
| Outcome: | The results show that adjacency pairs are useful for recording conversation history . key-value pairs are also useful when there are underlying tasks, such as consultation and sales . |