Text Mining Through Semi Automatic Semantic Annotation

Kiyavitskaya, Nadzeya; Zeni, Nicola; Mich, Luisa; Cordy, James R.; Mylopoulos, John

doi:10.1007/11944935_13

Cited by 33 publications

(27 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The issue with manually annotating documents is that it is very laborious for non-trivial documents sets. Semi-automatic annotation is used to pre-annotate documents to make the process of manual annotation much less laborious (Kiyavitskaya et al 2006, Névéol et al 2011) while still retaining the advantages of manually annotating documents over automatic annotation, i.e. it is less error-prone (see for instance; Lin et al 2015).…”

Section: Related Workmentioning

confidence: 99%

From science to practice: Bringing innovations to agronomy and forestry

Willems¹,

Koenderink²,

Top³

2015

JAI

View full text Add to dashboard Cite

A B S T R A C TThe challenge of the work presented here is to make innovative research output in the agronomy and forestry domain accessible to end-users, so that it can be practically applied. We have developed an approach that consists of three key-elements: an ontology with domain knowledge, a set of documents that have been annotated and metaannotated, and a system (ask-Valerie) that is based on a dialogue to represent the interaction between end user and system. We show that the dialogue-metaphor is a good way of modelling the interaction between user and system. The system helps the user in formulating his question and in answering it in a useful way. Meta-annotations of key-paragraphs in the document-base turn out to be relevant in assessing in one glance what the content of a document is. End-users are very enthusiastic about the possibilities that ask-Valerie offers them in translating scientific results to their own situation.

show abstract

Section: Related Workmentioning

confidence: 99%

From science to practice: Bringing innovations to agronomy and forestry

Willems¹,

Koenderink²,

Top³

2015

JAI

View full text Add to dashboard Cite

show abstract

“…Recent efforts on computerizing building code rules are focused more on the concept of marking-up regulatory texts to create a computable representation [14]. Other research investigations are centered chiefly on the investigations of automated or semi-automated extraction of information from regulatory texts into rules and other computable objects ( [15], [16], [17], [18], [19], and [20]).…”

Section: Literature Reviewmentioning

confidence: 99%

Methods for Computable Building Codes

Nawari¹,

Alsaffar²

2015

cea

View full text Add to dashboard Cite

Building codes and regulatory standards are becoming increasingly complex with the acquisition of new knowledge in the design and construction domain. The necessity for computable representation of the building codes and regulations for automating the code checking process is becoming ever more critical. Within the framework of Building Information Modeling (BIM) work process, model checking against building regulations is generally needed to be an automatic or semi-automatic process. These checking mechanisms generally do not modify a building design, but rather evaluates a design on the basis of the configuration of objects, their relations and attributes. This paper presents a summary of the core existing methods for computerizing building codes and standards. It reviews main concepts for these methods including knowledge representation, reasoning procedures, and knowledge acquisition. Moreover, this study evaluates the capabilities of the reviewed methods in reference to their practical applications and applied limitations for modeling computable building codes and standards. Additionally, the paper proposes methods with practical flexibility of encoding building codes knowledge domain and at the same time possess transparent and verifiable syntax and sematic features. The suggested approaches rely on evidently identifying objective and subjective data of the regulatory text before formalizing building codes. The methodology realizes the limitations of the formalization systems by clearly identifying which components of the building codes and standards can be transformed into computable model and which parts can't be encoded and requires manual compliance checking.

show abstract

“…This section introduces the Cerno framework for semi-automatic semantic annotation and also presents the Gaius T extension, intended specifically for the annotation of regulatory text [6].…”

Section: Semantic Annotation Processmentioning

confidence: 99%

“…The architecture and the per- formance of the tool are described in detail in a previous paper [6]. To annotate input documents, Cerno uses context-free grammars to generate a parse tree before applying transformation rules, which generate output in a pre-specified format.…”

Section: The Cerno Frameworkmentioning

confidence: 99%

“…Our work seeks to add tool support to this process to improve productivity, quality and consistency in the first step of the output. To achieve this goal, we adopt the Cerno framework [6] for semantic annotation. The framework initially requires the construction of linguistic markers to identify various concepts, on the basis of which it provides automated assistance to engineers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automating the Extraction of Rights and Obligations for Regulatory Compliance

Kiyavitskaya

Zeni

Breaux

et al. 2008

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Government regulations are increasingly affecting the security, privacy and governance of information systems in the United States, Europe and elsewhere. Consequently, companies and software developers are required to ensure that their software systems comply with relevant regulations, either through design or re-engineering. We previously proposed a methodology for extracting stakeholder requirements, called rights and obligations, from regulations. In this paper, we examine the challenges to developing tool support for this methodology using the Cerno framework for textual semantic annotation. We present the results from two empirical evaluations of a tool called "Gaius T" that is implemented using the Cerno framework and that extracts a conceptual model from regulatory texts. The evaluation, carried out on the U.S. HIPAA Privacy Rule and the Italian accessibility law, measures the quality of the produced models and the tool's effectiveness in reducing the human effort to derive requirements from regulations.

show abstract

Text Mining Through Semi Automatic Semantic Annotation

Cited by 33 publications

References 13 publications

From science to practice: Bringing innovations to agronomy and forestry

From science to practice: Bringing innovations to agronomy and forestry

Methods for Computable Building Codes

Automating the Extraction of Rights and Obligations for Regulatory Compliance

Contact Info

Product

Resources

About