Clustering is the division of data into groups of similar objects. In clustering, some details are disregarded in exchange for data simplification. Clustering can be viewed as a data modeling technique that provides for concise summaries of the data. Clustering is therefore related to many disciplines and plays an important role in a broad range of applications. The applications of clustering usually deal with large datasets and data with many attributes. Exploration of such data is a subject of data mining. This survey concentrates on clustering algorithms from a data mining perspective.

A Survey of Clustering Data Mining Techniques

This paper presents the results of an experimental study of some common document clustering techniques. In particular, we compare the two main approaches to document clustering, agglomerative hierarchical clustering and K-means. (For K-means we used a “standard” K-means algorithm and a variant of K-means, “bisecting” K-means.) Hierarchical clustering is often portrayed as the better quality clustering approach, but is limited because of its quadratic time complexity. In contrast, K-means and its variants have a time complexity which is linear in the number of documents, but are thought to produce inferior clusters. Sometimes K-means and agglomerative hierarchical approaches are combined so as to “get the best of both worlds.” However, our results indicate that the bisecting K-means technique is better than the standard K-means approach and as good or better than the hierarchical approaches that we tested for a variety of cluster evaluation metrics. We propose an explanation for these results that is based on an analysis of the specifics of the clustering algorithms and the nature of document

/pdf/a-comparison-of-document-clustering-techniques-3npklskhy9.pdf

A Comparison of Document Clustering Techniques

Traditionally, Information Extraction (IE) has focused on satisfying precise, narrow, pre-specified requests from small homogeneous corpora (e.g., extract the location and time of seminars from a set of announcements). Shifting to a new domain requires the user to name the target relations and to manually create new extraction rules or hand-tag new training examples. This manual labor scales linearly with the number of target relations.

This paper introduces Open IE (OIE), a new extraction paradigm where the system makes a single data-driven pass over its corpus and extracts a large set of relational tuples without requiring any human input. The paper also introduces TEXTRUNNER, a fully implemented, highly scalable OIE system where the tuples are assigned a probability and indexed to support efficient extraction and exploration via user queries.

We report on experiments over a 9,000,000 Web page corpus that compare TEXTRUNNER with KNOWITALL, a state-of-the-art Web IE system. TEXTRUNNER achieves an error reduction of 33% on a comparable set of extractions. Furthermore, in the amount of time it takes KNOWITALL to perform extraction for a handful of pre-specified relations, TEXTRUNNER extracts a far broader set of facts reflecting orders of magnitude more relations, discovered on the fly. We report statistics on TEXTRUNNER's 11,000,000 highest probability tuples, and show that they contain over 1,000,000 concrete facts and over 6,500,000 more abstract assertions.

/pdf/open-information-extraction-from-the-web-4hdvlsd9yu.pdf

Open information extraction from the web

Because many animal species are undescribed, and because the identification of known species is often difficult, interim taxonomic nomenclature has often been used in biodiversity analysis. By assigning individuals to presumptive species, called operational taxonomic units (OTUs), these systems speed investigations into the patterning of biodiversity and enable studies that would otherwise be impossible. Although OTUs have conventionally been separated through their morphological divergence, DNA-based delineations are not only feasible, but have important advantages. OTU designation can be automated, data can be readily archived, and results can be easily compared among investigations. This study exploits these attributes to develop a persistent, species-level taxonomic registry for the animal kingdom based on the analysis of patterns of nucleotide variation in the barcode region of the cytochrome c oxidase I (COI) gene. It begins by examining the correspondence between groups of specimens identified to a species through prior taxonomic work and those inferred from the analysis of COI sequence variation using one new (RESL) and four established (ABGD, CROP, GMYC, jMOTU) algorithms. It subsequently describes the implementation, and structural attributes of the Barcode Index Number (BIN) system. Aside from a pragmatic role in biodiversity assessments, BINs will aid revisionary taxonomy by flagging possible cases of synonymy, and by collating geographical information, descriptive metadata, and images for specimens that are likely to belong to the same species, even if it is undescribed. More than 274,000 BIN web pages are now available, creating a biodiversity resource that is positioned for rapid growth.

/pdf/a-dna-based-registry-for-all-animal-species-the-barcode-190e3osdti.pdf

A DNA-Based Registry for All Animal Species: The Barcode Index Number (BIN) System

https://www.stat.washington.edu/mmp/Papers/compare-jmva-revised.pdf

Comparing clusterings---an information based distance

Clustering is a powerful technique for large-scale topic discovery from text. It involves two phases: first, feature extraction maps each document or record to a point in high-dimensional space, then clustering algorithms automatically group the points into a hierarchy of clusters. We describe an unsupervised, near-linear time text clustering system that offers a number of algorithm choices for each phase. We introduce a methodology for measuring the quality of a cluster hierarchy in terms of FMeasure, and present the results of experiments comparing different algorithms. The evaluation considers some feature selection parameters (tfidfand feature vector length) but focuses on the clustering algorithms, namely techniques from Scatter/Gather (buckshot, fractionation, and split/join) and kmeans. Our experiments suggest that continuous center adjustment contributes more to cluster quality than seed selection does. It follows that using a simpler seed selection algorithm gives a better time/quality tradeoff. We describe a refinement to center adjustment, “vector average damping,” that further improves cluster quality. We also compare the near-linear time algorithms to a group average greedy agglomerative clustering algorithm to demonstrate the time/quality tradeoff quantitatively.

/pdf/fast-and-effective-text-mining-using-linear-time-document-3w7tfdcpld.pdf

Fast and effective text mining using linear-time document clustering

We present an application of kernel methods to extracting relations from unstructured natural language sources. We introduce kernels defined over shallow parse representations of text, and design efficient algorithms for computing the kernels. We use the devised kernels in conjunction with Support Vector Machine and Voted Perceptron learning algorithms for the task of extracting person-affiliation and organization-location relations from text. We experimentally evaluate the proposed methods and compare them with feature-based learning algorithms, with promising results.

/pdf/kernel-methods-for-relation-extraction-46eoz4g86s.pdf

Kernel methods for relation extraction

/pdf/kernel-methods-for-relation-extraction-8n9ons765o.pdf

Kernel Methods for Relation Extraction

This paper reports on a large-scale, end-to-end relation and event extraction system. At present, the system extracts a total of 100 types of relations and events, which represents a much wider coverage than is typical of extraction systems. The system consists of three specialized pattern-based tagging modules, a high-precision coreference resolution module, and a configurable template generation module. We report quantitative evaluation results, analyze the results in detail, and discuss future directions.

REES: A Large-Scale Relation and Event Extraction System

A system and method is provided for automatically identifying information in unstructured text and extracting data representing certain types of information from the text to produce a structured set of templates with the extracted data. The newly structured data is then delivered to different types of user devices in accordance stored criteria associated with each type of device.

Chinatsu Aone

Papers

Fast and effective text mining using linear-time document clustering

Kernel methods for relation extraction

Kernel Methods for Relation Extraction

REES: A Large-Scale Relation and Event Extraction System

Content distribution system and method