ML models predict next speaker in multi-party dialogues, with content-based deep learning performing best on large corpora while simpler speaker-only models suffice for small topic-focused ones.
Different but Equal: Comparing User Collaboration with Digital Personal Assistants vs. Teams of Expert Agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This work compares user collaboration with conversational personal assistants vs. teams of expert chatbots. Two studies were performed to investigate whether each approach affects accomplishment of tasks and collaboration costs. Participants interacted with two equivalent financial advice chatbot systems, one composed of a single conversational adviser and the other based on a team of four experts chatbots. Results indicated that users had different forms of experiences but were equally able to achieve their goals. Contrary to the expected, there were evidences that in the teamwork situation that users were more able to predict agent behavior better and did not have an overhead to maintain common ground, indicating similar collaboration costs. The results point towards the feasibility of either of the two approaches for user collaboration with conversational agents.
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Multi-Party Turn-Taking Models from Dialogue Logs
ML models predict next speaker in multi-party dialogues, with content-based deep learning performing best on large corpora while simpler speaker-only models suffice for small topic-focused ones.