William de Beaumont

Generic Parsing for Multi-Domain Semantic Interpretation

Producing detailed syntactic and semantic representations of natural language is essential for practical dialog systems such as plan-based assistants and tutorial systems. Development of such systems is time-consuming and costly as they are typically hand-crafted for each application, and dialog corpus data is more difficult to obtain than text. The TRIPS parser and grammar addresses these issues by providing broad coverage of common constructions in practical dialog and producing semantic representations suitable for dialog processing across domains. Our system bootstraps dialog system development in new domains and helps build parsed corpora.

Going beyond PBD: A play-by-play and mixed-initiative approach

Publisher Summary This chapter explores the Procedure Learning On the Web (PLOW) that demonstrates natural language (NL) is a powerful intuitive tool for end users to build Web tasks with significant complexity using only a single demonstration. The natural play-by-play demonstration that would occur in human–human teaching provides enough information for the system to generalize demonstrated actions. Mixed-initiative interaction also makes the task-building process much more convenient and intuitive. Without the systems proactive involvement in learning, the human instructors job could become very tedious, difficult, and complex. Semantic information in NL description also makes the system more robust by letting it handle the dynamic nature of the Web. Although PLOW sheds more light on NLs roles and the collaborative problem-solving aspects in the end-user programming on the Web, significant challenges still exist and new ones will emerge as application domains are expanded. Better reasoning about tasks, broader coverage of language understanding, and more robust Web object handling will be needed to address the challenges.

Increasing the coverage of a domain independent dialogue lexicon with VERBNET

This paper investigates how to extend coverage of a domain independent lexicon tailored for natural language understanding. We introduce two algorithms for adding lexical entries from VerbNet to the lexicon of the Trips spoken dialogue system. We report results on the efficiency of the method, discussing in particular precision versus coverage issues and implications for mapping to other lexical databases.

Complex Event Extraction using DRUM

Complex mechanisms, such as cell-signaling pathways, consist of many highly interconnected components, yet they are often described in disconnected fragmentary ways. The goal of DRUM (Deep Reader for Understanding Mechanisms) is to develop a system that can read papers and combine results of individual studies into a comprehensive explanatory model. A first step is to automatically extract relevant events and event relationships from the literature. This paper describes initial steps in extending an existing general deep language understanding system, TRIPS, to read biomedical papers. In a preliminary evaluation, our system was the best performing system among the participants, achieving results close to human expert performance. These results suggested that our system is viable for complex event extraction and, ultimately, understanding complex systems and mechanisms.

Towards an OWL-based framework for extracting information from clinical texts

In this paper, we present our ongoing work towards an OWL-based framework for extracting a variety of information (including patient history) from clinical texts. Our framework integrates a well-known natural language processing (NLP) system by converting its ontology and output logical form interpretation into the Web Ontology Language (OWL). The OWL-based Semantic Query-Enhanced Web Rule Language (SQWRL) is then used as a platform for authoring Semantic Web-aware rules for extracting information of interest from the OWL knowledge based created from parsing a clinical report. We also describe our ongoing work on using this system for extracting a timeline-based patient medical record from the history of present illness section of clinical texts.

Going beyond PBD

Publisher Summary This chapter explores the Procedure Learning On the Web (PLOW) that demonstrates natural language (NL) is a powerful intuitive tool for end users to build Web tasks with significant complexity using only a single demonstration. The natural play-by-play demonstration that would occur in human–human teaching provides enough information for the system to generalize demonstrated actions. Mixed-initiative interaction also makes the task-building process much more convenient and intuitive. Without the systems proactive involvement in learning, the human instructors job could become very tedious, difficult, and complex. Semantic information in NL description also makes the system more robust by letting it handle the dynamic nature of the Web. Although PLOW sheds more light on NLs roles and the collaborative problem-solving aspects in the end-user programming on the Web, significant challenges still exist and new ones will emerge as application domains are expanded. Better reasoning about tasks, broader coverage of language understanding, and more robust Web object handling will be needed to address the challenges.

Chapter 16 – Going beyond PBD: A play-by-play and mixed-initiative approach

Publisher Summary This chapter explores the Procedure Learning On the Web (PLOW) that demonstrates natural language (NL) is a powerful intuitive tool for end users to build Web tasks with significant complexity using only a single demonstration. The natural play-by-play demonstration that would occur in human–human teaching provides enough information for the system to generalize demonstrated actions. Mixed-initiative interaction also makes the task-building process much more convenient and intuitive. Without the systems proactive involvement in learning, the human instructors job could become very tedious, difficult, and complex. Semantic information in NL description also makes the system more robust by letting it handle the dynamic nature of the Web. Although PLOW sheds more light on NLs roles and the collaborative problem-solving aspects in the end-user programming on the Web, significant challenges still exist and new ones will emerge as application domains are expanded. Better reasoning about tasks, broader coverage of language understanding, and more robust Web object handling will be needed to address the challenges.