Volume 29, Issue 2

Modeling Entity and Event Relations in Scientific Documents for Supporting Knowledge Discovery and Organization
Yejun Wu
LIBRES Volume 29, Issue 2 (March 2020), page 77-90

---

Background. Scientific documents often contain knowledge about what one entity did to another entity under what conditions (such as time, place, and method), which is related to another statement of what one entity did to another entity under what conditions. Such knowledge can be represented as relations between entities and events. Here what one entity did to another entity under what condition is defined as an event, which expresses the relationship between two entities under a condition.
Objective. The objective of this paper is to design a model of entity and event relationship that can be used to represent knowledge identified from scientific documents and to facilitate knowledge discovery and organization.
Method. The paper first presents a brief literature review on causal relationships, then evaluates four existing knowledge organization models and five event ontologies for their commonalities and differences in representing entity relationships and event relationships. The paper then proposes a combined entity and event relationship model based on the strengths of the existing event ontologies. Five main kinds of entity and event relationships are identified from an oil spill document set.
Results. The three domain event ontologies, CIDOC CRM, Event Ontology and NewsML-G2, are only useful in serving specific purposes. The two generic event ontologies, DOLCE+DnS and Event Model F, must be enriched to be useful for representing knowledge for discovery. An entity and event model is proposed based on the strengths of these event models for representing knowledge in scientific documents.

Ontology-based Big Data Analysis for Orchid Smart Farming
Nattapong Kaewboonma, Faculty of Management Technology, Rajamangala University of Technology Srivijaya, Thailand
Wirapong Chansanam, Faculty of Humanities and Social Science, Khon Kaen University, Thailand
Marut Buranarach, Data Science and Analytics Research Group, National Electronics and Computer Technology Center, Thailand
LIBRES Volume 29, Issue 2 (March 2020), page 91-98

---

Background. Precision agriculture or smart farming is becoming more and more important in modern orchid farming in Thailand. Sensing and communication technologies have witnessed explosive growth in the recent past. These technologies are empowering information systems from many domains such as health care, environmental monitoring and farming, to collect and store large volume of data.
Objectives. The research aims to develop an ontology for big data analysis for the smart farming in Rajamangala University of Technology Srivijaya (RUTS), Nakhon Si Thammarat campus.
Methods. The ontology design and development process comprises: (1) Ontology design: the domain ontology provide vocabularies for concepts and relations within the orchid domain, and information ontology which specifies the record structure of databases; (2) Ontology development, which consists of five processes: (i) defining the scope, (ii) investigating the existing ontologies and plan to reuse, (iii) defining terms and its relations, (iv) create instances, and (v) implementation and evaluation.
Results. The research outcome is the domain ontology and information ontology wherein 11 concepts of smart farming were identified and classified into classes and sub-classes.
Contributions.The system is designed for assisting orchid farmers by giving recommended measures and expected results based on the knowledge extracted from best practices.

Automatic Extraction of Causal Chains from Text/
Aliaksandr Huminski and Yan Bin Ng
LIBRES Volume 29, Issue 2 (March 2020), page 99-108

---

Background. Automatic extraction of causal chains is valuable for discovering previously unknown and hidden connections between events. However, there is only a handful of works devoted to automatic extraction of causal chains from text.
Objective. To develop a method for automatic extraction of causal chains from text.
Method. A new approach based on linguistic templates is suggested for causal chain extraction. It is domain-independent, not restricted to extraction from single sentences and unfolded on big data. For implementation, a sequence of four modules was deployed. These are verb restriction, part-of-speech tagging, extracting causal relations, and unification and matching events.
Results. 14,821 causal chains (with length=2) have been extracted from 100,000 English Wikipedia articles.
Contributions. The extracted causal chains can contribute to developing commonsense knowledge bases, reasoning resources, problem-solving, and generally in discovering previously unknown relationships between entities/events.

Semantic Simulations Based on Object-Oriented Analysis and Modeling
LIBRES Volume 29, Issue 2 (March 2020), page 109-123

---

Background. This is part of an ongoing set of studies to develop a framework and techniques for rich semantic modeling, based on traditional ontologies and upper ontologies. Such models should provide the basis for direct representation of complex texts such as scientific research reports and descriptions of historical events. Semantic models have been developed to describe mechanisms and explore how semantic models can be related to object-oriented programming languages.
Objective. Object-oriented semantic modeling was applied to two simulations: of a waterfall and of the cardiopulmonary system. Issues related to the components of these models and their interaction were examined.
Results. Complete executable models for the waterfall and the cardiopulmonary system examples are demonstrated. Specific recommendations are offered for handling States, Portions of Matter, Meta-Operators, and Systems.