Turn-taking and Disfluencies Julia Hirschberg CS 4706 7/15/2016 1 Today • Turn-taking behaviors – Conversational Analysis – Importance in real systems • Disfluencies – How to model? Detect? – Role in human-human interaction – Importance in real systems? 7/15/2016 2 Turn-taking • Expected patterns of behavior – Deviation is significant – How do we find the patterns? • • • • Ordinary conversation Telephone talk Meetings Email? – Who looks for these? 7/15/2016 3 • Terminology – Adjacency pairs – Preference – Pre-sequence – Repair • Examples: – Telephone openings, closings – Broadcasts 7/15/2016 4 Could this be useful when we build SDS? • What do we expect to hear? • What should we produce? 7/15/2016 5 Auditory Cues to Turn-Taking • M. Schegloff “Reflections on studying prosody in talk-in-interaction, ” Language and Speech 41, 1999. (Michael Mu.) • H. Koiso et al ‘99 “An analysis of turntaking and backchannels based on prosodic and syntactic features…,” Language and Speech 41, 1999. (Sarah) 7/15/2016 6 Disfluencies and Self-Repairs • Are these just ‘noise’? – For people • S. Brennan & M. Williams, “The Feeling of Another’s Knowing,” J Memory and Language 34, 1995. (Judd) • S. Brennan & Schober, “How listeners compensate for disfluencies in spontaneous speech,” J Memory and Language 44, 2001. (Aron) – For parsers – For speech recognizers 7/15/2016 7 Hindle ’83: Finding the Edit Signal • If we have it, can we ‘repair’ the self-repair automatically? – Builds a correcting parser, Fidditch, for spontaneous speech – Given a string with an edit signal marked, produces a ‘repaired’ version I was * I am really annoyed – If X1 * X2 are similar linguistic elements separated by an edit signal, replace X1 w/X2 7/15/2016 8 What does it mean to be the same • Same surface string Well if they’d * if they’d… • Same category I was just that * the kind of guy… • Same constituent I think that you get * it’s more strict in Catholic schools • Restarts are completely different… I just think * Do you want something to eat? 7/15/2016 9 Bear et al ’92: Detecting and Correcting Self-Repairs • Use multiple knowledge sources but not edit signal – Lexical pattern matching – Parsing failure + pattern matching + reparsing – Acoustic information: pause, peak F0, – Cue words: well, no – Fragments 7/15/2016 10 But…is there an edit signal? 7/15/2016 11 7/15/2016 12 RIM Model of Self-Repairs (Nakatani & Hirschberg ’94) • ATIS corpus – 6414 turns with 346 (5.4%) repairs, 122 speakers – Hand-labeled for repairs and prosodic features • Findings: – Reparanda: 73% end in fragments, 30% in glottalization, co-articulatory gestures – DI: pausal duration differs significantly from fluent boundaries,small increase in f0 and 7/15/2016 amplitude 13 Does it identify self-repairs reliably? • CART prediction: 86% precision, 91% recall – Duration of interval, presence of fragment, pause filler, p.o.s., lexical matching across DI • Are there edit signals? 7/15/2016 14 Next Week • Spoken Dialogue Systems • Andy, David and Vera reporting 7/15/2016 15