We address the problem of predicting a word from previous words in a sample of text. In particular, we discuss n-gram models based on classes of words. We also discuss several statistical algorithms for assigning words to classes based on the frequency of their co-occurrence with other words. We find that we are able to extract classes that have the flavor of either syntactically based groupings or semantically based groupings, depending on the nature of the underlying statistics.

Class-based n -gram models of natural language

We survey the current techniques to cope with the problem of string matching that allows errors. This is becoming a more and more relevant issue for many fast growing areas such as information retrieval and computational biology. We focus on online searching and mostly on edit distance, explaining the problem and its relevance, its statistical behavior, its history and current developments, and the central ideas of the algorithms and their complexities. We present a number of experiments to compare the performance of the different algorithms and show which are the best choices. We conclude with some directions for future work and open problems.

/pdf/a-guided-tour-to-approximate-string-matching-22fowlmq5b.pdf

A guided tour to approximate string matching

Ontologies tend to be found everywhere. They are viewed as the silver bullet for many applications, such as database integration, peer-to-peer systems, e-commerce, semantic web services, or social networks. However, in open or evolving systems, such as the semantic web, different parties would, in general, adopt different ontologies. Thus, merely using ontologies, like using XML, does not reduce heterogeneity: it just raises heterogeneity problems to a higher level. Euzenat and Shvaikos book is devoted to ontology matching as a solution to the semantic heterogeneity problem faced by computer systems. Ontology matching aims at finding correspondences between semantically related entities of different ontologies. These correspondences may stand for equivalence as well as other relations, such as consequence, subsumption, or disjointness, between ontology entities. Many different matching solutions have been proposed so far from various viewpoints, e.g., databases, information systems, and artificial intelligence. The second edition of Ontology Matching has been thoroughly revised and updated to reflect the most recent advances in this quickly developing area, which resulted in more than 150 pages of new content. In particular, the book includes a new chapter dedicated to the methodology for performing ontology matching. It also covers emerging topics, such as data interlinking, ontology partitioning and pruning, context-based matching, matcher tuning, alignment debugging, and user involvement in matching, to mention a few. More than 100 state-of-the-art matching systems and frameworks were reviewed. With Ontology Matching, researchers and practitioners will find a reference book that presents currently available work in a uniform framework. In particular, the work and the techniques presented in this book can be equally applied to database schema matching, catalog integration, XML schema matching and other related problems. The objectives of the book include presenting (i) the state of the art and (ii) the latest research results in ontology matching by providing a systematic and detailed account of matching techniques and matching systems from theoretical, practical and application perspectives.

Ontology Matching

Classic IR (information retrieval) is inherently predicated on users searching for information, the so-called "information need". But the need behind a web search is often not informational -- it might be navigational (give me the url of the site I want to reach) or transactional (show me sites where I can perform a certain transaction, e.g. shop, download a file, or find a map). We explore this taxonomy of web searches and discuss how global search engines evolved to deal with web-specific needs.

/pdf/a-taxonomy-of-web-search-1c1wfauugs.pdf

A taxonomy of web search

Research aimed at correcting words in text has focused on three progressively more difficult problems:(1) nonword error detection; (2) isolated-word error correction; and (3) context-dependent work correction. In response to the first problem, efficient pattern-matching and n-gram analysis techniques have been developed for detecting strings that do not appear in a given word list. In response to the second problem, a variety of general and application-specific spelling correction techniques have been developed. Some of them were based on detailed studies of spelling error patterns. In response to the third problem, a few experiments using natural-language-processing tools or statistical-language models have been carried out. This article surveys documented findings on spelling error patterns, provides descriptions of various nonword detection and isolated-word error correction techniques, reviews the state of the art of context-dependent word correction techniques, and discusses research issues related to all three areas of automatic error correction in text.

Techniques for automatically correcting words in text

The method described assumes that a word which cannot be found in a dictionary has at most one error, which might be a wrong, missing or extra letter or a single transposition. The unidentified input word is compared to the dictionary again, testing each time to see if the words match—assuming one of these errors occurred. During a test run on garbled text, correct identifications were made for over 95 percent of these error types.

A technique for computer detection and correction of spelling errors

Some mistakes in spelling and typing produce correct words, such as typing “fig” when “fog” was intended. These errors are undetectable by traditional spelling correction techniques. In this paper we present a statistical technique capable of detecting and correcting some of these errors when they occur in sentences. Experimental results show that this technique is capable of detecting 76% of simple spelling errors and correcting 73%.

Context based spelling correction

It is generally agreed that natural language database query systems need to be tailored for each application in which they are used. This process, often called customization , involves, among other things, specification of the domain vocabulary and the grammatical properties of that vocabulary. In a previous paper, techniques for automatically generating domain vocabularies from large text collections were discussed. This paper is a continuation of that line of research, focusing on the problem of generating multi-word vocabulary terms (specifically pairs). It also discusses some of the statistical issues associated with word co-occurrences likely to be of use in a natural language interface for the application in question. Most importantly, an attempt is made to provide a more objective evaluation of the selection procedures used. Absent substantial experimentation with subjects using a working query system, all evaluation is necessarily subjective. This paper uses a surrogate for experimentation by relying on pre-existing dictionaries as indicators of domain relevance.

Generating and evaluating domain-oriented multi-word terms from texts

A text categorization method automatically classifies electronic documents by developing a single pooled dictionary of words for a sample set of documents, and then generating a decision tree model, based on the pooled dictionary, for classifying new documents. Adaptive resampling techniques are applied to improve the accuracy of the decision tree model.

Method for improvement accuracy of decision tree based text categorization

A method of automatically labeling of unlabeled text data can be practiced independent of human intervention, but that does not preclude manual intervention. The method can be used to extract relevant features of unlabeled text data for a keyword search. The method of automated labeling of unlabeled text data uses a document collection as a reference answer set. Members of the answer set are converted to vectors representing centroids of unknown groups of unlabeled text data. Unlabeled text data are clustered relative to the centroids by a nearest neighbor algorithm and the ID of the relevant answer is assigned to all documents in the cluster. At this point in the process, a supervised machine learning algorithm is trained on labeled data, and a classifier for assigning labels to new text data is output. Alternatively, a feature extraction algorithm may be run on classes generated by the step of clustering, and search features output which index the unlabeled text data.

Fred J. Damerau

Papers

A technique for computer detection and correction of spelling errors

Context based spelling correction

Generating and evaluating domain-oriented multi-word terms from texts

Method for improvement accuracy of decision tree based text categorization

Automatic labeling of unlabeled text data