Developing a Comprehensive Patent Related Information Retrieval Tool

Government Information Quarterly

Kerrigan

et al. 2014

Self Cite

This paper describes a research effort that aims to develop information infrastructure and tools to facilitate access, compliance and analysis of government regulations. It is well recognized that the complexity, diversity, and volume of government regulations are detrimental to business and hinder public understanding of government. The burden of complying with regulations can fall disproportionately on small businesses since these businesses may not have the expertise or resources to keep track of the regulations and the requirements. The situation can potentially be improved by developing appropriate tools that can help facilitate the regulatory and compliance process. To illustrate, this paper discusses the applications of information technology for selected services related to regulations, such as compliance assistance, comparison of regulation from diverse sources, and e-rulemaking.

Section: Summary and Discussionmentioning

confidence: 99%

REGNET: Regulatory information management, compliance and analysis

Government Information Quarterly

Kerrigan

et al. 2014

Self Cite

“…The techniques developed will account for varying language and make maximum utilization of the cross-referenced information [39], [40]. The required domain knowledge is available in the form of bioontologies at BioPortal.…”

Section: A Future Workmentioning

confidence: 99%

An ontology to integrate multiple information domains in the patent system

Taduri

2011 IEEE International Symposium on Technology and Society (ISTAS)

et al. 2011

Self Cite

Abstract-In recent years, there has been an explosive growth in scientific and regulatory documents related to the patent system. Relevant information is siloed into many heterogeneous information domains making it very challenging to retrieve information across multiple domains. In this paper, we develop an ontology for the patent system to integrate information from the patent and court case domains. Through a use case erythropoietin, we demonstrate how this ontology can be used to enhance information retrieval across multiple domains.

“…Domain ontologies provide a rich source of knowledge allowing applications to understand the semantics of the domain and handle terminological inconsistencies. For information retrieval, the use of domain knowledge can enhance the quality of results obtained [13,14]. In this paper, we present our methodology based on documents in the biomedical domain.…”

Section: Introductionmentioning

confidence: 99%

“…Several works have shown that the use of domain ontologies in IR facilitates semantic inter-operability and improves the quality of the results [11,13,14]. Another approach to handle terminological inconsistencies is Latent Semantic Indexing (LSI), where the various terms are mapped onto a single concept axis [28].…”

Section: Introductionmentioning

confidence: 99%

Retrieval of Patent Documents from Heterogeneous Sources Using Ontologies and Similarity Analysis

Taduri

2011 IEEE Fifth International Conference on Semantic Computing

et al. 2011

Self Cite

Abstract-In the past few years, there has been an explosive growth in scientific and legal information related to the patent system. Patents and related documents are siloed into multiple heterogeneous sources. Retrieving relevant information from diverse sources is a non-trivial task and poses many technical challenges. Among the challenges is the issue of terminological inconsistencies that are used in the documents. We tackle the terminological inconsistency issue by exploring domain knowledge through the use of ontology standards. Furthermore, we take advantage of cross-references and structural dependencies between the information sources to enhance terminological comparison. In this paper, we present a similarity analysis methodology which combines knowledge from two distinct sources -(1) domain ontologies and (2) ontologies which describe the information sources to assist a user in identifying relevant documents across several information sources simultaneously. Specifically, we explore the use of a rule-based system to infer relationships between documents based on pre-defined heuristics. We present our results through a use case in the bio-patent domain with a collection of 1150 patents and 30 court cases.