Modeling Long-Distance Dependencies in Double R July 2008 Jerry Ball Human Effectiveness Directorate Air Force Research Laboratory.

Slides:



Advertisements
Similar presentations
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA Modeling Social Cognition in a Unified Cognitive Architecture.
Advertisements

Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Double R Ontology and Gold Standard April 2008 Jerry Ball Senior Research Psychologist Human Effectiveness Directorate Air Force Research Laboratory.
Projecting Grammatical Features in Nominals: Cognitive Theory and Computational Model October 2009 Jerry Ball Air Force Research Laboratory.
Toward a Large-Scale Model of Language Comprehension in ACT-R 6 July 2007 Jerry Ball 1, Andrea Heiberg 2, and Ronnie Silber 3 Air Force Research Laboratory.
Second Language Acquisition
Psycholinguistic what is psycholinguistic? 1-pyscholinguistic is the study of the cognitive process of language acquisition and use. 2-The scope of psycholinguistic.
PM—Propositional Model A Computational Psycholinguistic Model of Language Comprehension Based on a Relational Analysis of Written English Jerry T. Ball,
Syntax-Semantics Mapping Rajat Kumar Mohanty CFILT.
Context Accommodation in Human Language Processing June 2010 Jerry T. Ball Senior Research Psychologist 711 th HPW / RHAC Air Force Research Laboratory.
Projecting Grammatical Features in Nominals: 23 March 2010 Jerry T. Ball Senior Research Psychologist 711 th HPW / RHAC Air Force Research Laboratory DISTRIBUTION.
A Naturalistic, Functional Approach to NLU November 2008 Jerry Ball Air Force Research Laboratory.
Language and Cognition Colombo, June 2011 Day 2 Introduction to Linguistic Theory, Part 4.
Linguistic Theory Lecture 7 About Nothing. Nothing in grammar Language often contains irregular paradigms where one or more expected forms are absent.
Synthetic Teammate Project March 2009
Lecture 11: Binding and Reflexivity.  Pronouns differ from nouns in that their reference is determined in context  The reference of the word dog is.
Introduction to phrases & clauses
Basic Expressions July 2007 Jerry Ball 1, Andrea Heiberg 2 Air Force Research Laboratory 1 L3 Communications 2.
1 LIN 1310B Introduction to Linguistics Prof: Nikolay Slavkov TA: Qinghua Tang CLASS 18, March 13, 2007.
Linguistic Theory Lecture 8 Meaning and Grammar. A brief history In classical and traditional grammar not much distinction was made between grammar and.
Language, Mind, and Brain by Ewa Dabrowska Chapter 10: The cognitive enterprise.
Language, Mind, and Brain by Ewa Dabrowska Chapter 2: Language processing: speed and flexibility.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Fall 2005-Lecture 2.
Abstraction and ACT-R. Outline Motivations for the Theory –Architecture –Abstraction Production Rules ACT-R Architecture of Cognition.
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Outline of English Syntax.
Transformational Grammar p.33 - p.43 Jack October 30 th, 2012.
The students will be able to know:
Syntax.
1. Introduction Which rules to describe Form and Function Type versus Token 2 Discourse Grammar Appreciation.
Emergence of Syntax. Introduction  One of the most important concerns of theoretical linguistics today represents the study of the acquisition of language.
Embedded Clauses in TAG
Context Free Grammars Reading: Chap 12-13, Jurafsky & Martin This slide set was adapted from J. Martin, U. Colorado Instructor: Paul Tarau, based on Rada.
1 Features and Unification Chapter 15 October 2012 Lecture #10.
1 The Interaction Between Verbs And Constructions Lucas Champollion Oct 18 th, 2004 Goldberg, Adele E. (1995): Constructions. Ch. 2.
Long-Term Memory Ch. 3 Review A Framework Types of Memory stores Building Blocks of Cognition Evolving Models Levels of Processing.
Relative clauses Chapter 11.
C Pearson Allyn & Bacon Encoding and Retrieval Processes in Long-Term Memory Chapter 6.
A Cognitive Substrate for Natural Language Understanding Nick Cassimatis Arthi Murugesan Magdalena Bugajska.
IV. SYNTAX. 1.1 What is syntax? Syntax is the study of how sentences are structured, or in other words, it tries to state what words can be combined with.
THE BIG PICTURE Basic Assumptions Linguistics is the empirical science that studies language (or linguistic behavior) Linguistics proposes theories (models)
Chapter 10 - Language 4 Components of Language 1.Phonology Understanding & producing speech sounds Phoneme - smallest sound unit Number of phonemes varies.
Linguistic Theory Lecture 10 Grammaticality. How do grammars determine what is grammatical? 1 st idea (traditional – 1970): 1 st idea (traditional – 1970):
Construction Driven Language Processing May 2007 Jerry T. Ball Senior Research Psychologist Air Force Research Laboratory Mesa, AZ.
October 15, 2007 Non-finite clauses and control : Grammars and Lexicons Lori Levin.
Context Free Grammars Reading: Chap 9, Jurafsky & Martin This slide set was adapted from J. Martin, U. Colorado Instructor: Rada Mihalcea.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Fall 2005-Lecture 4.
Culture , Language and Communication
Albert Gatt LIN3021 Formal Semantics Lecture 4. In this lecture Compositionality in Natural Langauge revisited: The role of types The typed lambda calculus.
Rules, Movement, Ambiguity
Linguistic Theory Lecture 5 Filters. The Structure of the Grammar 1960s (Standard Theory) LexiconPhrase Structure Rules Deep Structure Transformations.
Universal Grammar Functional Approaches
From Mind to Brain Machine The Architecture of Cognition David Davenport Computer Eng. Dept., Bilkent University, Ankara – Turkey.
Chapter 8. Situated Dialogue Processing for Human-Robot Interaction in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans Sabaleuski.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 2.
SYNTAX.
◦ Process of describing the structure of phrases and sentences Chapter 8 - Phrases and sentences: grammar1.
Lecture 1: Trace Theory.  We have seen that things move :  Arguments move out of the VP into subject position  Wh-phrases move out of IP into CP 
MENTAL GRAMMAR Language and mind. First half of 20 th cent. – What the main goal of linguistics should be? Behaviorism – Bloomfield: goal of linguistics.
2. The standards of textuality: cohesion Traditional approach to the study of lannguage: sentence as conventional object of study Structuralism (Bloofield,
Chapter 3 Language Acquisition: A Linguistic Treatment Jang, HaYoung Biointelligence Laborotary Seoul National University.
SYNTAX.
King Faisal University جامعة الملك فيصل Deanship of E-Learning and Distance Education عمادة التعلم الإلكتروني والتعليم عن بعد [ ] 1 King Faisal University.
Natural Language Processing Vasile Rus
Human Computer Interaction Lecture 21 User Support
PSYC 206 Lifespan Development Bilge Yagmurlu.
SYNTAX.
Towards Semantics Generation
Structure of a Lexicon Debasri Chakrabarti 13-May-19.
Presentation transcript:

Modeling Long-Distance Dependencies in Double R July 2008 Jerry Ball Human Effectiveness Directorate Air Force Research Laboratory

2 Double R Model Goal: Model the basic grammatical patterns of English to support development of cognitively plausible and functional language comprehension systems – Declaratives – “The man hit the ball” – Questions Yes-No Questions – “Did the man hit the ball?” Wh Questions – “Where did the man hit the ball?” – Imperatives – “Hit the ball!” – Relative Clauses – “The ball that the man hit” – Wh Clauses – “I know where the man hit the ball” – Passive constructions – “The ball was hit”

3 Empirical Evidence Basic grammatical patterns have been most extensively studied in generative grammar – The focus in generative grammar has been on studying the syntactic form of linguistic expressions in isolation from meaning and processing The “Simpler Syntax” of Culicover and Jackendoff (2005) is redressing the consideration of meaning and simplifying syntax as a side effect O’Grady’s “Syntactic Carpentry” (2005) integrates processing as well (see also Hawkins, 2004) Reference grammars (Huddleston & Pullum, 2002; Quirk et al., 1985) provide a wealth of examples which integrate form, function and meaning

4 Long-Distance Dependencies Long-distance dependencies are the sin qua non of modern linguistic theorizing – An important motivation for Chomsky’s transformational grammar – deep structures with arguments in place are mapped to surface structures with arguments “moved” by various transformations Introduction of traces supported the collapsing of deep and surface structure – traces mark the original location Construction specific transformations were generalized to Move  subject to universal, parameterized constraints – Many basic grammatical constructions involve long- distance dependencies Wh questions, relative clauses, passive constructions… – Require retention of grammatical information for extended stretches of input

5 Long-Distance Dependencies Binding of pronouns and anaphors: – Anaphors (“himself”) vs. pronouns (“him”) John i kicked himself i ( i = i ) (Principle A of GB Theory) John i kicked him j ( i not = j )(Principle B of GB Theory) – Proper binding often requires use of semantic information (but considered syntactic in generative grammar) John i and Mary j were talking. She j told him i … (gender) John i is reading a book j. It j is about… (animacy) John i is reading the comics j. They j are… (number)

6 Long-Distance Dependencies Verb Control – Object Control: “He i persuaded me j PRO j to go” PRO j is an “implicit” pronoun (a trace without movement) – Subject Control: “He i promised me j PRO i to go” Raising Verbs – “He i seems t i to like me” t i is a trace of a “raised” argument

7 Long-Distance Dependencies Passive Constructions – “The ball i was kicked t i by the man” The object is “raised” out of its normal position and the subject is pushed into an oblique complement position “by the man” Wh Questions – “Who i did John j decide PRO j to see t i ” Relative Clauses – “The ball i that the man kicked t i ”

8 Modeling Long-Distance Dependencies An ontology of DM chunk types supports the grammatical distinctions Productions match buffer elements at the appropriate level of the ontology given the function of the production, e.g. – Production matches pronoun “he…”  project nominal and put in subject buffer – Production matches predicate specifier (e.g. “…is…”)  project a declarative clause – Production matches declarative clause and a nominal in subject buffer (e.g. “he is…”)  integrate the nominal as the subject of the clause – Production matches transitive verb (e.g. “hitting”) functioning as clausal head (e.g. “he is hitting…”) and a nominal (e.g. “…the ball”)  integrate the nominal as the object of the verb

9 Ontology of Situation Referring Expressions Decl-sit-refer-expr Yes-no-quest-sit-refer-expr – “Is he going?” Wh-quest-sit-refer-expr – “Where did he go?” Imp-sit-refer-expr – “Don’t go!” Wh-sit-refer-expr – “I know where he went” Rel-sit-refer-expr – “The book that you like” Note: Situation Referring Expression corresponds to Clause in other approaches What are the grammatical cues that trigger recognition of an expression type? These cues need to be accessible!

10 Slots in Referring Expressions Bind-indx (all referring expression types) – Identifier for referring expression Parent (all chunk types) – Links child to parent chunk – Used to avoid multiply integrating chunk into other chunks Token (all chunk types) – Distinguishes types from tokens (and type-tokens) Grammatically relevant semantic info – Animate (all object referring expression types) – Gender (all animate referring expression types) – Number (all object referring expression types) – Person (all object referring expression types)

11 Recognizing Wh-Quest and Wh- Situation Referring Expressions (p cog-process-obj-refer-expr--> project-wh-quest-sit-refer-expr =goal> isa process-obj-refer-expr =wh-focus> isa wh-refer-expr ;; “where” =most-recent-child-sre-head> isa operator-pred-spec ;; “did” =retrieval-2> isa obj-refer-expr ;; “he” =subject> isa nothing =context> isa context - sit-context "wh-quest-sit-refer-expr“ ==> project wh-quest-sit-refer-expr Where did he…? (p cog-process-pred-type  project-wh-sit-refer-expr =goal> isa process-pred-type =wh-focus> isa wh-refer-expr ;; “where” =subject> isa refer-expr ;; “he” =retrieval-2> isa pred-type ;; “went” =context> isa context - sit-context "wh-sit-refer-expr" - sit-context "wh-quest-sit-refer-expr" ==> project wh-sit-refer-expr …where he went Note: the more grammatical cues, the greater the likelihood of being correct! “Who kicked…?” “Where the heck is...?” “Why is there…?

12 Modeling Long-Distance Dependencies Model needs simultaneous access to multiple grammatical elements – Serial retrieval from DM is not a viable option – Buffers support simultaneous access – buffers on left-hand side of production constitute focus of attention – limited to ~4 (Cowan, 2000) besides goal and context buffers – Can’t predict in advance of production selection which grammatical elements will be needed – Buffers and productions are functionally motivated – they are needed in the processing of various constructions A model with fewer buffers (and productions) that handles a similar set of phenomena might be a better model, but a model with fewer buffers that handles fewer phenomena is not comparable (Ball, in preparation)

13 Double R Buffers – Single Chunk Subject – stores the subject Wh-focus – stores the fronted wh expression Rel-focus – stores the relative clause marker Context – stores contextual information Construct – buffer for constructing DM chunks – Dual path processing – construct chunk vs. retrieve chunk Retrieval-2 – buffer for storing retrieved or constructed DM chunks – Retrieval buffer only used temporarily, retrieved chunk is copied into retrieval-2 for subsequent processing Most-recent-loc-refer-expr – just the most recent – Supports locative fronting “On the table is the book”

14 Double R Buffers – Multiple Chunk Most-recent-child- obj-refer-expr Most-recent-parent- obj-refer-expr Most-recent-grandparent- obj-refer-expr Most-recent-child- obj-refer-expr-head Most-recent-parent- obj-refer-expr-head Most-recent-grandparent- obj-refer-expr-head St-wm-1 St-wm-2 St-wm-3 St-wm-4 Four generic Short-Term Working Memory buffers Obj-Refer-Expr buffersObj-Refer-Expr-Head buffers Note: object referring expression corresponds to nominal in other approaches

15 Double R Buffers – Multiple Chunk Most-recent-child- sit-refer-expr Most-recent-parent- sit-refer-expr Most-recent-grandparent- sit-refer-expr Most-recent-child- sit-refer-expr-head Most-recent-parent- sit-refer-expr-head Most-recent-grandparent- sit-refer-expr-head Note 1: with the introduction of obj-refer-expr and sit-refer-expr specific buffers, the short-term working memory buffers are infrequently used (primarily for conjunctions and adverbs) Note 2: child, parent and grandparent buffers are all directly accessible, whereas only st-wm-1 is directly accessible Sit-Refer-Expr buffersSit-Refer-Expr-Head buffers

16 Long-Distance Dependencies I want to go Infinitive sit-refer-expr has implied subj with trace bound to matrix subj Combination of “bind-indx” and “trace” needed to indicate long-distance dependency Traces only occur in argument positions! Note: entire representation is not accessible at once!

17 Long-Distance Dependencies Subject control (verb): matrix clause subject binds to subject of infinitive situation complement – subject must be accessible He promised me to go Alternative view: antecedent & trace both bind to same object in situation model

18 Long-Distance Dependencies Object control (verb): matrix clause (indirect) object binds to subject of infinitive situation complement – object must be accessible He persuaded me to go

19 Who did he kick the ball to? Object of preposition is bound to fronted who-obj-refer-expr – wh-focus must be accessible Long-Distance Dependencies

20 Long-Distance Dependencies The man that I gave the book I-Obj Trace to Obj-Refer-Expr with animate or human head Rel-focus co-indexed with Obj-Refer-Expr rel-focus and subject must be accessible (rel-focus is optional)

21 Long-Distance Dependencies The book that I gave the man Obj Trace to Obj-Refer-Expr with inanimate head Rel-focus co-indexed with Obj-Refer-Expr rel-focus and subject must be accessible (rel-focus is optional)

22 Architectural Constraints No hard architectural limit on the number of buffers Buffers provide the context for production selection and execution – Highly context sensitive Productions limited to accessing ~4 buffers on left- hand side (beside goal and context buffers) – Focus of attention (Cowan, 2000) – “Conscious activity corresponds to the manipulation of the contents of these buffers by production rules” (Anderson, 2007) Can humans learn to buffer useful information? – Fronted Wh-expression buffer very useful in English, but not needed in in situ languages like Chinese

23 Processing Constraints A “mildly” deterministic, serial processing mechanism (selection and integration) operating over a parallel, probabilistic substrate (activation) Interactive and non-autonomous processing (no distinctly syntactic representations exist) Incremental processing with immediate determination of meaning – word by word No algorithmic backtracking or lookahead – a mechanism of context accommodation (Ball et al. 2007) used instead Forward chaining only Declarative and explicit linguistic representations generated via implicit execution of productions Operates in real-time on Marr’s algorithmic level (serial and parallel processing are relevant) – No slow down with length of input

24 Summary Additions to model are – motivated by functional considerations – driven by empirical evidence – constrained by well-established cognitive constraints on language processing Goal is a large-scale, functional language comprehension system implemented in the ACT-R cognitive architecture Model currently handles a fairly wide-range of grammatical constructions including numerous forms of long-distance dependency

25 Questions?

26 Ball, J., Heiberg, A. & Silber, R. (2007). Toward a Large-Scale Model of Language Comprehension in ACT-R 6. Proceedings of the 8th International Conference on Cognitive Modeling. References Ball, J. (in preparation). A Naturalistic Functional Approach to Modeling Language Comprehension. Culicover, P. & Jackendoff, R. (2005). Simpler Syntax. Oxford: Oxford University Press. Huddleston, R. & Pullum G. (2002). The Cambridge Grammar of the English Language. NY: Cambridge Unversity Press. O’Grady, William (2005). Syntactic Carpentry, an Emergentist Approach to Syntax. Mahway, NJ: LEA. Quirk, R., Greenbaum, S., Leech, G. & Svartvik, J. (1985). A Comprehensive Grammar of the English Language. Essex, UK: Pearson Education Limited. Cowan, N. (2000). The magical number 4 in short-term memory: A reconsideration of mental storage capacity. Behavioral and Brain Sciences, 24, Hawkins, J. (2004). Efficiency and Complexity in Grammars. Oxford: Oxford University Press. Anderson, J. (2007). How Can the Human Mind Occur in the Physical Universe. Oxford: Oxford University Press.

27 Long-Distance Dependencies The ball by the table was kicked by the man passive cue (be + V-ed or V-en) Subject co-indexed with Object subject must be accessible