Gloria T. Lau

A relatedness analysis of government regulations using domain knowledge and structural organization

The complexity and diversity of government regulations make understanding and retrieval of regulations a non-trivial task. One of the issues is the existence of multiple sources of regulations and interpretive guides with differences in format, terminology and context. This paper describes a comparative analysis scheme developed to help retrieval of related provisions from different regulatory documents. Specifically, the goal is to identify the most strongly related provisions between regulations. The relatedness analysis makes use of not only traditional term match but also a combination of feature matches, and not only content comparison but also structural analysis.Regulations are first compared based on conceptual information as well as domain knowledge through feature matching. Regulations also possess specific organizational structures, such as a tree hierarchy of provisions and heavy referencing between provisions. These structures represent useful information in locating related provisions, and are therefore exploited in the comparison of regulations for completeness. System performance is evaluated by comparing a similarity ranking produced by users with the machine-predicted ranking. Ranking produced by the relatedness analysis system shows a reduction in error compared to that of Latent Semantic Indexing. Various pairs of regulations are compared and the results are analyzed along with observations based on different feature usages. An example of an e-rulemaking scenario is shown to demonstrate capabilities and limitations of the prototype relatedness analysis system.

Similarity analysis on government regulations

Government regulations are semi-structured text documents that are often voluminous, heavily cross-referenced between provisions and even ambiguous. Multiple sources of regulations lead to difficulties in both understanding and complying with all applicable codes. In this work, we propose a framework for regulation management and similarity analysis. An online repository for legal documents is created with the help of text mining tool, and users can access regulatory documents either through the natural hierarchy of provisions or from a taxonomy generated by knowledge engineers based on concepts. Our similarity analysis core identifies relevant provisions and brings them to the users attention, and this is performed by utilizing both the hierarchical and referential structures of regulations to provide a better comparison between provisions. Preliminary results show that our system reveals hidden similarities that are not apparent between provisions based on node content comparisons.

Regulation retrieval using industry specific taxonomies

Increasingly, taxonomies are being developed and used by industry practitioners to facilitate information interoperability and retrieval. Within a single industrial domain, there exist many taxonomies that are intended for different applications. Industry specific taxonomies often represent the vocabularies that are commonly used by the practitioners. Their jobs are multi-faceted, which include checking for code and regulatory compliance. As such, it will be very desirable if industry practitioners are able to easily locate and browse regulations of interest. In practice, multiple sources of government regulations exist and they are often organized and classified by the needs of the issuing agencies that enforce them rather than the needs of the communities that use them. One way to bridge these two distinct needs is to develop methods and tools that enable practitioners to browse and retrieve government regulations using their own terms and vocabularies, for example, via existing industry taxonomies. The mapping from a single taxonomy to a single regulation is a trivial keyword matching task. We examine a relatedness analysis approach for mapping a single taxonomy to multiple regulations. We then present an approach for mapping multiple taxonomies to a single regulation by measuring the relatedness of concepts. Cosine similarity, Jaccard coefficient and market basket analysis are used to measure the semantic relatedness between concepts from two different taxonomies. Preliminary evaluations of the three relatedness analysis measures are performed using examples from the civil engineering and building industry. These examples illustrate the potential benefits of regulatory usage from the mapping between various taxonomies and regulations.

Analyzing government regulations using structural and domain information

Government regulations, by extending laws with specific guidance for corporate and public actions, provide an important societal benefit. Ideally, they should be intelligible to ordinary citizens as well as rule makers, but the volume of regulations coupled with heavy referencing between provisions limit their accessibility. Apart from the difficulties in locating and understanding a particular regulation, users often must consult and reconcile multiple authoritative sources. For example, US companies frequently must comply with overlapping federal, state, and local regulations; in addition, some nonprofit organizations publish their own codes of practice. The problem is exacerbated in the European Union, where regulators must harmonize legislation across countries with different languages and traditions. To address the difficulties encountered in comparing regulatory documents with multiple authoritative sources, the Regnet project is developing a relatedness analysis system that exploits such documents unique computational properties.

Legal information retrieval and application to e-rulemaking

The complexity and diversity of government regulations make understanding the regulations a non-trivial task. One of the issues is the existence of multiple sources of regulations and interpretive guides; the latter are often independent of governing bodies. This work aims to develop an information infrastructure for legal information retrieval with applications to electronic-rulemaking. The pilot study focuses on accessibility regulations from the US Federal government, private organizations and European agencies. A shallow parser is developed to consolidate different regulations into a unified XML format, which is well suited for handling semi-structured data such as legal documents. Handcrafted rules and a text mining tool are developed to extract the important features, such as concepts, measurements, effective dates and so on, and to incorporate them into the corpus.To compare and locate related provisions from different regulatory documents, we employ Information Retrieval techniques to combine generic features with domain knowledge. Structural information from regulations, such as the hierarchical organization of provisions and heavy referencing among provisions, are used to help improve the relatedness analysis. Results are obtained to illustrate the use of regulatory structure and domain knowledge in provision comparisons. Application to an e-rulemaking scenario for a rights-of-way drafted regulation is shown to demonstrate extended capabilities of the prototype system.

Utilizing statistical semantic similarity techniques for ontology mapping - with applications to AEC standard models

The objective of this paper is to introduce three semi-automated approaches for ontology mapping using relatedness analysis techniques. In the architecture, engineering, and construction (AEC) industry, there exist a number of ontological standards to describe the semantics of building models. Although the standards share similar scopes of interest, the task of comparing and mapping concepts among standards is challenging due to their differences in terminologies and perspectives. Ontology mapping is therefore necessary to achieve information interoperability, which allows two or more information sources to exchange data and to re-use the data for further purposes. The attribute-based approach, corpus-based approach, and name-based approach presented in this paper adopt the statistical relatedness analysis techniques to discover related concepts from heterogeneous ontologies. A pilot study is conducted on IFC and CIS/2 ontologies to evaluate the approaches. Preliminary results show that the attribute-based approach outperforms the other two approaches in terms of precision and F-measure.

Developing an ontology for the U.S. patent system

The past few years have experienced an explosive growth in scientific and regulatory documents related to the patent system. Relevant information is siloed into many heterogeneous information domains making it a challenging task to gather information. In this paper, we develop an ontology to standardize the representation of the patent system in order to overcome the heterogeneity and integrate information from the patent document, court case and file wrapper domains. Through a use case in the bio domain erythropoietin, we demonstrate how this ontology can be used as a tool to improve the learning curve of users gathering information across these multiple information domains. The proposed ontology provides the required semantics to develop automated tools for a variety of purposes including Information Retrieval (IR) and analytics.

Improving access to and understanding of regulations through taxonomies

Abstract Industrial taxonomies have the potential to automate information retrieval, facilitate interoperability and, most importantly, improve decision making — decisions that must comply with existing government regulations and codes of practice. However, it is difficult to find those regulations and codes most relevant to a particular decision, even though they are now in digital form, and often available online. The focus of this work is to map regulations and codes to existing industry-specific taxonomies that would improve their access and retrieval and facilitate their integration with application programs. Keyword matching is a commonly used technique for mapping from a single taxonomy to a single regulation. In this paper, we examine techniques to address two other mapping problems: from a single taxonomy to multiple regulations and from multiple taxonomies to a single regulation. Those techniques – Cosine similarity, Jaccard coefficient, and market basket analysis – provide metrics for measuring the similarity between concepts from different taxonomies. We discuss these metrics and provide evaluations using examples from the building industry. These examples illustrate the potential regulatory benefits from the mapping between various taxonomies and regulations.

Developing a comprehensive patent related information retrieval tool

In recent years, there has been a massive growth of regulatory and related information available online. This information is distributed across many different domains creating a problem for accessing and managing this data. This paper proposes a framework to access information across two such domains - patents and court cases. The framework is designed to boost the value of a set of patents based on information available in court cases by identifying and cross-referencing mutual information in the two domains. We test our framework by constructing a use case involving the hormone erythropoietin. A corpus of 1150 patents (including 135 closely related patents) and 30 court cases is gathered. Challenges associated with such integration and future plans are briefly discussed.

Mapping regulations to industry-specific taxonomies

For each industry, there exist many taxonomies that are intended for various applications. There are also multiple sources of regulations from different government agencies. Industry practitioners, unlike legal practitioners, are familiar with one or more industry-specific taxonomies but not necessarily regulatory organization systems. To help browsing of regulations by industry practitioners, we propose to map regulations to existing industry-specific taxonomies. A mapping from a single taxonomy to a single regulation is a trivial keyword matching task. From there, we examine techniques to map a single taxonomy to multiple regulations, as well as to map multiple taxonomies to a single regulation. Cosine similarity, Jaccard coefficient and market-basket analysis are tested to model the similarity metric between concepts from different taxonomies. Preliminary evaluations of the three metrics are performed. Examples from the building industry are drawn to illustrate the betterment of regulatory usage from the mapping between various taxonomies and regulations.