Abstract—Words and phrases acquire meaning from the way they are used in society, from their relative semantics to other words and phrases. For computers, the equivalent of “society ” is “database, ” and the equivalent of “use ” is “a way to search the database.” We present a new theory of similarity between words and phrases based on information distance and Kolmogorov complexity. To fix thoughts, we use the World Wide Web (WWW) as the database, and Google as the search engine. The method is also applicable to other search engines and databases. This theory is then applied to construct a method to automatically extract similarity, the Google similarity distance, of words and phrases from the WWW using Google page counts. The WWW is the largest database on earth, and the context information entered by millions of independent users averages out to provide automatic semantics of useful quality. We give applications in hierarchical clustering, classification, and language translation. We give examples to distinguish between colors and numbers, cluster names of paintings by 17th century Dutch masters and names of books by English novelists, the ability to understand emergencies and primes, and we demonstrate the ability to do a simple automatic English-Spanish translation. Finally, we use the WordNet database as an objective baseline against which to judge the performance of our method. We conduct a massive randomized trial in binary classification using support vector machines to learn categories based on our Google distance, resulting in an a mean agreement of 87 percent with the expert crafted WordNet categories. Index Terms—Accuracy comparison with WordNet categories, automatic classification and clustering, automatic meaning discovery using Google, automatic relative semantics, automatic translation, dissimilarity semantic distance, Google search, Google distribution via page hit counts, Google code, Kolmogorov complexity, normalized compression distance (NCD), normalized information distance (NID), normalized Google distance (NGD), meaning of words and phrases extracted from the Web, parameter-free data mining, universal similarity metric. Ç 1

Statistical measures of word similarity have application in many areas of natural language processing, such as language modeling and information retrieval. We report a comparative study of two methods for estimating word cooccurrence frequencies required by word similarity measures. Our frequency estimates are generated from a terabyte-sized corpus of Web data, and we study the impact of corpus size on the effectiveness of the measures. We base the evaluation on one TOEFL question set and two practice questions sets, each consisting of a number of multiple choice questions seeking the best synonym for a given target word.

The application of frequent patterns in classification appeared in sporadic studies and achieved initial success in the classification of relational data, text documents and graphs. In this paper, we conduct a systematic exploration of frequent pattern-based classification, and provide solid reasons supporting this methodology. It was well known that feature combinations (patterns) could capture more underlying semantics than single features. However, inclusion of infrequent patterns may not significantly improve the accuracy due to their limited predictive power. By building a connection between pattern frequency and discriminative measures such as information gain and Fisher score, we develop a strategy to set minimum support in frequent pattern mining for generating useful patterns. Based on this strategy, coupled with a proposed feature selection algorithm, discriminative frequent patterns can be generated for building high quality classifiers. We demonstrate that the frequent pattern-based classification framework can achieve good scalability and high accuracy in classifying large datasets. Empirical studies indicate that significant improvement in classification accuracy is achieved (up to 12 % in UCI datasets) using the so-selected discriminative frequent patterns. 1.

To enable information integration, schema matching is a critical step for discovering semantic correspondences of attributes across heterogeneous sources. While complex matchings are common, because of their far more complex search space, most existing techniques focus on simple 1:1 matchings. To tackle this challenge, this paper takes a conceptually novel approach by viewing schema matching as correlation mining, for our task of matching Web query interfaces to integrate the myriad databases on the Internet. On this "deep Web," query interfaces generally form complex matchings between attribute groups (e.g., corresponds to name, last name} in the Books domain). We observe that the cooccurrences patterns across query interfaces often reveal such complex semantic relationships: grouping attributes (e.g., last name}) tend to be co-present in query interfaces and thus positively correlated. In contrast, synonym attributes are negatively correlated because they rarely co-occur. This insight enables us to discover complex matchings by a correlation mining approach. In particular, we develop the DCM framework, which consists of data preparation, dual mining of positive and negative correlations, and finally matching selection. Unlike previous correlation mining algorithms, which mainly focus on finding strong positive correlations, our algorithm cares both positive and negative correlations, especially the subtlety of negative correlations, due to its special importance in schema matching. This leads to the introduction of a new correlation measure, H-measure, distinct from those proposed in previous work. We evaluate our approach extensively and the results show good accuracy for discovering complex matchings.

Existing association-rule mining algorithms often rely on the support-based pruning strategy to prune its combinatorial search space. This strategy is not quite effective for data sets with skewed support distributions because they tend to generate many spurious patterns involving items from different support levels or miss potentially interesting low-support patterns. To overcome these problems, we propose the concept of hyperclique pattern, which uses an objective measure called h-confidence to identify strong affinity patterns. We also introduce the novel concept of crosssupport property for eliminating patterns involving items with substantially different support levels. Our experimental results demonstrate the effectiveness of this method for finding patterns in dense data sets even at very low support thresholds, where most of the existing algorithms would break down. Finally, hyperclique patterns also show great promise for clustering items in high dimensional space.

We have found a method to automatically extract the meaning of words and phrases from the world-wide-web using Google page counts. The approach is novel in its unrestricted problem domain, simplicity of implementation, and manifestly ontological underpinnings. The world-wide-web is the largest database on earth, and the latent semantic context information entered by millions of independent users averages out to provide automatic meaning of useful quality. We demonstrate positive correlations, evidencing an underlying semantic structure, in both numerical symbol notations and number-name words in a variety of natural languages and contexts. Next, we demonstrate the ability to distinguish between colors and numbers, and to distinguish between 17th century Dutch painters; the ability to understand electrical terms, religious terms, and emergency incidents; we conduct a massive experiment in understanding WordNet categories; and finally we demonstrate the ability to do a simple automatic English-Spanish translation.

Frequent-pattern mining has been studied extensively on scalable methods for mining various kinds of patterns including itemsets, sequences, and graphs. However, the bottleneck of frequent-pattern mining is not at the efficiency but at the interpretability, due to the huge number of patterns generated by the mining process. In this paper, we examine how to summarize a collection of itemset patterns using only K representatives, a small number of patterns that a user can handle easily. The K representatives should not only cover most of the frequent patterns but also approximate their supports. A generative model is built to extract and profile these representatives, under which the supports of the patterns can be easily recovered without consulting the original dataset. Based on the restoration error, we propose a quality measure function to determine the optimal value of parameter K. Polynomial time algorithms are developed together with several optimization heuristics for efficiency improvement. Empirical studies indicate that we can obtain compact summarization in real datasets.

Abstract not found

The problem of assessing the significance of data mining results on high-dimensional 0–1 data sets has been studied extensively in the literature. For problems such as mining frequent sets and finding correlations, significance testing can be done by, e.g., chi-square tests, or many other methods. However, the results of such tests depend only on the specific attributes and not on the dataset as a whole. Moreover, the tests are more difficult to apply to sets of patterns or other complex results of data mining. In this paper, we consider a simple randomization technique that deals with this shortcoming. The approach consists of producing random datasets that have the same row and column margins with the given dataset, computing the results of interest on the randomized instances, and comparing them against the results on the actual data. This randomization technique can be used to assess the results of many different types of data mining algorithms, such as frequent sets, clustering, and rankings. To generate random datasets with given margins, we use variations of a Markov chain approach, which is based on a simple swap operation. We give theoretical results on the efficiency of different randomization methods, and apply the swap randomization method to several wellknown datasets. Our results indicate that for some datasets the structure discovered by the data mining algorithms is a random artifact, while for other datasets the discovered structure conveys meaningful information.

With ever-increasing amounts of graph data from disparate sources, there has been a strong need for exploiting significant graph patterns with user-specified objective functions. Most objective functions are not antimonotonic, which could fail all of frequency-centric graph mining algorithms. In this paper, we give the first comprehensive study on general mining method aiming to find most significant patterns directly. Our new mining framework, called LEAP(Descending Leap Mine), is developed to exploit the correlation between structural similarity and significance similarity in a way that the most significant pattern could be identified quickly by searching dissimilar graph patterns. Two novel concepts, structural leap search and frequency descending mining, are proposed to support leap search in graph pattern space. Our new mining method revealed that the widely adopted branch-and-bound search in data mining literature is indeed not the best, thus sketching a new picture on scalable graph pattern discovery. Empirical results show that LEAP achieves orders of magnitude speedup in comparison with the state-of-the-art method. Furthermore, graph classifiers built on mined patterns outperform the up-to-date graph kernel method in terms of efficiency and accuracy, demonstrating the high promise of such patterns.