DOC PREVIEW
Columbia COMS W4706 - Turn-taking and Disfluencies

This preview shows page 1-2-3-4-5 out of 15 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Turn-taking and DisfluenciesTodayTurn-takingSlide 4Could this be useful when we build SDS?Auditory Cues to Turn-TakingDisfluencies and Self-RepairsHindle ’83: Finding the Edit SignalWhat does it mean to be the sameBear et al ’92: Detecting and Correcting Self-RepairsBut…is there an edit signal?Slide 12RIM Model of Self-Repairs (Nakatani & Hirschberg ’94)Does it identify self-repairs reliably?Next Week01/14/19 1Turn-taking and DisfluenciesJulia HirschbergCS 470601/14/19 2Today•Turn-taking behaviors–Conversational Analysis–Importance in real systems•Disfluencies–How to model? Detect?–Role in human-human interaction–Importance in real systems?01/14/19 3Turn-taking•Expected patterns of behavior–Deviation is significant–How do we find the patterns?•Ordinary conversation•Telephone talk•Meetings•Email?–Who looks for these?01/14/19 4•Terminology–Adjacency pairs–Preference–Pre-sequence–Repair•Examples:–Telephone openings, closings–Broadcasts01/14/19 5Could this be useful when we build SDS?•What do we expect to hear?•What should we produce?01/14/19 6Auditory 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 turn-taking and backchannels based on prosodic and syntactic features…,” Language and Speech 41, 1999. (Sarah)01/14/19 7Disfluencies 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 recognizers01/14/19 8Hindle ’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’ versionI was * I am really annoyed –If X1 * X2 are similar linguistic elements separated by an edit signal, replace X1 w/X201/14/19 9What does it mean to be the same•Same surface stringWell if they’d * if they’d…•Same categoryI was just that * the kind of guy…•Same constituentI think that you get * it’s more strict in Catholic schools•Restarts are completely different…I just think * Do you want something to eat?01/14/19 10Bear et al ’92: Detecting and Correcting Self-Repairs•Use multiple knowledge sources but not edit signal–Lexical pattern matching–Parsing failure + pattern matching + re-parsing–Acoustic information: pause, peak F0, –Cue words: well, no–Fragments01/14/19 11But…is there an edit signal?01/14/19 1201/14/19 13RIM 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 amplitude01/14/19 14Does 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 sig nals?01/14/19 15Next Week•Spoken Dialogue Systems•Andy, David and Vera


View Full Document

Columbia COMS W4706 - Turn-taking and Disfluencies

Download Turn-taking and Disfluencies
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Turn-taking and Disfluencies and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Turn-taking and Disfluencies 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?