Finding Errors Automatically in Semantically Tagged Dialogues

We describe a novel method for detecting errors in task-based human-computer (HC) dialogues by automatically deriving them from semantic tags. We examined 27 HC dialogues from the DARPA Communicator air travel domain, comparing user inputs to system responses to look for slot value discrepancies, bo...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Aberdeen, John, Doran, Christine, Damianos, Laurie, Bayer, Samuel, Hirschman, Lynette
Format:	Report
Sprache:	eng
Schlagworte:	ALGORITHMS AUTOMATIC COMPUTER COMMUNICATIONS Computer Programming and Software DARPA COMMUNICATOR DETECTION DIALOGUE ERROR DETECTION ERRORS FRAMES HH(HUMAN-HUMAN) HUMAN COMPUTER HUMAN FACTORS ENGINEERING Human Factors Engineering & Man Machine System LABELED SUBSTANCES LABELS MAN COMPUTER INTERFACE PERFORMANCE(HUMAN) RESPONSE SEMANTICS SLOTS TRAVEL
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!