Open AccessJournal Article
Learning trees from strings: a strong learning algorithm for some context-free grammars
TL;DR: This work takes as its starting point a simple learning algorithm for substitutable context-free languages, based on principles of distributional learning, and modify it so that it will converge to a canonical grammar for each language.
read more
Abstract: Standard models of language learning are concerned with weak learning: the learner, receiving as input only information about the strings in the language, must learn to generalise and to generate the correct, potentially infinite, set of strings generated by some target grammar. Here we define the corresponding notion of strong learning: the learner, again only receiving strings as input, must learn a grammar that generates the correct set of structures or parse trees. We formalise this using a modification of Gold's identification in the limit model, requiring convergence to a grammar that is isomorphic to the target grammar. We take as our starting point a simple learning algorithm for substitutable context-free languages, based on principles of distributional learning, and modify it so that it will converge to a canonical grammar for each language. We prove a corresponding strong learning result for a subclass of context-free grammars.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
One model for the learning of language
TL;DR: The authors showed that a domain general learning setup, originally developed in cognitive psychology to model rule learning, is able to acquire key pieces of natural language from relatively few examples of sentences, highlighting some features of language and language acquisition that may arise from general cognitive processes.
37
Musical Syntax II: Empirical Perspectives
Marcus T. Pearce,Martin Rohrmeier +1 more
- 01 Jan 2018
TL;DR: The first goal here is to review empirical research on computational modeling of musical structure from a syntactic point of view, and survey research on processing of musical syntax from the perspective of computational modeling, experimental psychology and cognitive neuroscience.
22
•Proceedings Article
Very efficient learning of structured classes of subsequential functions from positive data
Adam Jardine,Jane Chandlee,Rémi Eyraud,Jeffrey Heinz +3 more
- 30 Aug 2014
TL;DR: A new algorithm is presented that can identify in polynomial time and data using positive examples any class of subsequential functions that share a particular nitestate structure and allows for the exact learning of partial functions.
•Proceedings Article
Proceedings of the 13th Meeting on the Mathematics of Language (MoL 13)
András Kornai,Marco Kuhlmann +1 more
- 01 Jan 2013
TL;DR: This volume marks a time when the computational and the theoretical linguistics camps together again, and direct computational concerns such as machine translation, decoding, and complexity are now clearly seen as belonging to the core focus of the field.
14
Grammatical Inference of PCFGs Applied to Language Modelling and Unsupervised Parsing
TL;DR: The analysis shows that the type of grammars induced by the algorithm can potentially outperform the state-of-the-art in unsupervised parsing on the WSJ10 corpus and are, in theory, capable of modelling context-free features of natural language syntax.
13
References
Language identification in the limit
TL;DR: It was found that theclass of context-sensitive languages is learnable from an informant, but that not even the class of regular languages is learningable from a text.
3.8K
•Book
A mathematical introduction to logic
Herbert B. Enderton
- 01 Jan 1972
TL;DR: A comparison of first- and second-order logic in the case of SETs shows that the former is more likely to be correct and the latter is less likely.
2.6K
•Proceedings Article
A brief introduction to boosting
Robert E. Schapire
- 31 Jul 1999
TL;DR: The boosting algorithm AdaBoost is introduced, and the underlying theory of boosting is explained, including an explanation of why boosting often does not suffer from overfitting.
•Book
Formal Principles of Language Acquisition
Kenneth Wexler,Peter W. Culicover +1 more
- 01 Jan 1980
TL;DR: The authors of this book have developed a rigorous and unified theory that opens the study of language learnability to discoveries about the mechanisms of language acquisition in human beings and has important implications for linguistic theory, child language research, and the philosophy of language.
1.4K