The amount of readily available online text has reached hundreds of billions of words and continues to grow. Yet for most core natural language tasks, algorithms continue to be optimized, tested and compared after training on corpora consisting of only one million words or less. In this paper, we evaluate the performance of different learning methods on a prototypical natural language disambiguation task, confusion set disambiguation, when trained on orders of magnitude more labeled data than has previously been used. We are fortunate that for this particular application, correctly labeled training data is free. Since this will often not be the case, we examine methods for effectively exploiting very large corpora when labeled data comes at a cost.

This paper describes a new approach to automatically learning linguistic knowledge for spelling correction. A major feature of this approach is the fact that the acquired knowledge is captured in a small set of easily understood rules, as opposed to a large set of opaque features and weights. A perspicuous representation is advantageous in order to best exploit human intuition to understand and improve upon the acquired knowledge of the system.

Previous work demonstrated that Web counts can be used to approximate bigram counts, suggesting that Web-based frequencies should be useful for a wide variety of Natural Language Processing (NLP) tasks. However, only a limited number of tasks have so far been tested using Web-scale data sets. The present article overcomes this limitation by systematically investigating the performance of Web-based models for several NLP tasks, covering both syntax and semantics, both generation and analysis, and a wider range of n-grams and parts of speech than have been previously explored. For the majority of our tasks, we find that simple, unsupervised models perform better when n-gram counts are obtained from the Web rather than from a large corpus. In some cases, performance can be improved further by using backoff or interpolation techniques that combine Web counts and corpus counts. However, unsupervised Web-based models generally fail to outperform supervised state-ofthe-art models trained on smaller corpora. We argue that Web-based models should therefore be used as a baseline for, rather than an alternative to, standard supervised models.

Spelling errors that happen to result in a real word in the lexicon cannot be detected by a conventional spelling checker. We present a method for detecting and correcting many such errors by identifying tokens that are semantically unrelated to their context and are spelling variations of words that would be related to the context. Relatedness to context is determined by a measure of semantic distance initially proposed by Jiang and Conrath (1997). We tested the method on an artificial corpus of errors; it achieved recall of up to 50% and precision of 18 to 25% -- levels that approach practical usability.

Previous work demonstrated that web counts can be used to approximate bigram frequencies, and thus should be useful for a wide variety of NLP tasks. So far, only two generation tasks (candidate selection for machine translation and confusion-set disambiguation) have been tested using web-scale data sets. The present paper investigates if these results generalize to tasks covering both syntax and semantics, both generation and analysis, and a larger range of n-grams. For the majority of tasks, we find that simple, unsupervised models perform better when n-gram frequencies are obtained from the web rather than from a large corpus. However, in most cases, web-based models fail to outperform more sophisticated state-of-theart models trained on small corpora. We argue that web-based models should therefore be used as a baseline for, rather than an alternative to, standard models. 1

Contextual spelling errors are defined as the use of an incorrect, though valid, word in a particular sentence or context. Traditional spelling checkers flag misspelled words, but they do not typically attempt to identify words that are used incorrectly in a sentence. We explore the use of Latent Semantic Analysis for correcting these incorrectly used words and the results are compared to earlier work based on a Bayesian classifier.

This paper describes an automatic, context-sensitive, word-error correction system based on statistical language modeling (SLM) as applied to optical character recognition (OCR) postprocessing.

This paper describes a spelling correction system that functions as part of an intelligent tutor that carries on a natural language dialogue with its users. The process that searches the lexicon is adaptive as is the system filter, to speed up the process. The basis of our approach is the interaction between the parser and the spelling corrector. Alternative correction targets are fed back to the parser, which does a series of syntactic and semantic checks, based on the dialogue context, the sentence context, and the phrase context.

Trigram language models are compressed using a Golomb coding method inspired by the original Unix spell program. Compression methods trade off space, time and accuracy (loss). The proposed HashTBO method optimizes space at the expense of time and accuracy. Trigram language models are normally considered memory hogs, but with HashTBO, it is possible to squeeze a trigram language model into a few megabytes or less. HashTBO made it possible to ship a trigram contextual speller in Microsoft Office 2007.

It has been widely observed that search queries are composed in a very different style from that of the body or the title of a document. Many techniques explicitly accounting for this language style discrepancy have shown promising results for information retrieval, yet a large scale analysis on the extent of the language differences has been lacking. In this paper, we present an extensive study on this issue by examining the language model properties of search queries and the three text streams associated with each web document: the body, the title, and the anchor text. Our information theoretical analysis shows that queries seem to be composed in a way most similar to how authors summarize documents in anchor texts or titles, offering a quantitative explanation to the observations in past work. We apply these web scale n-gram language models to three search query processing (SQP) tasks: query spelling correction, query bracketing and long query segmentation. By controlling the size and the order of different language models, we find that the perplexity metric to be a good accuracy indicator for these query processing tasks. We show that using smoothed language models yields significant accuracy gains for query bracketing for instance, compared to using web counts as in the literature. We also demonstrate that applying web-scale language models can have marked accuracy advantage over smaller ones.