Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.

Slides:



Advertisements
Similar presentations
QAA Enhancement Themes Conference Heriot Watt University Wednesday 5 th March 2008 Poster Presentation by Mhairi Freeman (lecturer), Sally Michie, Stephanie.
Advertisements

Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Computer Supported Collaborative Learning Track Introduction Carolyn Penstein Rosé Carnegie Mellon University Language Technologies Institute and Human-Computer.
Towards Adaptive Web-Based Learning Systems Katerina Georgouli, MSc, PhD Associate Professor T.E.I. of Athens Dept. of Informatics Tempus.
Critical Thinking Course Introduction and Lesson 1
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Module 2.5 B.  Access the Internet in order to find resources for specific subject areas.  Analyze resources from websites for use in tutoring sessions.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Active ReadingStrategies. Reader Reception Theory emphasizes that the reader actively interprets the text based on his or her particular cultural background.
1 ISEM 3120 Seminar ISEM Objective(s): This year, the focus of this subject is to firstly teach you how to conduct a research project, and secondly pick.
Ethnography. In ethnography, the researcher  Participates in people's daily lives for an extended period of time  Watches everyday happenings  Listens.
Lecture 13 Revision IMS Systems Analysis and Design.
Writing Good Software Engineering Research Papers A Paper by Mary Shaw In Proceedings of the 25th International Conference on Software Engineering (ICSE),
ICS 463, Intro to Human Computer Interaction Design: 3. Perception Dan Suthers.
HRM-755 PERFORMANCE MANAGEMENT
NAACL HLT 2010 | Los Angeles Thursday, June 3, 2010 Engaging Learning Groups using Social Interaction Strategies Rohit Kumar, Carolyn P. Rosé Language.
Chapter One – Thinking as a Writer
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
14: THE TEACHING OF GRAMMAR  Should grammar be taught?  When? How? Why?  Grammar teaching: Any strategies conducted in order to help learners understand,
Metaphor Analysis in Social Science: The problem Lynne Cameron and Rob Maslen.
RSBM Business School Research in the real world: the users dilemma Dr Gill Green.
Thinking Actively in a Social Context T A S C.
1 UT International Students’ Perception of their Communicative Competence.
Home, school & community partnerships Leadership & co-ordination Strategies & targets Monitoring & assessment Classroom teaching strategies Professional.
NSW Curriculum and Learning Innovation Centre Draft Senior Secondary Curriculum ENGLISH May, 2012.
TLE Challenge – Session 2
Effective Public Speaking Chapter # 3 Setting the Scene for Community in a Diverse Culture.
4/12/2007dhartman, CS A Survey of Socially Interactive Robots Terrance Fong, Illah Nourbakhsh, Kerstin Dautenhahn Presentation by Dan Hartmann.
UNIT 1 ENGLISH DISCOURSE ANALYSIS (an Introduction)
What is linguistics  It is the science of language.  Linguistics is the systematic study of language.  The field of linguistics is concerned with the.
Copyright © 2002 Thomson Learning, Inc. Chapter 5: Language: Barrier and Bridge PowerPoint Presentation to accompany Looking Out, Looking In, Tenth Edition.
B 203: Qualitative Research Techniques Interpretivism Symbolic Interaction Hermeneutics.
Encouraging Creativity & Innovation in a Team Professional Year Program - Unit 5: Workplace media and communication channels.
Choice Words, Opening Minds, and Mindset COOR ISD February 2015.
TOWARDS ACADEMICALLY PRODUCTIVE TALK SUPPORTED BY CONVERSATIONAL AGENTS Carolyn Penstein Rosé, Carnegie Mellon University Lauren Resnick, University of.
SPEECH AND WRITING. Spoken language and speech communication In a normal speech communication a speaker tries to influence on a listener by making him:
HYMES (1964) He developed the concept that culture, language and social context are clearly interrelated and strongly rejected the idea of viewing language.
PIER Research Methods Protocol Analysis Module Hua Ai Language Technologies Institute/ PSLC.
Pragmatics.
UNIT 7. DIDACTIC APPROACHES
Discourse and Genre. What is Genre? Genre – is an activity that people engage in through the use of language. Two types of genre 1. Spoken genres – academic.
1 Branches of Linguistics. 2 Branches of linguistics Linguists are engaged in a multiplicity of studies, some of which bear little direct relationship.
ACE TESOL Diploma Program – London Language Institute OBJECTIVES You will understand: 1. The terminology and concepts of semantics, pragmatics and discourse.
 There must be a coherent set of links between techniques and principles.  The actions are the techniques and the thoughts are the principles.
Carolyn Penstein Rosé Language Technologies Institute Human-Computer Interaction Institute School of Computer Science With funding from the National Science.
Jozef Goetz contribution, 2011 About You Introduce yourself to the class: -Your name, your major and concentration (and where you work - optional)
By: Nicole Oldham. Effectively planned, well-paced, relevant, and interesting instruction is a key aspect of effective classroom management. For schools.
EEL 5937 Agent communication EEL 5937 Multi Agent Systems Lotzi Bölöni.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Interpersonal communication. defining the process of message transaction between people to create and sustain shared meaning.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
LIS 570 Qualitative Research. Definition A process of enquiry that draws from the context in which events occur, in an attempt to describe these occurrences,
Discourse Analysis Week 10 Riggenbach (1999) Chapter 1 - Quotes.
What is rhetoric? What you need to know for AP Language.
INTRODUCTION TO THE WIDA FRAMEWORK Presenter Affiliation Date.
Objectives of session By the end of today’s session you should be able to: Define and explain pragmatics and prosody Draw links between teaching strategies.
Grounded theory, discourse analysis and hermeneutics Part Two – Discourse Analysis ERPM001 Interpretive Methodologies Dr Alexandra Allan.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
So, dear colleagues, first of all we need to understand the exceptional value of the teacher in the civilized world. Always there was a relationship:
IINDIVIDUAL LEARNING STYLE IN LANGUAGE LEARNING. Most children and adults can master some content - how they master, it is determined by individual learning.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Computational Models of Discourse Analysis
Chapter 8 Communicative competence
Computational Models of Discourse Analysis
Standards learning goals - syllabus lecture notes – the current .ppt
Standards learning goals - syllabus lecture notes – the current .ppt
Presentation transcript:

Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute

Warm-Up Discussion What is the distinction between personality, identity, and perspective?  Does the distinction matter computationally How do they related to one another as lenses for understanding social media data? What do we take from today’s readings for assignment 4? Personality Identity Perspective

Student Comment At first the paper did not seem related to our task of identifying gender but perhaps this paper shows that the way we see ourselves is extremely consistent. No matter how you ask the question a subject will always give you an honest answer as to how they see themselves. This could mean that no matter how hard we try we will sooner or later embed signals into our blog posts that indicate our perceived gender.

Student Comment It seems that the importance of "spiritual self" in presentation is the most important takeaway from this paper. 96% of users attempt to describe themselves with aspects of their "spiritual self" (i.e., perceived abilities). So focusing on these instead of the material or the social might be better (although, it's possible that a particular gender uses one of these sub-types significantly more than another, which could also be handy, but we don't have that information). Is this personality or identity? How would you expect it to relate to other online behavior?

Semester Review

Semester in Review Unit 1: Theoretical Foundation Unit 2: Linguistic Structure Unit 3: Sentiment Unit 4: Identity and Personality Unit 5: Social Positioning In each Unit:  Readings from Discourse Analysis and Sociolinguistics  Readings from Language Technologies  Hands-on assignment Implementation and corpus based experiment Competitive error analysis Student Presentations

Building Tasks According to Gee’s theory, whenever we speak or write, we are constructing 7 areas of reality What we build: Significance, Practices, Identities, Relationships, Politics, Connections, Sign systems and knowledge How we build them: Social languages, Socially situated identities, Discourses, Conversations, Figured worlds, intertextuality

What we Build Significance: things and people made more or less significant through the text Practices: ritualized activities and how are they being enacted through the text (for example, lecturing or mentoring) Identities: manner in which things and people are being cast in a role through the text Relationships: style of social relationship, like level of formality Politics: how “social goods” are being distributed, who is responsible for the flow, where is it going Connections: connections and disconnections between things and people, e.g., what ideas are related, how are things causally connected, what is affecting what? Sign Systems and Knowledge: languages, social languages, and ways of knowing, what ways of communicating and knowing are treated as standard and acceptable in the context, e.g., that you’re expected to speak in English in class

Discourse Environmentalism Conversation Global Warming Discourse StatusQuo Socially Situated Identity Environmentalist Social Language Liberal rhetoric Figured World Expected structure of Conservationist Commercial Form-Function Correspondence Range of meanings for the word “sustainability” Situated Meaning Meaning of “sustainability” in the commercial Imagine an environmentalist commercial

Computationalizing Gee? Challenge: not variationist Form-function correspondences can be modeled naturally through rules Cells of table like feature extractors? Social Languages like topic models? Figured worlds related to “social causality”

Metafunctions

What is a system?

Computationalizing SFL? See Elijah’s ACL paper! We had to REALLY simplify to get there Not clear how to do that for Heteroglossia yet

Computational Techniques Text entailment/ similarity measures/ paraphrase/ constraint relaxation Topic models Machine Learning Techniques: bootstrapping, HMMs, other statistical modeling techniques Basic features: unigrams, bigrams, POS bigrams, acoustic and prosodic features (speech) Created features: dictionaries, templates, syntactic dependency relations

Basic Aspects of Discourse Structure are Easiest to Model Turn taking Topic segments Speech acts (at least direct ones) More recent computational work focuses on more challenging “discoursey” problems like sentiment and stance Some recent work on metaphors (related to frames), but not applied to discourse level problems

Problems Labels in public datasets don’t necessarily match the theory  Computational approaches embody variationist assumptions, but much of the theory is grounded in a more contextualized view of meaning making Lack of a fully satisfying operationalization of style (style is hard to separate from content)  Grammatical metaphor and other indirect strategies  Same effect can be achieved in so many ways – each technique only captures one slice – so you’re always just grasping a glimpse of what’s there Overfitting spurious correlations  “subpopulations” leading to problems with generalization  Similar variation arising due to numerous different factors (gender, age, SES)  Features at too low level – words serving multiple purposes simultaneously

Engagement and Personality?

How would you expect an Engagement style analysis to relate to personality? What effect would you expect to see on conversations? Are these necessarily connected?

Freshman Engineering Study 131 Freshman engineering students worked in groups of 3 or 4 to design a better wrench  Applying principles related to stress and leverage Procedure  Tutorial on computer aided engineering  Pretest  Collaborative design activity  Posttest  Questionnaire

Heteroglossia Manipulation

Social Manipulation

Tutor Agent Design RequestDetecto r T.TakingCoordinator TutoringManag er OutputCoordinator ConcertChatActorConcertChatListener ConcertChat Server TutoringActor PromptingActor MessageFilter DiscourseMemory PresenceFilter PromptingManage r IntroductionsActor IntroductionsManag er ActivityDetector AnnotationFilter PlanExecutor SocialControlle r ProgressDetector Tutor One last thing on this topic, Does more (or less) stress in a wrench make it easier to use? S95no change? TutorYou are correct about that.. Stress doesn't determine ease of use. Tutor It's the moment achieved by the wrench that determines the ease of use. S89yay! Tutor It's good to have your contributions in the discussion Jackie :-) TutorGo team :-) S89Go team yay Tutor I am happy to be working with our team S89Me too S95whoa the bot knows my name Tutor Unfortunately maximum stress (12800) in our design1 is way above the maximum allowed stress (i.e. 8750) TutorThis wrench cannot be safely used! Kumar, R. & Rosé, C. P. (2011). Architecture for building Conversational Agents that support Collaborative Learning, IEEE Transactions on Learning Technologies special issue on Intelligent and Innovative Support Systems for Computer Supported Collaborative Learning

Results on Breadth of Coverage of Design Space Significant main effect of Heteroglossia on number of ideas mentioned  Heteroglossia was better than Monoglossia and Neutral Significant interaction  In the Social condition, Monoglossia was worse than the other two

Results on Perception Students were significantly happier with the interaction in the Heteroglossia condition than Neutral, with Monoglossia in the middle Students liked the Heteroglossic and Monoglossic agents better than the Neutral agent Students in the Heteroglossia condition felt marginally more successful than students in the Monoglossia condition No effect on Personality indicators such as Pushy, Wishy Washy, etc. Does that mean that impression of personality and how you feel about an interaction with someone are not linked?

Student Comment I would also note that English is a very gender neutral language, so gender performativity is harder to classify.

Engagement Already established: Positioning a proposition  But can it also be primarily positioning between people?  Patterns of positioning propositions as having the same or different alignment between speaker and hearer could do this Is positioning in communication always positioning by means of propositional content?

Connection between Heteroglossia and Attitude But is this really different from a disclaim? And is this really different from a proclaim?

Hedging and Occupation? And as such, I believe hedging is a much more effective tool in showing generational or occupational differences rather than gender differences.  For example, teenagers often use verbs such as 'like' and 'all' to report speech: he was all 'that's stupid' and then he was like ''but I'm stupid too'. The occupational differences I would attribute to the differences between people who need exact values as opposed to people who can accept generalizations or approximations.

Questions?