We present an algorithm for unsupervised induction of labeled parse trees. The algorithm has three stages: bracketing, initial labeling, and label clustering. Bracketing is done from raw text using an unsupervised incremental parser. Initial labeling is done using a merging model that aims at minimizing the grammar description length. Finally, labels are clustered to a desired number of labels using syntactic features extracted from the initially labeled trees. The algorithm obtains 59% labeled f-score on the WSJ10 corpus, as compared to 35 % in previous work, and substantial error reduction over a random baseline. We report results for English, German and Chinese corpora, using two label mapping methods and two label set sizes. 1

We present the Darwinised Data-Oriented Parsing algorithm, an incremental, dy-namic form of Data-Oriented Parsing, in which exemplars are used as replicators, subject to a selection pressure towards gen-eralisability. 1 1

Abstract not found

Abstract. Child language acquisition, one of Nature’s most fascinating phenomena, is to a large extent still a puzzle. Experimental evidence seems to support the view that early language is highly formulaic, consisting for the most part of frozen items with limited productivity. Fairly quickly, however, children find patterns in the ambient language and generalize them to larger structures, in a process that is not yet well understood. Computational models of language acquisition can shed interesting light on this process. This paper surveys various works that address language learning from data; such works are conducted in different fields, including psycholinguistics, cognitive science and computer science, and we maintain that knowledge from all these domains must be consolidated in order for a well-informed model to emerge. We identify the commonalities and differences between the various existing approaches to language learning, and specify desiderata for future research that must be considered by any plausible solution to this puzzle. 1

Evaluating automatic annotation: automatically detecting and enriching instances of the dative alternation

Abstract not found