Raffaella Bernardi, Alberto Testoni
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Generating goal-oriented questions in Visual Dialogue tasks is a challenging and longstanding problem. State-Of-The-Art systems are shown to generate questions that, although grammatically correct, often lack an effective strategy and sound unnatural to humans. Inspired by the cognitive literature on information search and cross-situational word learning, we design Confirm-it, a model based on a beam search re-ranking algorithm that guides an effective goal-oriented strategy by asking questions that confirm the model's conjecture about the referent. We take the GuessWhat?! game as a case-study. We show that dialogues generated by Confirm-it are more natural and effective than beam search decoding without re-ranking.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.05312")
get_code_for_paper("2109.05312")
have("2109.05312")
Connect an agent — have() is free.