Eric Bloedorn

Summarizing similarities and differences among related documents

In many modern information retrieval applications, a common problem which arises is the existence of multiple documents covering similar information, as in the case of multiple news stories about an event or a sequence of events. A particular challenge for text summarization is to be able to summarize the similarities and differences in information content among these documents. The approach described here exploits the results of recent progress in information extraction to represent salient units of text and their relationships. By exploiting meaningful relations between units based on an analysis of text cohesion and the context in which the comparison is desired, the summarizer can pinpoint similarities and differences, and align text segments. In evaluation experiments, these techniques for exploiting cohesion relations result in summaries which (i) help users more quickly complete a retrieval task (ii) result in improved alignment accuracy over baselines, and (iii) improve identification of topic-relevant similarities and differences.

Data-driven constructive induction in AQ17-PRE: A method and experiments

A method is presented for constructive induction, in which new attributes are constructed as various functions of original attributes. Such a method is called data-driven constructive induction, because new attributes are derived from an analysis of the data (examples) rather than the generated rules. Attribute construction and rule generation are repeated until a termination condition, such as the satisfaction of a rule quality measure, is met. The first step of this method, the generation of new attributes, has been implemented in AQ17-PRE. Initial experiments with AQ17-PRE have shown that it leads to an improvement of the learned rules in terms of both their simplicity and their accuracy on testing examples.<<ETX>>

Using NLP for Machine Learning of User Profiles

As more information becomes available electronically, tools for finding information of interest to users becomes increasingly important. The goal of the research described here is to build a system for generating comprehensible user profiles that accurately capture user interest with minimum user interaction, The research focuses on the importance of a suitable generalization hierarchy and representation for learning profiles which are predictively accurate and comprehensible. In our experiments we evaluated both traditional features based on weighted term vectors as well as subject features corresponding to categories which could be drawn from a thesaurus. Our experiments, conducted in the context of a content-based profiling system for on-line newspapers on the World Wide Web the IDD News Browser, demonstrate the importance of a generalization hierarchy and the promise of combining natural language processing techniques with machine learning ML to address an information retrieval IR problem.

Data-Driven Constructive Induction: A Methodology and its Applications

Constructive induction, viewed generally, is a process combining two intertwined searches: first for the best representation space, and second for the best hypothesis in that space. The first search employs operators for improving the initial representation space, such as those for generating new attributes, selecting best attributes among the given ones, and abstracting attributes. In the methodology presented, these operators are chosen on the basis of an analysis of the training data, hence the term data-driven. The second search employs an AQ inductive learning method to the examples projected at each iteration into the newly modified representation space. The aim of the second search is to determine a generalized description of examples. Experimental applications of the methodology to text categorization and natural scene interpretation demonstrate a significant practical utility of the proposed methodology.

The AQ17-DCI System for Data-Driven Constructive Induction and its Application to the Analysis of World Economics

Constructive induction divides the problem of learning an inductive hypothesis into two intertwined searches: one-for the “best” representation space, and two-for the “best” hypothesis in that space. In datadriven constructive induction (DCI), a learning system searches for a better representation space by analyzing the input examples (data). The presented datadriven constructive induction method combines an AQ-type learning algorithm with two classes of representation space improvement operators: constructors, and destructors. The implemented system, AQ17-DCI, has been experimentally applied to a GNP prediction problem using a World Bank database. The results show that decision rules learned by AQ17-DCI outperformed the rules learned in the original representation space both in predictive accuracy and rule simplicity.