All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.

efficient convergence to a correct grammar. We discuss implications for learning from overt data only, as well as other learning issues. We argue that Optimality Theory promotes confluence of the demands of more effective learnability and deeper linguistic explanation.

Speech recognition errors are inevitable in a speech dialog system. This paper presents an error handling method based on correction grammars which recognize the correction utterances which follow a recognition error. Correction grammars are dynamically created from existing grammars and a set

independent probabilistic event detectors to propose candidate detections of low-level features. The outputs of these detectors provide the input stream for a stochastic context-free grammar parsing mechanism. The grammar and parser provide longer range temporal constraints, disambiguate uncertain low

way. We use a corpus of bracketed sentences, called a Treebank, in combination with decision tree building to tease out the relevant aspects of a parse tree that will determine the correct parse of a sentence. This stands in contrast to the usual approach of further grammar tailoring via the usual

Ferris (1999) rejects my case against grammar correction in L2 writing classes (Truscott, 1996) and attempts to build her own case for the practice. This paper responds to her criticisms. I argue that these criticisms are both unfounded and highly selective, leaving large portions of my case unchal

This paper proposes a novel approach to the problem of training classifiers to detect and correct grammar and usage errors in text by selectively introducing mistakes into the training data. When training a classifier, we would like the distribution of examples seen in training to be as similar

. Discriminative training is used to estimate the models, which requires incorrect parses for each sentence in the training data as well as the correct parse. The lexicalized grammar formalism used is Combinatory Categorial Grammar (CCG), and the grammar is automatically extracted from CCGbank, a CCG version

In this paper, we propose two enhance-ments to a statistical machine translation based approach to grammar correction for correcting all error categories. First, we propose tuning the SMT systems to op-timize a metric more suited to the gram-mar correction task (F-β score) rather than

I attempt to perform context-sensitive grammar correction on frequently confused pairs of words. This provides a machine learning problem with a high dimensional space where many factors are irrelevant. I implement a system similar to Winnow-2 to allow for generating a decision hyper-plane while