No public posts in this group. You must login and become a member in order to post messages, and view any private posts.
Machines that speak with us (Spoken Dialogue Systems) rely disproportionately on accurate transcription of the speech signal into readable text. When the system has low confidence in the automatic speech recognition (ASR) of a caller's utterance, a typical dialogue strategy requires the system to repeat its best guess and ask for confirmation. This leads to unnatural interactions and dissatisfied callers. Our novel methodology, wizard ablation, collects simulated human-system dialogues that vary in controlled ways in order to investigate problem-solving strategies people would use if a person's abilities and options were restricted to be more like a machine's. Our testbed application, the CheckItOut dialog system, is modeled on a corpus of telephone transactions between patrons and librarians that we collected at New York City's Andrew Heiskell Braille & Talking Book Library. (Loqui, a Latin phrase meaning "I speak"; because the "I" in the case of an ablated wizard is neither the wizard nor the system, we like the alliterative allusion to Loki (lo-kee), the Norse god of mischief.)
Syndicate content