CS 4705 Discourse Structure and Text Coherence What makes a text/dialogue coherent? Incoherent? “Consider, for example, the difference between passages.

Slides:



Advertisements
Similar presentations
Discourse Structure and Discourse Coherence
Advertisements

Atomatic summarization of voic messages using lexical and prosodic features Koumpis and Renals Presented by Daniel Vassilev.
Interlanguage IL LEC. 9.
Punctuation Generation Inspired Linguistic Features For Mandarin Prosodic Boundary Prediction CHEN-YU CHIANG, YIH-RU WANG AND SIN-HORNG CHEN 2012 ICASSP.
C O N T E X T - F R E E LANGUAGES ( use a grammar to describe a language) 1.
“Effect of Genre, Speaker, and Word Class on the Realization of Given and New Information” Julia Agustín Gravano & Julia Hirschberg {agus,
“Downstepped contours in the given/new distinction” Agustín Gravano Spoken Language Processing Group Columbia University, New York On the Role of Prosody.
Automatic Prosodic Event Detection Using Acoustic, Lexical, and Syntactic Evidence Sankaranarayanan Ananthakrishnan, Shrikanth S. Narayanan IEEE 2007 Min-Hsuan.
Pragmatics II: Discourse structure Ling 571 Fei Xia Week 7: 11/10/05.
1 Spoken Dialogue Systems Dialogue and Conversational Agents (Part IV) Chapter 19: Draft of May 18, 2005 Speech and Language Processing: An Introduction.
INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING NLP-AI IIIT-Hyderabad CIIL, Mysore ICON DECEMBER, 2003.
Chapter 20: Natural Language Generation Presented by: Anastasia Gorbunova LING538: Computational Linguistics, Fall 2006 Speech and Language Processing.
Introduction to RST Rhetorical Structure Theory Maite Taboada and Manfred Stede Simon Fraser University / Universität Potsdam Contact:
Presented by Ravi Kiran. Julia Hirschberg Stefan Benus Jason M. Brenier Frank Enos Sarah Friedman Sarah Gilman Cynthia Girand Martin Graciarena Andreas.
Prosodic Cues to Discourse Segment Boundaries in Human-Computer Dialogue SIGDial 2004 Gina-Anne Levow April 30, 2004.
CS 4705 Discourse Structure and Text Coherence. What makes a text/dialogue coherent? Incoherent? “Consider, for example, the difference between passages.
Discourse Structure Grosz and Sidner. Why bother? Leads to an account of discourse meaning Constrains how utterances are related Useful for explaining.
Final Review CS4705 Natural Language Processing. Semantics Meaning Representations –Predicate/argument structure and FOPC Thematic roles and selectional.
Information Status Varieties of Information Status –Contrast John wanted a poodle but Becky preferred a corgi. –Topic/comment The corgi they bought turned.
1 SIMS 256: Applied Natural Language Processing Marti Hearst November 27, 2006.
On the Correlation between Energy and Pitch Accent in Read English Speech Andrew Rosenberg, Julia Hirschberg Columbia University Interspeech /14/06.
On the Correlation between Energy and Pitch Accent in Read English Speech Andrew Rosenberg Weekly Speech Lab Talk 6/27/06.
The ‘cooler climes’ text 1. Your kind invitation to come and enjoy cooler climes is so tempting 2.but I have been waiting to learn the outcome of medical.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 7.
Classification of Discourse Functions of Affirmative Words in Spoken Dialogue Julia Agustín Gravano, Stefan Benus, Julia Hirschberg Shira Mitchell, Ilia.
Test Taking Tips How to help yourself with multiple choice and short answer questions for reading selections A. Caldwell.
14: THE TEACHING OF GRAMMAR  Should grammar be taught?  When? How? Why?  Grammar teaching: Any strategies conducted in order to help learners understand,
 A summary is a brief restatement of the essential thought of a longer composition. It reproduces the theme of the original with as few words as possible.
Natural Language and Dialogue Systems Lab Computational Models of Discourse and Dialogue 2011: Conversation in Social Media.
Discourse Markers Discourse & Dialogue CS November 25, 2006.
AUTOMATIC DETECTION OF REGISTER CHANGES FOR THE ANALYSIS OF DISCOURSE STRUCTURE Laboratoire Parole et Langage, CNRS et Université de Provence Aix-en-Provence,
A brief overview of Speech Recognition and Spoken Language Processing Advanced NLP Guest Lecture August 31 Andrew Rosenberg.
Teaching Productive Skills Which ones are they? Writing… and… Speaking They have similarities and Differences.
LAS LINKS DATA ANALYSIS. Objectives 1.Analyze the 4 sub-tests in order to understand which academic skills are being tested. 2.Use sample tests to practice.
Discourse Analysis Radhika Mamidi. Coherence and cohesion What makes a text coherent? What are the coherent devices? Discourses have to have connectivity.
August Discourse Structure and Anaphoric Accessibility Massimo Poesio and Barbara Di Eugenio with help from Gerard Keohane.
1 Special Electives of Comp.Linguistics: Processing Anaphoric Expressions Eleni Miltsakaki AUTH Fall 2005-Lecture 2.
LATERALIZATION OF PHONOLOGY 2 DAY 23 – OCT 21, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
HYMES (1964) He developed the concept that culture, language and social context are clearly interrelated and strongly rejected the idea of viewing language.
Background: Speakers use prosody to distinguish between the meanings of ambiguous syntactic structures (Snedeker & Trueswell, 2004). Discourse also has.
1 Natural Language Processing Lecture Notes 14 Chapter 19.
Recognizing Discourse Structure: Speech Discourse & Dialogue CMSC October 11, 2006.
Dialog Models September 18, 2003 Thomas Harris.
Discourse & Dialogue CS 359 November 13, 2001
Automatic recognition of discourse relations Lecture 3.
1Computer Sciences Department. Book: INTRODUCTION TO THE THEORY OF COMPUTATION, SECOND EDITION, by: MICHAEL SIPSER Reference 3Computer Sciences Department.
Lexical, Prosodic, and Syntactics Cues for Dialog Acts.
Intention & Cooperation Discourse and Dialogue CS 359 October 18, 2001.
Phone-Level Pronunciation Scoring and Assessment for Interactive Language Learning Speech Communication, 2000 Authors: S. M. Witt, S. J. Young Presenter:
Discourse: Structure and Coherence Kathy McKeown Thanks to Dan Jurafsky, Diane Litman, Andy Kehler, Jim Martin.
Recognizing Discourse Structure: Text Discourse & Dialogue CMSC October 16, 2006.
Acoustic Cues to Emotional Speech Julia Hirschberg (joint work with Jennifer Venditti and Jackson Liscombe) Columbia University 26 June 2003.
Key Stage 2 Portfolio. Llafaredd / Oracy Darllen / Reading Ysgrifennu / Writing Welsh Second Language.
2. The standards of textuality: cohesion Traditional approach to the study of lannguage: sentence as conventional object of study Structuralism (Bloofield,
Discourse: Structure and Coherence Kathy McKeown Thanks to Dan Jurafsky, Diane Litman, Andy Kehler, Jim Martin.
Implicature. I. Definition The term “Implicature” accounts for what a speaker can imply, suggest or mean, as distinct from what the speaker literally.
Introduction to RST (Rhetorical Structure Theory)
Discourse Structure and Text Coherence
Automatic Speech Recognition
Studying Intonation Julia Hirschberg CS /21/2018.
Studying Intonation Julia Hirschberg CS /21/2018.
Structural relations Carnie 2013, chapter 4 Kofi K. Saah.
Recognizing Structure: Sentence, Speaker, andTopic Segmentation
“Downstepped contours in the given/new distinction”
Agustín Gravano & Julia Hirschberg {agus,
Discourse Structure in Generation
CSCI 5832 Natural Language Processing
Recognizing Structure: Dialogue Acts and Segmentation
CS4705 Natural Language Processing
Introduction to Computational Linguistics
Presentation transcript:

CS 4705 Discourse Structure and Text Coherence

What makes a text/dialogue coherent? Incoherent? “Consider, for example, the difference between passages (18.71) and (18.72). Almost certainly not. The reason is that these utterances, when juxtaposed, will not exhibit coherence. Do you have a discourse? Assume that you have collected an arbitrary set of well-formed and independently interpretable utterances, for instance, by randomly selecting one sentence from each of the previous chapters of this book.” vs….

“Assume that you have collected an arbitrary set of well-formed and independently interpretable utterances, for instance, by randomly selecting one sentence from each of the previous chapters of this book. Do you have a discourse? Almost certainly not. The reason is that these utterances, when juxtaposed, will not exhibit coherence. Consider, for example, the difference between passages (18.71) and (18.72). (J&M:695)

What makes a text coherent? Appropriate use of coherence relations between subparts of the discourse -- rhetorical structure Appropriate sequencing of subparts of the discourse -- discourse/topic structure Appropriate use of referring expressions

Rhetorical Structure Theory (Mann, Matthiessen, and Thompson ‘89) One theory of discourse structure, based on identifying relations between parts of the text –How many rhetorical relations are there? –MMT say 23 but… Nucleus/satellite notion encodes asymmetry Some rhetorical relations: –Elaboration (set/member, class/instance/whole/part…) –Contrast: multinuclear –Condition: Sat presents precondition for N –Purpose: Sat presents goal of the activity in N –Sequence: multinuclear

–Result: N results from something presented in Sat –Evidence: Sat provides evidence for something claimed in N A sample definition: –Relation: evidence –Constraints on N: H might not believe N as much as S think s/he should –Constraints on Sat: H already believes or will believe Sat An example: George Bush supports Big Business. He is sure to veto House Bill 1711.

1) Title: Bouquets in a basket – with living flowers 2) There is a gardening revolution going on 3) People are planting flower baskets with living plants 4) Mixing many types in one container for a summer of floral beauty 5) To create your own “Victorian” bouquet of flowers 6) Choose varying shapes, sizes and forms, besides a variety of complementary colors 7) Plants that grow tall should be surrounded by smaller ones and filled with others that tumble over the side of a hanging basket 8) Leaf textures and colors will also be important 9) There is the silver-white foliage of dusty miller, the feathery threads of lotus vine floating down from above, the deep greens, or chartreuse, even the widely varied foliage colors of the coleus.

1) Title: Bouquets in a basket – with living flowers 2) There is a gardening revolution going on 3) People are planting flower baskets with living plants (S:Evidence,N2) 4) Mixing many types in one container for a summer of floral beauty (S:Elaboration,N3) 5) To create your own “Victorian” bouquet of flowers 6) Choose varying shapes, sizes and forms, besides a variety of complementary colors (S:Condition,5?) 7) Plants that grow tall should be surrounded by smaller ones and filled with others that tumble over the side of a hanging basket 8) Leaf textures and colors will also be important 9) There is the silver-white foliage of dusty miller, the feathery threads of lotus vine floating down from above, the deep greens, or chartreuse, even the widely varied foliage colors of the coleus.

Some Problems with RST (cf. Moore & Pollack ‘92)Moore & Pollack ‘92 How many Rhetorical Relations are there? How can we use RST in dialogue as well as monologue? How do we incorporate speaker intentions into RST? RST does not allow for multiple relations holding between parts of a discourse RST does not model overall structure of the discourse

What’s the Rhetorical Structure? System: Hello. How may I help you? User: I would like to find out why I was charged for a call? System: What call would you like to inquire about? User: My bill says I made a call to Syncamaloo, Texas, but I’ve never even heard of this town. System: May I have the date of the call that appears on your bill?

Identifying RS Automatically (Marcu ’99)Marcu ’99 Train a parser on a discourse treebank –90 RS trees, hand-annotated for rhetorical relations –Elementary discourse units (edu’s) linked by RR –Parser learns to identify N and S and their RR –Features: Wordnet-based similarity, lexical, structural Uses discourse segmenter to id edu’s –Trained to segment on hand-labeled corpus (C4.5) –Features: 5-word POS window, presence of discourse markers, punctuation, seen a verb?,… –Eval: 96-8% accuracy

Eval of parser: –Id edu’s: Recall 75%, Precision 97% –Id hierarchical structure (2 edu’s related): Recall 71%, Precision 84% –Id nucleus/satellite labels: Recall 58%, Precision 69% –Id RR: Recall 38%, Precision 45% Later errors due mostly to edu mis-identification –Id of hierarchical structure and n/s status comparable to human when hand-labeled edu’s used Hierarchical structure is easier to id than RR

What Can Hierarchical Structure Tell Us? Welcome to word processing. That’s using a computer to type letters and reports. Make a typo? No problem. Just back up, type over the mistake, and it’s gone.  And, it eliminates retyping.  And, it eliminates retyping.

Structures of Discourse Structure (Grosz & Sidner ‘86)Grosz & Sidner ‘86) Leading alternative theory of discourse structure –Provides for multiple levels of analysis: S’s purpose as well as content of utterances and S and H’s attentional state –Identifies only a few, general relations that hold among intentions Three components: –Linguistic structure –Intentional structure –Attentional structure

Linguistic Structure What is actually said/written How is this represented? –Assume discourse is segmented into Discourse Segments (DS) -- how? what is basic unit of analysis? segmentation agreement automatic segmentation –Embedding relations: topic structure –Cue phrases

Intentional Structure Discourse purpose (DP): basic purpose of the discourse Discourse segment purposes (DSPs): how this segment contributes to the overall DP Segment relations: –Satisfaction-precedence: DSP1 must be satisfied before DSP2 (e.g. ds1 satp ds2) –Dominance: DSP1 dominates DSP2 if fulfilling DSP2 constitutes part of fulfilling DSP1 (e.g. ds3 dom ds4)

Attentional State Focus stack: –Stack of focus spaces, each containing objects, properties and relations salient during each DS, plus the DSP (content plus purpose) –State changes modeled by transition rules controlling the addition/deletion of focus spaces Information at lower levels may or may not be available at higher levels Focus spaces are pushed onto the stack when –new DS or embedded DS (e.g. DS that are dominated by other DS) are begun –popped when they are completed

Limits of G&S ‘86 Assumes that discourses are task-oriented Assumes there is a single, hierarchical structure shared by S and H How do we identify entities that are salient (on the focus stack)? Do people really build such structures when they converse? Use them in interpreting what others say?

How are these structures recognized from a discourse? Linguistic markers: –tense and aspect –cue phrases –intonational variation Inference of S intentions Inference from task structure Intonational Information

Acoustic and Prosodic Cues to Discourse Structure Intuition: –Speakers vary acoustic and prosodic cues to convey variation in discourse structure –Systematic? In read or spontaneous speech? Evidence: –Observations from recorded corpora –Laboratory experiments –Machine learning of discourse structure from acoustic/prosodic features

Boston Directions Corpus (Hirschberg & Nakatani ’96)Hirschberg & Nakatani ’96 Experimental Design 12 speakers: 4 used Spontaneous and read versions of 9 direction-giving tasks Corpus: 50m read; 67m spon Labeling –Prosodic: ToBI intonational labeling –Discourse: Grosz & SidnerDiscourse Features used in analysis

–F0 max and mean –Energy (rms) max and mean –Speaking rate (syllables per sec) –Duration of preceding and subsequent pause Correlations with SBEG, SCONT and SF phrases Results (significant differences) –SBEG higher in f0 and RMS max and mean, with longer preceding and shorter succeeding pauses –SF lower in f0 and RMS max and mean, with shorter preceding and longer succeeding pauses, and are spoken more rapidly Discourse structure is signaled by acoustic/prosodic variation: do people use it?

ds1: step 1, enter and get token first enter the Harvard Square T stop and buy a token ds2: inbound on red line then proceed to get on the inbound um Red Line uh subway Boston Directions Corpus: Describe how to get to MIT from Harvard

ds3: take subway from hs, to cs to ks and take the subway from Harvard Square to Central Square and then to Kendall Square ds4: describe ks station you’ll see a music sculpture there which will tell you it’s Kendall Square it’s very nice ds5: get off T. then get off the T

Next Class Dialogue Systems (J&M 22, new version) HW3 due