Accenting and Information Status Julia Hirschberg CS 4706 01 14 19 1 Information Status Topic comment theme rheme The orangutan we wanted to buy escaped from the pet store Focus of attention I only bought candy for that orangutan Given new I only bought candy for that orangutan I would never buy an ape drugs All commonly signaled in human speech by intonation 01 14 19 2 Today Acent and Given New Motivation in speech technology Models of Given New Experiments on Given New and pitch accent Possible models of intonation wrt given new entities How to identify given new information automatically How to produce given new information appropriately Why is this important 01 14 19 3 A Simple Definition Given Recoverable from some form of context or what a Speaker believes to be in a Hearer s consciousness New Not recoverable from context or what a Speaker believes is not in a Hearer s consciousness 01 14 19 4 Role in Speech Technologies TTS Natural production Given information is often deaccented New information is usually accented but ASR Improved recognition Given information may already have been recognized earlier New information may be important cue to topic shift Summarization Improved precision Given information less likely to be included in a summary new information more likely 01 14 19 5 Spoken Dialogue Systems Grounding Critical for system to convey what is given and what is new to facilitate Hearer comprehension 01 14 19 6 Prince 81 A More Complex Model Speaker S and Hearer H in a discourse construct a discourse model Includes discourse entities attributes and links between entities Discourse entities individuals classes exemplars substances concepts NPs Entities when first introduced are new Brand new H must create a new entity My dog bit a rhinoceros this morning 01 14 19 7 Unused H already knows of this entity The sun came out this morning Evoked entities are old or given already in the discourse Explicitly evoked in text or speech The rhinoceros was wearing suspenders Situationally evoked Watch out for the snake Inferables are also old or given I bought a new car The gear shift is a bit tricky 01 14 19 8 Prince 92 A Still More Complex Model Hearer centric information status Given what S believes H has in his her consciousness New what S believes H does not have in his her consciousness But discourse entities may also be given and new wrt the current discourse Discourse old already evoked in the discourse Discourse new not evoked 01 14 19 9 The stars are very bright tonight Hearergiven Discourse new When I see stars this bright I think of my vacations in the mountains Hearer given Discourse given My friend Buddy and I would sneak out late at night Hearer new Discourse new I said My friend BUDDY Hearer new Discourse given 01 14 19 10 Given New and Pitch Accent New information is often accented and given information is often deaccented Halliday 67 Brown 83 Terken 84 But there are many exceptions a simple TTS rule accent new and deaccent given will make 25 30 errors How can we reduce these errors to produce human like intonation 01 14 19 11 Brown 83 Accent Status and Subclasses of Given New Speech elicitation in laboratory 12 Scottish English undergrads A describes a diagram for B to draw which B cannot see Draw a black triangle Draw a circle in the middle Draw a blue triangle next to the black one with a line from the top angle to the bottom Analysis based on Prince 81 categories with modifications 01 14 19 12 Brand new given inferable middle angle given contextually evoked the page given textually evoked divided into current topic vs earlier mention Accent status of all entity referring NPs Results Brand new information accented 87 Note new entity old expression issue Given contextually evoked information deaccented 98 Given textually evoked deaccented current topic 100 earlier 96 Given inferable information accented 79 01 14 19 13 Boston Directions Corpus Hirschberg Nakatani 96 Experimental Design 12 speakers 4 used Spontaneous and read versions of 9 directiongiving tasks monologues Corpus 50m read 67m spon Labeling Prosodic ToBI intonational labeling Given new Prince 92 grammatical function p o s 01 14 19 14 Hearer and Discourse Given New Labeling first enter HG DN the Harvard Square T stop and buy HI DN a token then proceed to get on HI DN the inbound um Red Line uh subway and take HG DG the subway from HG DG Harvard Square to HG DN Central Square and then to HG DN Kendall Square then get off HG DG the T 01 14 19 17 Does Given New Status Predict Deaccenting NPa HG Deaccented 37 1 1009 Total HI HN DG DN 53 9 26 2 43 3 38 8 406 130 596 950 HG Hearer Given HI Hearer Inferable HN Hearer New DG Discourse Given DN Discourse New 01 14 19 18 And Bard 99 Givenness deaccenting and intelligibility Speech elicited in laboratory Glasgow Scottish English Map Task Each has a slightly different map A traces a route described by B Analysis Compare repeated mentions of same items i e given items wrt accent status Within dialogue Across dialogue Findings 01 14 19 19 Deaccenting rare in repeated mentions within 15 and across 6 dialogues But repeated mentions were less intelligible Caveats Were they really identifying deaccenting the absence of a pitch accent Were mentions within speaker or across speaker Some more questions to ask 01 14 19 20 What else is going on Given new and grammatical function Hypothesis how discourse entities are evoked in a discourse influences accent status E g How might grammatical function and surface position interact with the accentuation of given items Cases X has not been mentioned in the prior context X has been mentioned with the same grammatical function surface position X has been mentioned but with a different grammatical function surface position 01 14 19 21 Experimental Design Major problem How to elicit spontaneous productions while varying desired phenomena systematically Key simple variations and actions can capitalize upon natural tendency to associate grammatical functions with particular thematic roles for a given set of verbs 01 14 19 22 Rectangle Triangle Cylinder Octagon 01 14 19 Diamond 23 Context 1 Rectangle Triangle Cylinder Octagon 01 14 19 Diamond 24 Context 2 Rectangle Triangle Cylinder Diamond Octagon 01 14 19 25 Context 3 Rectangle Triangle Cylinder Octagon Diamond 01 14 19 26 Target A Triangle Rectangle Cylinder Octagon 01 14 19 Diamond 27 Target B Rectangle Triangle Cylinder Octagon 01 14 19 Diamond 28 Experimental Conditions 10 native