We study the class of relations implemented by nested word to word transducers (also known as visibly pushdown transducers). We show that any such relation can be uniformized by a functional relation from the same class, implemented by an unambiguous transducer. We give an exponential upper bound on the state complexity of the uniformization, improving a previous doubly exponential upper bound....

The objective of this project is to analyze the performance of a class-based language model and compare it to the performance of traditional n-gram language models. Class-based language models are well-studied, as is the use of clustering to learn classes of words. However, it seems fairly standard across the literature to use hard-clustering i.e. assign each word to a single class and then to ...

Event-related potentials (ERPs) were recorded as subjects read semantically meaningful, syntactically legal but nonsensical and random word strings. The constraints imposed by formal sentence structure alone did not reduce the amplitude of the N400 component elicited by open-class words, whereas semantic constraints did. Semantic constraints also eliminated the word-frequency effect of a larger...

An automatic word classi cation system has been designed which processes word unigram and bigram frequency statistics extracted from a corpus of natural language utterances. The system implements a type of simulated annealing which employs an average class mutual information metric. Resulting classi cations are hierarchical, allowing variable class granularity. Words are represented as structur...

The main disadvantage of collocation-based word sense disambiguation is that the recall is low, with relatively high precision. How to improve the recall without decrease the precision? In this paper, we investigate a word-class approach to extend the collocation list which is constructed from the manually sense-tagged corpus. But the word classes are obtained from a larger scale corpus which i...