Towards a Robuster Interpretive Parsing

The input data to grammar learning algorithms often consist of overt forms that do not contain full structural descriptions. This lack of information may contribute to the failure of learning. Past work on Optimality Theory introduced Robust Interpretive Parsing (RIP) as a partial solution to this problem. We generalize RIP and suggest replacing the winner candidate with a weighted mean violation of the potential winner candidates. A Boltzmann distribution is introduced on the winner set, and the distribution’s parameter $$T$$ is gradually decreased. Finally, we show that GRIP, the Generalized Robust Interpretive Parsing Algorithm significantly improves the learning success rate in a model with standard constraints for metrical stress assignment.

[1]  Tamás Biró,et al.  Elephants and Optimality Again: SA-OT accounts for pronoun resolution in child language , 2009 .

[2]  P. Boersma.  How we learn variation, optionality and probalility , 1997 .

[3]  Louise Guthrie,et al.  Lexical Disambiguation using Simulated Annealing , 1992, COLING.

[4]  Yaneer Bar-Yam,et al.  Dynamics Of Complex Systems , 2019 .

[5]  P. Smolensky,et al.  Optimality Theory: Constraint Interaction in Generative Grammar , 2004 .

[6]  Chien Yu-Chin,et al.  Children's Knowledge of Locality Conditions in Binding as Evidence for the Modularity of Syntax and Pragmatics , 1990 .

[7]  Diana Apoussidou.  The Tibetan numerals segmentation problem and how virtual learners solve it , 2012 .

[8]  Jason Eisner,et al.  Eecient Generation in Primitive Optimality Theory , 1997 .

[9]  Giorgio Magri,et al.  An online model of the acquisition of phonotactics within Optimality Theory , 2011, CogSci.

[10]  Tamás Biró,et al.  Quadratic Alignment Constraints and Finite State Optimality Theory , 2003 .

[11]  Paul Boersma,et al.  A programme for bidirectional phonology and phonetics and their acquisition and evolution , 2011 .

[12]  Ross Gagliano,et al.  Review of , 2006, UBIQ.

[13]  Paul Boersma,et al.  Some Correct Error-Driven Versions of the Constraint Demotion Algorithm , 2009, Linguistic Inquiry.

[14]  Wolfgang Christian,et al.  Dynamics of Complex Systems (Studies in Nonlinearity) , 1998 .

[15]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[16]  F. Glover,et al.  In Modern Heuristic Techniques for Combinatorial Problems , 1993 .

[17]  Charles D. Yang,et al.  Knowledge and learning in natural language , 2000 .

[18]  Paul Boersma,et al.  Review of Tesar & Smolensky(2000); Learnability in Optimality Theory [Review of: B. Tesar, Smolensky (2000) Learnability in Optimality Theory] , 2003 .

[19]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[20]  Andries W. Coetzee,et al.  Variation as accessing ‘non-optimal’ candidates , 2006, Phonology.

[21]  Alan S. Prince,et al.  Generalized alignment , 1993 .

[22]  Joe Pater.  Gradual Learning and Convergence , 2008, Linguistic Inquiry.

[23]  V. Cerný.  Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm , 1985 .

[24]  Jeroen van de Weijer,et al.  Optimality theory : phonology, syntax, and acquisition , 2000 .

[25]  Tamás Biró,et al.  Finding the right words: implementing optimality theory with simulated annealing , 2006 .

[26]  Bruce Tesar,et al.  A revised version of this paper will appear in the proceedings of CLS 39. Using phonotactics to learn phonological alternations , 1994 .

[27]  Jason Eisner.  Easy and Hard Constraint Ranking in Optimality Theory: Algorithms and Complexity , 2000 .

[28]  Bruce Tesar,et al.  Computational optimality theory , 1996 .

[29]  Mark Johnson,et al.  Learning OT constraint rankings using a maximum entropy model , 2003 .

[30]  Andries W. Coetzee,et al.  What it Means to be a Loser: Non-optimal Candidates in Optimality Theory , 2004 .

[31]  Gerhard Jäger,et al.  Maximum Entropy Models and Stochastic Optimality Theory , 2003 .

[32]  T. Biró,et al.  How to Define Simulated Annealing for Optimality Theory ? , 2005 .

[33]  Paul Boersma,et al.  Some listener-oriented accounts of h-aspiré in French , 2007 .

[34]  P. Boersma,et al.  Empirical Tests of the Gradual Learning Algorithm , 2001, Linguistic Inquiry.

[35]  P. Hendriks,et al.  When Production Precedes Comprehension: An Optimization Approach to the Acquisition of Pronouns , 2006 .

[36]  William J. Turkel.  Learning Phonology: Genetic Algorithms and Yoruba Tongue Root Harmony , 2000 .

[37]  J. McCarthy.  OT constraints are categorical , 2003, Phonology.

[38]  Giorgio Magri,et al.  Convergence of error-driven ranking algorithms* , 2012, Phonology.