Share This Author
Incremental Parsing with the Perceptron Algorithm
It is demonstrated that training a perceptron model to combine with the generative model during search provides a 2.1 percent F-measure improvement over the Generative model alone, to 88.8 percent.
Probabilistic Top-Down Parsing and Language Modeling
- Brian Roark
- Computer ScienceInternational Conference on Computational Logic
- 8 May 2001
A lexicalized probabilistic top-down parser is presented, which performs very well, in terms of both the accuracy of returned parses and the efficiency with which they are found, relative to the best broad-coverage statistical parsers.
Spoken Language Derived Measures for Detecting Mild Cognitive Impairment
- Brian Roark, Margaret Mitchell, John-Paul Hosom, Kristy Hollingshead, J. Kaye
- PsychologyIEEE Transactions on Audio, Speech, and Language…
- 1 September 2011
The results indicate that using multiple, complementary measures can aid in automatic detection of MCI, and demonstrate a statistically significant improvement in the area under the ROC curve (AUC) when using automatic spoken language derived features in addition to the neuropsychological test scores.
Discriminative n-gram language modeling
Deriving lexical and syntactic expectation-based measures for psycholinguistic modeling via incremental top-down parsing
- Brian Roark, A. Bachrach, Carlos Cardenas, Christophe Pallier
- LinguisticsConference on Empirical Methods in Natural…
- 6 August 2009
Novel methods for calculating separate lexical and syntactic surprisal measures from a single incremental parser using a lexicalized PCFG and an approximation to entropy measures that would otherwise be intractable to calculate for a grammar of that size are presented.
Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm
This paper compares two parameter estimation methods: the perceptron algorithm, and a method based on conditional random fields (CRFs), which have the benefit of automatically selecting a relatively small feature set in just a couple of passes over the training data.
Generalized Algorithms for Constructing Statistical Language Models
An algorithm for computing efficiently the expected counts of any sequence in a word lattice output by a speech recognizer or any arbitrary weighted automaton is given and a new technique for creating exact representations of n-gram language models by weighted automata is described.
Discriminative Syntactic Language Modeling for Speech Recognition
A reranking model makes use of syntactic features together with a parameter estimation method that is based on the perception algorithm that provides an additional 0.3% reduction in test-set error rate beyond the model of (Roark et al., 2004a; Roark etAl., 2004b).
Unsupervised language model adaptation
Unsupervised language model adaptation, from ASR transcripts, shows an error rate reduction of 3.9% over the unadapted baseline performance, from 28% to 24.1%, using 17 hours of unsupervised adaptation material.