Martin Toepfer

UIMA Ruta: Rapid development of rule-based information extraction applications

Rule-based information extraction is an important approach for processing the increasingly available amount of unstructured data. The manual creation of rule-based applications is a time-consuming and tedious task, which requires qualified knowledge engineers. The costs of this process can be reduced by providing a suitable rule language and extensive tooling support. This paper presents UIMA Ruta, a tool for rule-based information extraction and text processing applications. The system was designed with focus on rapid development. The rule language and its matching paradigm facilitate the quick specification of comprehensible extraction knowledge. They support a compact representation while still providing a high level of expressiveness. These advantages are supplemented by the development environment UIMA Ruta Workbench. It provides, in addition to extensive editing support, essential assistance for explanation of rule execution, introspection, automatic validation, and rule induction. UIMA Ruta is a useful tool for academia and industry due to its open source license. We compare UIMA Ruta to related rule-based systems especially concerning the compactness of the rule representation, the expressiveness, and the provided tooling support. The competitiveness of the runtime performance is shown in relation to a popular and freely-available system. A selection of case studies implemented with UIMA Ruta illustrates the usefulness of the system in real-world scenarios.

Fine-grained information extraction from German transthoracic echocardiography reports

BackgroundInformation extraction techniques that get structured representations out of unstructured data make a large amount of clinically relevant information about patients accessible for semantic applications. These methods typically rely on standardized terminologies that guide this process. Many languages and clinical domains, however, lack appropriate resources and tools, as well as evaluations of their applications, especially if detailed conceptualizations of the domain are required. For instance, German transthoracic echocardiography reports have not been targeted sufficiently before, despite of their importance for clinical trials. This work therefore aimed at development and evaluation of an information extraction component with a fine-grained terminology that enables to recognize almost all relevant information stated in German transthoracic echocardiography reports at the University Hospital of Würzburg.MethodsA domain expert validated and iteratively refined an automatically inferred base terminology. The terminology was used by an ontology-driven information extraction system that outputs attribute value pairs. The final component has been mapped to the central elements of a standardized terminology, and it has been evaluated according to documents with different layouts.ResultsThe final system achieved state-of-the-art precision (micro average.996) and recall (micro average.961) on 100 test documents that represent more than 90 % of all reports. In particular, principal aspects as defined in a standardized external terminology were recognized with f1=.989 (micro average) and f1=.963 (macro average). As a result of keyword matching and restraint concept extraction, the system obtained high precision also on unstructured or exceptionally short documents, and documents with uncommon layout.ConclusionsThe developed terminology and the proposed information extraction system allow to extract fine-grained information from German semi-structured transthoracic echocardiography reports with very high precision and high recall on the majority of documents at the University Hospital of Würzburg. Extracted results populate a clinical data warehouse which supports clinical research.

Collective information extraction with context-specific consistencies

Conditional Random Fields (CRFs) have been widely used for information extraction from free texts as well as from semi-structured documents. Interesting entities in semi-structured domains are often consistently structured within a certain context or document. However, their actual compositions vary and are possibly inconsistent among different contexts. We present two collective information extraction approaches based on CRFs for exploiting these context-specific consistencies. The first approach extends linear-chain CRFs by additional factors specified by a classifier, which learns such consistencies during inference. In a second extended approach, we propose a variant of skip-chain CRFs, which enables the model to transfer long-range evidence about the consistency of the entities. The practical relevance of the presented work for real-world information extraction systems is highlighted in an empirical study. Both approaches achieve a considerable error reduction.

Integrated Tools for Query-driven Development of Light-weight Ontologies and Information Extraction Components

This paper reports on a user-friendly terminology and information extraction development environment that integrates into existing infrastructure for natural language processing and aims to close a gap in the UIMA community. The tool supports domain experts in data-driven and manual terminology refinement and refactoring. It can propose new concepts and simple relations and includes an information extraction algorithm that considers the context of terms for disambiguation. With its tight integration of easy-to-use and technical tools for component development and resource management, the system is especially designed to shorten times necessary for domain adaptation of such text processing components. Search support provided by the tool fosters this aspect and is helpful for building natural language processing modules in general. Specialized queries are included to speed up several tasks, for example, the detection of new terms and concepts, or simple quality estimation without gold standard documents. The development environment is modular and extensible by using Eclipse and the Apache UIMA framework. This paper describes the system’s architecture and features with a focus on search support. Notably, this paper proposes a generic middleware component for queries in a UIMA based workbench.

Exploiting Structural Consistencies with Stacked Conditional Random Fields

Conditional Random Fields (CRF) are popular methods for labeling unstructured or textual data. Like many machine learning approaches, these undirected graphical models assume the instances to be independently distributed. However, in real-world applications data is grouped in a natural way, e.g., by its creation context. The instances in each group often share additional structural consistencies. This paper proposes a domain-independent method for exploiting these consistencies by combining two CRFs in a stacked learning framework. We apply rule learning collectively on the predictions of an initial CRF for one context to acquire descriptions of its specific properties. Then, we utilize these descriptions as dynamic and high quality features in an additional (stacked) CRF. The presented approach is evaluated with a real-world dataset for the segmentation of references and achieves a significant reduction of the labeling error.