This paper describes RESOLVE, a s>stem that uses decision trees to learn how to classify coreferent phrases in the domain of business joint ventures An experiment is presented in which the performance of RESOLVE is compared to the performance of a manually engineered set of rules for the same task The results show that decision trees achieve higher performance than the rules in two of three evaluation metrics developed for the coreference task In addition to achieving better performance than the rules, RESOLVE provides a framework that facilitates the exploration of the types of knowledge that are useful for solving the coreference problem

This paper describes a cross-disciplinary extension of previous work on inferring the meanings of unknown verbs from context. In earlier work, a computational model was developed to incrementally infer meanings while processing texts in an information extraction task setting. In order to explore the space of possible predictors that the system could use to infer verb meanings, we performed a statistical analysis of the corpus that had been used to test the computational system. There were various syntactic and semantic features of the verbs that were significantly diagnostic in determining verb meaning. We also evaluated human performance at inferring the verb in the same set of sentences. The overall number of correct predictions for humans was quite similar to that of the computational system, but humans had higher precision scores. The paper concludes with a discussion of the implications of these statistical and experimental findings for future computational work. Introduction Ver...

This dissertation presents a new approach to solving the coreference resolution problem for a natural language processing (NLP) task known as information extraction. It describes a new system, named resolve, that uses machine learning techniques to determine when two phrases in a text co-refer, i.e., refer to the same thing. Resolve can be used as a component within an information extraction system -- a system that extracts information automatically from a corpus of texts that all focus on the same topic area -- or it can be used as a stand-alone system to evaluate the relative contribution of different types of knowledge to the coreference resolution process. Resolve represents an improvement over previous approaches to the coreference resolution problem, in that it uses a machine learning algorithm to handle some of the work that had previously been performed manually by a know...

Recent work on ontology-based Information Extraction (IE) has tried to make use of knowledge from the target ontology in order to improve semantic annotation results. However, very few approaches exploit the ontology structure itself, and those that do so, have some limitations. This paper introduces a hierarchical learning approach for IE, which uses the target ontology as an essential part of the extraction process, by taking into account the relations between concepts. The approach is evaluated on the largest available semantically annotated corpus. The results demonstrate clearly the benefits of using knowledge from the ontology as input to the information extraction process. We also demonstrate the advantages of our approach over other state-of-the-art learning systems on a commonly used benchmark dataset.

This paper presents a method for enabling users to specialize an information extraction system to satisfy their particular needs. The method allows the user to man- ually demonstrate the creation of seman- tic nodes and transitions while ecanning a sample text article using a graphical user interface. On the basis of such examples, the system creates rules that translate text to semantic nets; then it generalizes these rules so that they can apply to a broad class of text instead of only the training articles.

A corpus-based statistical Generalization Tree model is described to achieve rule optimization for the information extraction task. First, the user creates specific rules for the target information from the sample articles through a training interface. Second, WordNet is applied to generalize noun entities in the specific rules. The degree of generalization is adjusted to fit the user's needs by use of the statistical Generalization ree mode]. Finally, the optimally generalized rules are applied to scan new information. The results of experiment demonstrate the applicability of our Generalization Tree method.

This paper describes WAVE, a fully automatic, incremental induction algorithm for learning information extraction rules. Unlike traditional batch learners, WAVE learns from a stream of training instances, not a set. WAVE overcomes the inherent problems of incremental operation by maintaining a generalization hierarchy of rules. Use of a hierarchy allows similar rules to be found e#ciently, provides a natural bound on generalization, enables recall#precision trade-o#s without retraining, and speeds extraction since all rules need not be applied to an instance. Finally, because the reliability of rule predictions are continually updated throughout storage, the hierarchy can be used for extraction at any time. Experiments show that WAVE performs as well as CRYSTAL, a related batch algorithm, in twovery di#erent extraction domains. WAVE is signi#- cantly faster in a simulated incremental application setting. Introduction As the Internet continues to grow at an astonish...

Abstract. Business intelligence requires the collecting and merging of information from many different sources, both structured and unstructured, in order to analyse for example financial risk, operational risk factors, follow trends and perform credit risk management. While traditional data mining tools make use of numerical data and cannot easily be applied to knowledge extracted from free text, traditional information extraction is either not adapted for the financial domain, or does not address the issue of information integration: the merging of information from different kinds of sources. We describe here the development of a system for content mining using domain ontologies, which enables the extraction of relevant information to be fed into models for analysis of financial and operational risk and other business intelligence applications such as company intelligence, by means of the XBRL standard. The results so far are of extremely high quality, due to the implementation of primarily high-precision rules.

Abstract. Business Intelligence (BI) requires the acquisition and aggregation of key pieces of knowledge from multiple sources in order to provide valuable information to customers or feed statistical BI models and tools. The massive amount of information available to business analysts makes information extraction and other natural language processing tools key enablers for the acquisition and use of that semantic information. We describe the application of ontology-based extraction and merging in the context of a practical e-business application for the EU MUSING Project where the goal is to gather international company intelligence and country/region information. The results of our experiments so far are very promising and we are now in the process of building a complete end-to-end solution.

Financial operators have today access to an extremely large amount of data, both quantitative and qualitative, real-time or historical and can use this information to support their decision-making process. Quantitative data are largely processed by automatic computer programs, often based on artificial intelligence techniques, that produce quantitative analysis, such as historical price analysis or technical analysis of price behaviour. Differently, little progress has been made in the processing of qualitative data, which mainly consists of financial news articles from financial newspapers or on-line news providers. As a result the financial market players are overloaded with qualitative information which is potentially extremely useful but, due to the lack of time, is often ignored. The goal of this work is to reduce the qualitative data-overload of the financial operators. The research involves the identification of the information in the source financial articles which is relevant ...