Hao Wang, Toben Mintz Department of Psychology University of Southern California.

Slides:



Advertisements
Similar presentations
CHAPTER 2 THE NATURE OF LEARNER LANGUAGE
Advertisements

Why it is Hard to Label Our Concepts Jesse Snedeker and Lila Gleitman Harvard and U. Penn.
How Children Acquire Language
18 and 24-month-olds use syntactic knowledge of functional categories for determining meaning and reference Yarden Kedar Marianella Casasola Barbara Lust.
Syntax and Context-Free Grammars Julia Hirschberg CS 4705 Slides with contributions from Owen Rambow, Kathy McKeown, Dan Jurafsky and James Martin.
Psych 156A/ Ling 150: Acquisition of Language II Lecture 10 Grammatical Categories.
Rules vs. Constructions A debate on question-acquisition Lucia Pozzan, Lidiya Tornyova & Virginia Valian IASCL 2011.
Linguistics, Morphology, Syntax, Semantics. Definitions And Terminology.
Analysing Syntax 1 Lesson 8B.
Part of Speech Tagging Importance Resolving ambiguities by assigning lower probabilities to words that don’t fit Applying to language grammatical rules.
Psych 156A/ Ling 150: Acquisition of Language II Lecture 14 Poverty of the Stimulus III.
PSY 369: Psycholinguistics Language Acquisition: Learning words, syntax, and more.
Syntactic category acquisition. 1;0 1;1 1;2 1;3 1;4 1;5 1;6 daddy, mommy bye dog, hi, uh oh baby, ball, no eye, nose, banana, juice, shoe, kitty, bird,
Topics in Cognition and Language: Theory, Data and Models *Perceptual scene analysis: extraction of meaning events, causality, intentionality, Theory of.
From linear sequences to abstract structures: Distributional information in infant-direct speech Hao Wang & Toby Mintz Department of Psychology University.
Language, Mind, and Brain by Ewa Dabrowska Chapter 10: The cognitive enterprise.
Casenhiser and Goldberg (2005) Ability to learn to pair novel constructional meaning with novel form Known nouns and nonsense verb arranged in non- English.
Predicting the Semantic Orientation of Adjective Vasileios Hatzivassiloglou and Kathleen R. McKeown Presented By Yash Satsangi.
Distributional Cues to Word Boundaries: Context Is Important Sharon Goldwater Stanford University Tom Griffiths UC Berkeley Mark Johnson Microsoft Research/
Matakuliah: G0922/Introduction to Linguistics Tahun: 2008 Session 11 Syntax 2.
EBMT1 Example Based Machine Translation as used in the Pangloss system at Carnegie Mellon University Dave Inman.
Machine Translation Prof. Alexandros Potamianos Dept. of Electrical & Computer Engineering Technical University of Crete, Greece May 2003.
Syntax and Grammar John Goldsmith Cognitive Neuroscience May 1999.
Young Children Learn a Native English Anat Ninio The Hebrew University, Jerusalem 2010 Conference of Human Development, Fordham University, New York Background:
1 Human simulations of vocabulary learning Présentation Interface Syntaxe-Psycholinguistique Y-Lan BOUREAU Gillette, Gleitman, Gleitman, Lederer.
Psych 156A/ Ling 150: Acquisition of Language II Lecture 7 Grammatical Categories.
Psycholinguistics 11 Later language Acquisition. Acquisition of Morphology Order of Morpheme acquisition OrderMorpheme 1Present progressive 2-3Prepositions.
Today  What is syntax?  Grammaticality  Ambiguity  Phrase structure Readings: 6.1 – 6.2.
Transformational Grammar p.33 - p.43 Jack October 30 th, 2012.
14: THE TEACHING OF GRAMMAR  Should grammar be taught?  When? How? Why?  Grammar teaching: Any strategies conducted in order to help learners understand,
Syntax The number of words in a language is finite
McEnery, T., Xiao, R. and Y.Tono Corpus-based language studies. Routledge. Unit A 2. Representativeness, balance and sampling (pp13-21)
Assessment of Semantics
Distributional Part-of-Speech Tagging Hinrich Schütze CSLI, Ventura Hall Stanford, CA , USA NLP Applications.
2007. Software Engineering Laboratory, School of Computer Science S E Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying.
Dr. Monira Al-Mohizea MORPHOLOGY & SYNTAX WEEK 12.
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.
Assessment of Morphology & Syntax Expression. Objectives What is MLU Stages of Syntactic Development Examples of Difficulties in Syntax Why preferring.
Psycholinguistic Theory
Adele E. Goldberg. How argument structure constructions are learned.
© Child language acquisition To what extent do children acquire language by actively working out its rules?
Language Language – our spoken, written or signed words and the ways we combine them to communicate meaning.
English-speaking children who are typically developing first acquire item-specific patterns (e.g. put it in) and their meanings as a whole, then develop.
인공지능 연구실 황명진 FSNLP Introduction. 2 The beginning Linguistic science 의 4 부분 –Cognitive side of how human acquire, produce, and understand.
_____________________ Definition Part of Speech (circle one) Picture Antonym (Opposite) Vocab Word Noun Pronoun Adjective Adverb Conjunction Verb Interjection.
Parsing with Context-Free Grammars for ASR Julia Hirschberg CS 4706 Slides with contributions from Owen Rambow, Kathy McKeown, Dan Jurafsky and James Martin.
Artificial Intelligence: Natural Language
Number Sense Disambiguation Stuart Moore Supervised by: Anna Korhonen (Computer Lab)‏ Sabine Buchholz (Toshiba CRL)‏
Automatic acquisition for low frequency lexical items Nuria Bel, Sergio Espeja, Montserrat Marimon.
SIMS 296a-4 Text Data Mining Marti Hearst UC Berkeley SIMS.
Linguistics Lecture-1: Words Pushpak Bhattacharyya, CSE Department, IIT Bombay 14 June, 2008.
The Parts of Speech nouns verbs adjectives adverbs prepositions interjections conjunctions pronouns.
Word classes and part of speech tagging. Slide 1 Outline Why part of speech tagging? Word classes Tag sets and problem definition Automatic approaches.
Chapter 6 Key Concepts. cognates Words in related languages that developed from the same ancestral root and therefore have a same or similar form across.
1 The acquisition of reference in two-year-olds a cross-linguistic perspective Margot Rozendaal - University of Amsterdam ELA, 9 December 2005, Lyon.
CHILD LANGUAGE Research and further reading. Semantic Roles Roger Brown (1973) Looks at the 2 word stage ( months) and categorises utterances into.
Chapter 3 Language Acquisition: A Linguistic Treatment Jang, HaYoung Biointelligence Laborotary Seoul National University.
Approaches to Teaching and Learning How people learn languages Session 2.
Usage-Based Phonology Anna Nordenskjöld Bergman. Usage-Based Phonology overall approach What is the overall approach taken by this theory? summarize How.
Child Syntax and Morphology
Vocabulary Module 2 Activity 5.
Chapter 3 Morphology Without grammar, little can be conveyed. Without vocabulary, nothing can be conveyed. (David Wilkins ,1972) Morphology refers to.
Words in puddles of sound
Grammar Review.
CSCI 5832 Natural Language Processing
THE TOTAL PHYSICAL RESPONSE METHOD (TPR)
FIRST SEMESTER GRAMMAR
Traditional Grammar VS. Generative Grammar
Chapter Six CIED 4013 Dr. Bowles
Michael C. Frank Stanford University
Presentation transcript:

Hao Wang, Toben Mintz Department of Psychology University of Southern California

The Problem of Learning Syntactical Categories Grammar includes manipulations of lexical items based on their syntactical categories. Learning syntactical categories are fundamental to the acquisition of language.

The Problem of Learning Syntactical Categories Nativist approach Children are innately endowed with the possible syntactical categories. How to map a lexical item to its syntactical category or categories? Empirical approach Children have to figure out the syntactical categories in their target language, and assign categories to lexical items. There is no or little help from syntactical constraints.

Approaches Based on Semantic Categories Grammatical Categories correspond to Semantic/Conceptual Categories (Macnamara, 1972; Bowerman, 1973; Bates & MacWhinney, 1979; Pinker, 1984) object  noun action  verb But what about action, noise, love to think, to know (Maratsos & Chalkley, 1980)

Grammatical Categories from Distributional Analyses Structural Linguistics Grammatical categories defined by similarities of word patterning ( Bloomfield, 1933; Harris, 1951) Maratsos & Chalkley (1980): Distributional learning theory lexical co-occurrence patterns (and morphology and semantics) the cat is on the mat cat, mat

Grammatical Categories from Distributional Analyses Patterns across whole utterances (Cartwright & Brent, 1997) My cat meowed. Your dog slept. Det N X/Y. Bigram co-occurrence patterns (Mintz, Newport, & Bever, 1995, 2002; Redington, Chater & Finch, 1998) the cat is on the mat

Probabilistic Bigram Co-Occurrence Patterns X was - 20% there - 5% is - 30% wants - 15% seeing - 7% … the - 57% a - 25% blue - 0% silly - 5% your - 7% … Y was - 20% has - 30% is - 30% belongs - 2% around - 5% … the - 45% a - 35% blue - 5% silly - 0% your - 10% …

Frequent Frames (Mintz, 2003) Frames are defined as “two jointly occurring words with one word intervening”. “would you put the cans back ?” “you get the nuts.” “you take the chair back. “you read the story to Mommy.” Frame: you_X_the

Sensitivity to Frame-like Units Frames lead to categorization in adults (Mintz, 2002) Fifteen-month-olds are sensitive to frame-like sequences (Gómez & Maye, 2005)

Other Motivation for Frames Verb learning in children can be facilitated by frequent frames (Childers & Tomasello, 2001) Aspects of verb meaning carried by verb frame, linguistically defined (Gleitman, 1991; Gillette, Gleitman, Gleitman, Lederer, 1999; etc.)

Distributional Analyses Using Frequent Frames (Mintz, 2003) Six corpora from CHILDES (MacWhinney, 2000). Analyzed utterances to children under 2;6. Accuracy results averaged over all corpora.

Limitation of the Frequent Frame Analyses Requires two passes through the corpus Step 1, identify the frequent frames by tallying the frame frequency. Step 2, categorizing words using those frames. Tracks the frequency of all frames E.g., approximately frame types in one of the corpora in Mintz (2003).

Goal of current study Provides a psychological plausible model of word categorization Children possesses limited memory and cognitive capacity. Human memory is imperfect. Children may not be able to track all the frames he/she has encountered.

Features of current model It processes input and updates the categorization frames dynamically. Frame is associated with and ranked by a activation value. It has a limited memory buffer for frames. Only stores the most activated 150 frames. It implements a forgetting function on the memory. After processed a new frame, the activation of all frames in the memory decreased by

Child Input Corpora Six corpora from CHILDES (MacWhinney, 2000). Analyzed utterances to children under 2;6. Peter (Bloom, Hood, Lightbown, 1974; Bloom, Lightbown, Hood, 1975) Eve (Brown, 1973) Nina (Suppes, 1974) Naomi (Sachs, 1983) Anne (Theakston, Lieven, Pine, Rowland, 2001) Aran (Theakston et al., 2001) Mean Utterance/Child: ~17,200 MIN: 6,950 ; MAX: 20,857

Procedure The child-directed utterances from each corpus was processed individually Utterances were presented to the model in the order of appearance in the corpus Each utterance was segmented into frames “you read the story to Mommy” you read the read the story the story to story to Mommy

Procedure continued… you read the read the story the story to story to Mommy Memory ActivationFrame you_X_the read_X_story the_X_to story_X_Mommy

Procedure continued… The memory buffer only stores most activated 150 frames. It becomes full very quickly after processing several utterances. Memory ActivationFrame you_X_the read_X_story the_X_to story_X_Mommy to_X_it the_X_on ……

Procedure continued… “you put the” Frame: you_X_the Look up you_X_the frame in the memory Increase the activation of you_X_the frame by 1 Re-rank the memory by activation Memory ActivationFrame you_X_the read_X_story the_X_to story_X_Mommy to_X_it the_X_on ……

Procedure continued… “you have a” Frame: you_X_a Look up you_X_a frame in the memory story_X_Mommy < 1 Remove story_X_Mommy Add you_X_a to memory, set the activation to 1 Re-rank the memory by activation Memory ActivationFrame you_X_the read_X_story the_X_to to_X_it the_X_on story_X_Mommy ……

Procedure continued… A new frame not in memory The activation of all frames in memory are greater than 1 There is no change to the memory. Memory ActivationFrame you_X_the read_X_story the_X_to to_X_it the_X_on story_X_Mommy ……

Evaluating Model Performance Hit: two words from the same linguistic category grouped together False Alarm: two words from different linguistic categories grouped together Upper bound of 1

V ADV V Accuracy Example Hits: 10 False Alarms: 5 Accuracy:

Ten Categories for Accuracy Noun, pronoun Verb, Aux., Copula Adjective Preposition Adverb Determiner Wh-word Negation -- “not” Conjunction Interjection

Averaged accuracy across 6 corpora Accuracy Eve Peter Anne Aran Nina Naomi Average

The Development of Accuracy Accuracy are very high and stable in the entire process

Compare to Frequent Frames After processing about half of the corpus, 70% of frequent frames are in the most activated 45 frames in memory.

#w2 typew2 tokenActivationFrame what_X_you you_X_to you_X_it you_X_a you_X_the are_X_doing what_X_that you_X_me to_X_it would_X_like why_X_you Memory of Final Step of Eve Corpus

Stability of Frames in Memory Big changes of frames in memory in early stage, but become stable after processing 10% of the corpus

Summary After processed the entire corpus, the learning algorithm has identified almost all of the frequent frames by highest activation. Consequently, high accuracy of word categorization is achieved. After processing fewer than half of the utterances, the 45 most activated frames included approximately 70% of frequent frames.

Summary Frames are a robust cue for categorizing words. With limited and imperfect memory, the learning algorithm can identify most frequent frames after processing a relatively small number of utterances. Thus yield a high accuracy of word categorization.