Adding Sentence Types to a Model of Syntactic Category Acquisition

The acquisition of syntactic categories is a crucial step in the process of acquiring syntax. At this stage, before a full grammar is available, only surface cues are available to the learner. Previous computational models have demonstrated that local contexts are informative for syntactic categorization. However, local contexts are affected by sentence-level structure. In this paper, we add sentence type as an observed feature to a model of syntactic category acquisition, based on experimental evidence showing that pre-syntactic children are able to distinguish sentence type using prosody and other cues. The model, a Bayesian Hidden Markov Model, allows for adding sentence type in a few different ways; we find that sentence type can aid syntactic category acquisition if it is used to characterize the differences in word order between sentence types. In these models, knowledge of sentence type permits similar gains to those found by extending the local context.

[1]  Sharon Goldwater,et al.  A role for the developing lexicon in phonetic category acquisition. , 2013, Psychological review.

[2]  Micha Elsner,et al.  Bootstrapping a Unified Model of Lexical and Phonetic Acquisition , 2012, ACL.

[3]  Stephen Crain,et al.  Sometimes children are as good as adults: The pragmatic use of prosody in children’s on-line sentence processing , 2012 .

[4]  Tanel Alumäe,et al.  A Hierarchical Dirichlet Process Model for Joint Part-of-Speech and Morphology Induction , 2012, NAACL.

[5]  Mark Steedman,et al.  A Probabilistic Model of Syntactic and Semantic Acquisition from Child-Directed Utterances and their Meanings , 2012, EACL.

[6]  Walter Daelemans,et al.  Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics , 2012 .

[7]  Malathi Thothathiri,et al.  The Effect of Prosody on Distributional Learning in 12‐ to 13‐Month‐Old Infants , 2012 .

[8]  Mark Steedman,et al.  A Bayesian Mixture Model for PoS Induction Using Multiple Features , 2011, EMNLP.

[9]  J. Tenenbaum,et al.  The learnability of abstract syntactic principles , 2011, Cognition.

[10]  Morten H. Christiansen,et al.  Learning grammatical categories from distributional cues: Flexible frames for language acquisition , 2010, Cognition.

[11]  Grzegorz Chrupala,et al.  Online Entropy-Based Model of Lexical Category Acquisition , 2010, CoNLL.

[12]  Afsaneh Fazly,et al.  An Incremental Bayesian Model for Learning Syntactic Categories , 2008, CoNLL.

[13]  Diane Brentari,et al.  The relationship between early gestures and intonation , 2008 .

[14]  Charles Kemp,et al.  Bayesian models of cognition , 2008 .

[15]  Mark Johnson,et al.  A Bayesian LDA-based model for semi-supervised part-of-speech tagging , 2007, NIPS.

[16]  Thomas L. Griffiths,et al.  A fully Bayesian approach to unsupervised part-of-speech tagging , 2007, ACL.

[17]  Julia Hirschberg,et al.  V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure , 2007, EMNLP.

[18]  M. Meilă.  Comparing clusterings---an information based distance , 2007 .

[19]  Fumitaka Homae,et al.  The right hemisphere of sleeping infant perceives sentential prosody , 2006, Neuroscience Research.

[20]  L. Gerken,et al.  Infants can use distributional cues to form syntactic categories , 2005, Journal of Child Language.

[21]  R. Gómez,et al.  A first step in form-based category abstraction by 12-month-old infants. , 2004, Developmental science.

[22]  Dan Klein,et al.  Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency , 2004, ACL.

[23]  Toben H. Mintz.  Frequent frames as a cue for grammatical categories in child directed speech , 2003, Cognition.

[24]  Alexander Clark,et al.  Combining Distributional and Morphological Information for Part of Speech Induction , 2003, EACL.

[25]  D. Massaro,et al.  Perceiving Prosody from the Face and Voice: Distinguishing Statements from Echoic Questions in English , 2003, Language and speech.

[26]  Heather L. Balog,et al.  Do children produce the melody before the words? A review of developmental intonation research , 2002 .

[27]  G. Pullum,et al.  The Cambridge Grammar of the English Language , 2002 .

[28]  Alexander Clark.  Unsupervised induction of stochastic context-free grammars using distributional clustering , 2001, CoNLL.

[29]  Anna L. Theakston,et al.  The role of performance limitations in the acquisition of verb-argument structure: an alternative account. , 2001, Journal of child language.

[30]  A. D. Dominicis,et al.  Intonation Systems: A Survey of Twenty Languages , 1999 .

[31]  Nick Chater,et al.  Distributional Information: A Powerful Cue for Acquiring Syntactic Categories , 1998, Cogn. Sci..

[32]  T. A. Cartwright,et al.  Syntactic categorization in early language acquisition: formalizing the role of distributional analysis , 1997, Cognition.

[33]  P. Jusczyk,et al.  Infants remember the order of words in a spoken sentence , 1996 .

[34]  Peter W. Jusczyk,et al.  Does sentential prosody help infants organize and remember speech information? , 1994, Cognition.

[35]  Bernard Mérialdo,et al.  Tagging English Text with a Probabilistic Model , 1994, CL.

[36]  Robert L. Mercer,et al.  Class-Based n-gram Models of Natural Language , 1992, CL.

[37]  B. MacWhinney.  The CHILDES project: tools for analyzing talk , 1992 .

[38]  John J. Godfrey,et al.  SWITCHBOARD: telephone speech corpus for research and development , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[39]  A. Fernald,et al.  Prosody and focus in speech to infants and adults , 1991 .

[40]  A. Fernald.  Intonation and Communicative Intent in Mothers' Speech to Infants: Is the Melody the Message?. , 1989 .

[41]  P. Jusczyk,et al.  A precursor of language acquisition in young infants , 1988, Cognition.

[42]  P. Kuhl,et al.  Acoustic determinants of infant preference for motherese speech , 1987 .

[43]  R. Galligan,et al.  Intonation with single words: purposive and grammatical use , 1987, Journal of Child Language.

[44]  C. Trevarthen,et al.  The infant's role in mother–infant communications , 1986, Journal of Child Language.

[45]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[46]  H. Gleitman,et al.  The current status of the motherese hypothesis , 1984, Journal of Child Language.

[47]  D. Stern,et al.  The prosody of maternal speech: infant age and context related changes , 1983, Journal of Child Language.

[48]  D. Stern,et al.  Intonation contours as signals in maternal speech to prelinguistic infants. , 1982 .

[49]  Roger W. Brown,et al.  A First Language: The Early Stages , 1974 .

[50]  Z. Harris.  From Morpheme to Utterance , 1946 .

[51]  Thomas L. Griffiths,et al.  Learners Use Word-Level Statistics in Phonetic Category Acquisition , 2011 .

[52]  Amy Perfors,et al.  Joint acquisition of word order and word reference , 2009 .

[53]  Thomas L. Griffiths,et al.  Learning phonetic categories by learning a lexicon , 2009 .

[54]  P Taylor,et al.  Intonation and dialogue context as constraints for speech recognition , 1998 .

[55]  A. Fernald,et al.  Intonation and communicative intent in mothers' speech to infants: is the melody the message? , 1989, Child development.

[56]  M. Maratsos,et al.  The internal language of children's syntax : The ontogenesis and representation of syntactic categories , 1980 .

[57]  H. Gleitman,et al.  Mother, Id rather do it myself: Some effects and non-effects of maternal speech style , 1977 .

[58]  S. Waxman,et al.  Please Scroll down for Article Journal of Cognition and Development Mapping Words to the World in Infancy: Infants' Expectations for Count Nouns and Adjectives , 2022 .