42
Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Embed Size (px)

Citation preview

Page 1: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Linguistic issues in building

dialogue systems         

Radhika Mamidi

IIIT-H

Page 2: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Outline Linguistic issues in NLP including Pragmatics Computational Pragmatics

Pragmatics Discourse Analysis Conversation Analysis

Spoken Dialogue Systems Types, models, domains Comparing human-human vs human-system

dialogues Speech Act interpretation

Page 3: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Why is Natural Language Processing so difficult? Human language is:

Complex and Ambiguous

We use language creatively We don’t mean what we say!

Language Understanding needs contextual and general knowledge apart from linguistic knowledge. To know what we mean shared knowledge is

necessary.

Representing all this knowledge computationally is THE challenge.

Page 4: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Let’s analyze this spoken sentence:“I made her duck”

How many meanings/interpretations?

Page 5: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Human language is complex and ambiguous When shot at, the dove dove into the bushes. The insurance was invalid for the invalid. They were too close to the door to close it. The buck does funny things when the does

are present. There was a row among the oarsmen about

how to row. Upon seeing the tear in the painting I shed a

tear.

Page 6: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Language understanding: Parsing problem! Gene Autry is better after being kicked by a

horse. The women included their husbands and

their children in their potluck suppers. Two cars were reported stolen by the

Groveton police yesterday. (Steven Pinker. 1994. The language instinct. Morrow. 102.)

Page 7: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H
Page 8: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

We use language creatively…

Example recommendations:

A man like him is hard to find. He's an unbelievable worker. You would indeed be fortunate to get this person to

work for you. There is nothing you can teach a man like him. I can assure you that no person would be better for

the job.

Page 9: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

What we say and what we mean A man like him is hard to find.

[For a chronically absent employee]

He's an unbelievable worker. [For a dishonest employee]

You would indeed be fortunate to get this person to work for you. [For a lazy employee]

There is nothing you can teach a man like him. [For a stupid employee]

Page 10: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Cooperative model: various types of knowledge

MemoryGeneral Knowledge

Lexicon Syntactic Rules

Semantic Rules

DiscourseRules

LexicalProcessing

INPUTSSyntactic

ProcessingSemantic

ProcessingDiscourseProcessing

OUTPUTS

Hetararchical model of Language Processing

(Greene, 1986)Eg: The building blocks…

Page 11: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Pragmatics Study of how utterances have meanings in situations. (Leech, 1983) Study of how more gets communicated than is said. (Yule, 1996) How people comprehend and produce a communicative

act or speech act in a concrete speech situation. It distinguishes two intents or meanings in each

utterance or communicative act of verbal communication.

Informative intent = the sentence meaningCommunicative intent = speaker meaning

(Sperber and Wilson, 1995).

Page 12: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Pragmatic competence

the ability to comprehend and produce a communicative act

Includes one's knowledge about the social distance, social status between the speakers involved, the cultural knowledge such as politeness, and the linguistic knowledge explicit and implicit.

Page 13: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Topics in Pragmatics deals with relations between linguistic aspects and

aspects of context.

Conversational ImplicatureA: Coffee?

B: It will keep me awake. Presupposition

“I bought this book in Italy last summer” Speech Acts

“Why don’t you call Mary?” Deixis

“I’d like you to leave that over there and come here now”

Page 14: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Discourse Analysis

Anaphora resolution

John and Mary bought new cars. They are good friends.

John and Mary bought new cars. They are 2008 models.

Rhetorical relations

John fell. Jack pushed.

John went to work. He works at IBM.

John went to work. He took a taxi.

Ellipsis

Mary bought a new car. So did Susan.

Mary bought a new dress. So did Susan.

Page 15: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Conversation Analysis Turn Constructional Component Turn Allocational Component

Sequence Organization Adjacency pairs: greeting-greeting, question-answer pairs Pre-sequences

Preference Organisation:agreement and acceptance are promoted over their alternatives

Repair:who initiates repair (self or other) and by who resolves the problem (self or other)

Sacks, H., Schegloff, E. A., & Jefferson, G. (1974)

Page 16: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Computational Pragmatics“Computational pragmatics studies, from an explicitly computational

point of view, how relations between linguistic phenomena and their context of use govern speakers’ abilities to interpret and generate utterances in conversation”

How to compute these relations in terms of explicitrepresentations. . .

• given a linguistic expressions, how to compute the relevant contextual properties• given a particular context, how to compute the relevantlinguistic expression

(Bunt & Black, 2000)

Page 17: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Application of computational pragmaticsWork on computational pragmatics often takes

place within research on dialogue systems.

Systems that are able to interact with human users in natural language.

Helps us make decisions on how to deal in a computational way with all phenomena related to language use.

Page 18: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

What is a dialogue system?

An artificial agent like robot or a computer system that can interact with human beings.

Helps us understand the nature of dialogue and test theories

Helps us understanding the collaborative nature of interaction

Helps us access information and services more efficiently

Page 19: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Uses of dialogue systems

Phone-based applications: timetable info or flight-booking

Personal assistant: understand user needs and tasks

Intelligent tutoring: student engagement Embodied conversational agents

– Engagement via realistic and affective physical and facial gestures

Intelligent environments: home or car– Understanding user situation and activity

Page 20: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Architecture

(Mamidi and Khan, 2005)

Page 21: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Available intelligent dialogue systems Interactive Voice Systems [e.g. railway enquiry system

asking the user to press certain numbers for accomplishing the task]

Question-Answering Systems [e.g. START, a web-based QA system answering user's questions on movies, places, people etc.]

Natural Language Interfaces [e.g. tutoring systems, trip planning systems]

Task-oriented Restricted Domain Easier to implement

Ultimate goal to have Dialog Systems that talk like human beings and display intelligence in understanding the complex cognitive structure of language.

Page 22: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Dialogue domains

Travel information (SUNDIAL, ATIS) Transport (TRAINS) Business Appointments (VERBMOBIL) Car-Navigation Access to on-line information

(SUN Speech Acts)

Page 23: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Dialogue models

Dialogues can be: Non-machine-mediated: ordinary every-day human

dialogue analysed by computational means (dialogue datais recorded, transcribed and analysed to build automatedsystems).

Machine-mediated: The computer offers assistance to the participants (VERBMOBIL).

Simulated: Both participants are human, but one pretends to be a computer system.

Non-simulated: Genuine interaction between human and computer (fully-fledged Dialogue Systems)

Page 24: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Types of dialog systems

Single initiative systemGuide user through a series of scripted prompts.

Eg. Telephone enquiry

Mixed initiative systemCooperative and flexible responses to user queries.

Eg. Restaurant database

Page 25: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H
Page 26: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Sample dialogue: CSLI Dialogue System for in-car devicesU: What music do you have?S: I have rock, soul … // aggregationU: What rock songs?Sys: Just a second: you have to turn left at the next intersection // interruptionU: OK.S: I have songs by U2, Cake, Green Day, Jet, … // return to previous threadU: Play something by them. // pronominal referenceS: OK. Playing xxx. < plays random song by Jet >U: Play American Idiot instead.S: Do you mean the song or the album? // disambiguationU: The album please. // fragmentU: I need somewhere for lunch.S: There is a highly rated vegetarian restaurant near here. // knows preferencesU: What other cuisines?S: There are Italian, Japanese, Malaysian, Nepali, and Thai restaurants close

by.

Page 27: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Sample…

A: And what time would you like to leave Pittsburgh? (relevant next contribution)

C: Uh hmm, I don’t think there’s many options for non-stop

A: Right. There’s three non-stops today.

Page 28: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Comparing human-human vs computer-human dialogues Human-Human

Hums, grunts, pauses, false starts, hesitations Barge in conversations Elliptical constructions Context is important

Computer-Human dialogues Rigid; turn by turn pattern User speaks a word or two

Page 29: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Intelligent agent components

perception - the agent must be able to perceive the world around it

beliefs - the agent must have a representation of the present state of the world

desire/wants - the agent should have positive or negative responses to various states of the world, creating a way to compare the desirability of states

planning/reasoning - the agent must be able to reason about ways to attain other states

commitment - the agent must be able to decide to act to get to a different state

intentions - the agent must be able to maintain the course of action decided on

acting - the agent must be able to act and thus change its state

(Allen,1995)

Page 30: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Illocutionary speech acts

Searle (1975): Assertives Directives Commissives Expressives Declarations

Page 31: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Challenges

Speech recognition errors Parsing language in practical dialogue

Need to capture what was said Spoken language is not sentence based A single utterance realises a sequences of speech act.

Intention recognition Mixed initiative Integrate dialogue and task performance Context-dependent interpretation Dialogue strategies (turn-taking mechanisms)

Page 32: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

If computers were to speak like us… Recognise intention of speaker

A1: Lend me your umbrella. It is cloudy. [Request] A2: Don't water the plants now. It is cloudy. [Warning] A3: It will rain today. It is cloudy. [Assertion] A4: I hope the pictures will come out well. It is cloudy.

[Doubt] Make proper inference

B1: Did you look at the sentence I sent you to translate. C1: Yeah. It was such an easy sentence! B2: Was it easy? C2: No, I meant it was tough.

Page 33: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

And…

Ellipsis Retaining the logical form of previous sentence. Reconstructing full content.

Turn management: determining when the turn is over and who talks next

Grounding - acknowledgement, repetition Clarification: question to resolve some lack of

understanding Anaphora resolution

Page 34: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Speech act interpretation

BDI model Cue based model

Page 35: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Belief Desire Intention (BDI) modelBunt and Black (2000) define this line of inquiry as

follows:to apply the principles of rational agenthood to the modeling of a (computer-based) dialogue participant, where a rational communicative agent is endowed not only with certain private knowledge and the logic of belief, but is considered to also assume a great deal of common knowledge/beliefs with an interlocutor, and to be able to update beliefs about the interlocutor’s intentions and beliefs as a dialogue progresses.

Page 36: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Belief Desire Intention algorithm Extremely powerful approach to dialogue act

comprehension/speech act interpretation. Uses rich knowledge structures and powerful

planning techniques. Addresses even subtle indirect uses of

dialogue acts. Incorporates knowledge about speaker and

hearer intentions, actions, knowledge, and belief that is essential for any complete model of dialogue.

Page 37: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Drawback

It requires that each utterance have a single literal meaning, which is operated on by plan inference rules to produce a final non-literal interpretation.

Much recent work has argued against this literal-first non-literal-second model of interpretation.

Page 38: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Alternative - Cue model

Listener uses different cues in the input to help decide how to build an interpretation.

The surface input to the interpretive algorithm provides clues to structure-building, rather than providing a literal meaning which must be modified by purely inferential processes.

What characterizes a cue-based model is the use of different sources of knowledge (cues) for detecting a speech act, such as lexical, collocational, syntactic, prosodic, or conversational-structure cues.

Page 39: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

Conclusion

Pragmatics is the base of Computational Pragmatics.

Dialogue allows to explore novel challenges in language technologies.

Understanding human-human dialogue helps in building human-system dialogue.

Goal is to build robust dialogue systems for mixed-initiative, multi-domains and multi-party interactions.

Page 40: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

References Allen, James. 1995. Natural Language Understanding. Menlo Park,

CA: Benjamin Cummings. Allen, James, Donna Byron, Myroslava Dzikovska, George

Ferguson, Lucian Galescu, and Amanda Stent. 2001. Towards Conversational Human-Computer Interaction. AI Magazine.

Allen, James, Donna Byron, Myroslava Dzikovska, George Ferguson, Lucian Galescu, and Amanda Stent. 1998. Natural Language Engineering. Cambridge University Press.

Bunt, Harry and William Black (eds.) 2000. Abduction, Belief and Context in Dialogue. Amsterdam: John Benjamins.

Greene, Judith. 1986. Language Understanding: A cognitive approach. Open university press.

Jurafsky, Daniel, and James H. Martin. 2000. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall.

Leech, Geoffrey N. 1983. Principles of Pragmatics. London: Longman.

Page 41: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H

References Levinson, Stephen C. 1983. Pragmatics. Cambridge University

Press. Mamidi, Radhika and Monis Raja Khan. 2005. Linguistic issues in

building Dialog Systems. Presented at The Linguistic Society of India Platinum Jubilee Conference, University of Hyderabad, India. 6-8 December, 2005

Ruslan, Mitkov (ed). 2003. The Oxford handbook of Computational Linguistics. Oxford University Press.

Sacks, H, E. A. Schegloff, G Jefferson. 1974. A simplest systematics for the organization of turn-taking for conversation. Language, 50, 696-735.

John Searle. 1975. Indirect speech acts. In Syntax and Semantics, 3: Speech Acts, ed. P. Cole & J. L. Morgan, pp. 59–82. New York: Academic Press.

Sperber, D and D. Wilson. 1995. Relevance: Communication and Cognition, 2nd ed. Oxford: Blackwell.

Yule, George.1996. Pragmatics (Oxford Introductions to Language Study). Oxford University Press.

Page 42: Linguistic issues in building dialogue systems Radhika Mamidi IIIT-H