this paper. Finally, thanks to Stan Chen and Roni Rosenfeld: our derivation for Exponential priors closely follows the text of their derivation for Gaussian priors.

We augment naive Bayes models with statistical n-gram language models to address shortcomings of the standard naive Bayes text classifier. The result is a generalized naive Bayes classifier

This thesis is about modeling, analyzing, and predicting errorful behavior in large vocabulary continuous speech recognition systems. Because today's state-of-the-art recognizers are not designed to be situated naturally in an error feedback loop, they are ill-positioned for inclusion in multi-modal interfaces, multi-media databases, and other interesting applications. I make improvements to the current approach to predicting and analyzing error behaviors, which is currently based only on the measurement ofword error rate. The speech recognizer's functionality is extended to include con dence annotations, which are \meta-level " markings that indicate how certain the recognizer is that it has decoded its input correctly. This is accomplished by feeding externally de ned error conditions back to the recognizer. Error feedback enables the construction of statistical models that map measurements of the recognizer's internal states and behaviors to externally de ned error conditions.

The most widely-used evaluation metric for language models for speech recognition is the perplexity of test data. While perplexities can be calculated efficiently and without access to a speech recognizer, they often do not correlate well with speech recognition word-error rates. In this research, we attempt to find a measure that like perplexity is easily calculated but which better predicts speech recognition performance. We investigate two approaches; first, we attempt to extend perplexity by using similar measures that utilize information about language models that perplexity ignores. Second, we attempt to imitate the word-error calculation without using a speech recognizer by artificially generating speech recognition lattices. To test our new metrics, we have built over thirty varied language models. We find that perplexity correlates with word-error rate remarkably well when only considering n-gram models trained on in-domain data. When considering other types of models, our novel metrics are superior to perplexity for predicting speech recognition performance. However, we conclude that none of these measures predict word-error rate sufficiently accurately to be effective tools for language model evaluation in speech recognition.

Abstract not found

We propose a novel method for using the World Wide Web to acquire trigram estimates for statistical language modeling. We submit an N-gram as a phrase query to web search engines. The search engines return the number of web pages containing the phrase, from which the N-gram count is estimated. The N-gram counts are then used to form web-based trigram probability estimates. We discuss the properties of such estimates, and methods to interpolate them with traditional corpus based trigram estimates. We show that the interpolated models improve speech recognition word error rate significantly over a small test set. 1.

We present a modular system for detection and correction of errors made by nonnative (English as a Second Language = ESL) writers. We focus on two error types: the incorrect use of determiners and the choice of prepositions. We use a decisiontree approach inspired by contextual spelling systems for detection and correction suggestions, and a large language model trained on the Gigaword corpus to provide additional information to filter out spurious suggestions. We show how this system performs on a corpus of non-native English text and discuss strategies for future enhancements. 1

It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the parallel corpus. The savings can be quite substantial (up to 90%) and cause no reduction in BLEU score. In some cases, an improvement in BLEU is obtained at the same time although the effect is less pronounced if state-of-the-art phrasetable smoothing is employed.

We discuss different strategies for smoothing the phrasetable in Statistical MT, and give results over a range of translation settings. We show that any type of smoothing is a better idea than the relativefrequency estimates that are often used. The best smoothing techniques yield consistent gains of approximately 1 % (absolute) according to the BLEU metric. 1

N-gram language models are frequently used by the speech recognition systems to constrain and guide the search. N-gram models use only the last N-1 words to predict the next word. Typical values of N that are used range from 2-4. N-gram language models thus lack the long-term context information. We show that the predictive power of the N-gram language models can be improved by using long-term context information about the topic of discussion. We use information retrieval techniques to generalize the available context information for topic-dependent language modeling. We demonstrate the effectiveness of this technique by performing experiments on the Wall Street Journal text corpus, which is a relatively difficult task for topic-dependent language modeling since the text is relatively homogeneous. The proposed method can reduce the perplexity of the baseline language model by 37%, indicating the predictive power of the topic-dependent language model. 1.