Lexical and Grammatical Inference

AAAI Conferences

Children are facile at both discovering word boundaries and using those words to build higher-level structures in tandem. Current research treats lexical acquisition and grammar induction as two distinct tasks; doing so has led to unreasonable assumptions. State-ofthe-art unsupervised results presuppose a perfectly segmented, noise-free lexicon, while largely ignoring how the lexicon is used. This paper combines both tasks in a novel framework for bootstrapping lexical acquisition and grammar induction.


Meaning to Learn: Bootstrapping Semantics to Infer Syntax

AAAI Conferences

Context-free grammars cannot be identified in the limit from positive examples (Gold 1967), yet natural language grammars are more powerful than context-free grammars and humans learn them with remarkable ease from positive examples (Marcus 1993). Identifiability results for formal languages ignore a potentially powerful source of information available to learners of natural languages, namely, meanings. This paper explores the learnability of syntax (i.e.


On the Relationship Between Lexical Semantics and Syntax for the Inference of Context-Free Grammars

AAAI Conferences

Context-free grammars cannot be identified in the limit from positive examples (Gold 1967), yet natural language grammars are more powerful than context-free grammars and humans learn them with remarkable ease from positive examples (Marcus 1993). Identifiability results for formal languages ignore a potentially powerful source of information available to learners of natural languages, namely, meanings. This paper explores the learnability of syntax (i.e.


Grammatical Inference and the Argument from the Poverty of the Stimulus

AAAI Conferences

Formal results in grammatical inference clearly have some relevance to first language acquisition. Initial formalisations of the problem (Gold 1967) are however inapplicable to this particular situation. In this paper we construct an appropriate formalisation of the problem using a modern vocabulary drawn from statistical learning theory and grammatical inference and looking in detail at the relevant empirical facts. We claim that a variant of the Probably Approximately Correct (PAC) learning framework (Valiant 1984) with positive samples only, modified so it is not completely distribution free is the appropriate choice. Some negative results derived from cryptographic problems (Kearns et al. 1994) appear to apply in this situation but the existence of algorithms with provably good performance (Ron, Singer, & Tishby 1995) and subsequent work, shows how these negative results are not as strong as they initially appear, and that recent algorithms for learning regular languages partially satisfy our criteria. We conclude by speculating about the extension of these results beyond regular languages.


Acquiring Word-Meaning Mappings for Natural Language Interfaces

arXiv.org Artificial Intelligence

This paper focuses on a system, WOLFIE (WOrd Learning From Interpreted Examples), that acquires a semantic lexicon from a corpus of sentences paired with semantic representations. The lexicon learned consists of phrases paired with meaning representations. WOLFIE is part of an integrated system that learns to transform sentences into representations such as logical database queries. Experimental results are presented demonstrating WOLFIE's ability to learn useful lexicons for a database interface in four different natural languages. The usefulness of the lexicons learned by WOLFIE are compared to those acquired by a similar system, with results favorable to WOLFIE. A second set of experiments demonstrates WOLFIE's ability to scale to larger and more difficult, albeit artificially generated, corpora. In natural language acquisition, it is difficult to gather the annotated data needed for supervised learning; however, unannotated data is fairly plentiful. Active learning methods attempt to select for annotation and training only the most informative examples, and therefore are potentially very useful in natural language applications. However, most results to date for active learning have only considered standard classification tasks. To reduce annotation effort while maintaining accuracy, we apply active learning to semantic lexicons. We show that active learning can significantly reduce the number of annotated examples required to achieve a given level of performance.