Biomedical relation extraction via knowledge-enhanced reading comprehension

Background In biomedical research, chemical and disease relation extraction from unstructured biomedical literature is an essential task. Effective context understanding and knowledge integration are two main research problems in this task. Most work of relation extraction focuses on classification for entity mention pairs. Inspired by the effectiveness of machine reading comprehension (RC) in the respect of context understanding, solving biomedical relation extraction with the RC framework at both intra-sentential and inter-sentential levels is a new topic worthy to be explored. Except for the unstructured biomedical text, many structured knowledge bases (KBs) provide valuable guidance for biomedical relation extraction. Utilizing knowledge in the RC framework is also worthy to be investigated. We propose a knowledge-enhanced reading comprehension (KRC) framework to leverage reading comprehension and prior knowledge for biomedical relation extraction. First, we generate questions for each relation, which reformulates the relation extraction task to a question answering task. Second, based on the RC framework, we integrate knowledge representation through an efficient knowledge-enhanced attention interaction mechanism to guide the biomedical relation extraction. Results The proposed model was evaluated on the BioCreative V CDR dataset and CHR dataset. Experiments show that our model achieved a competitive document-level F1 of 71.18% and 93.3%, respectively, compared with other methods. Conclusion Result analysis reveals that open-domain reading comprehension data and knowledge representation can help improve biomedical relation extraction in our proposed KRC framework. Our work can encourage more research on bridging reading comprehension and biomedical relation extraction and promote the biomedical relation extraction.

Designing a Framework of Ethnomedicinal Plant Knowledge Integration Using OSS

Indigenous knowledge refers to the knowledge, innovations, and practices of indigenous communities. Ethnic groups are repository knowledge of herbal medicine. Many indigenous people use several plants for medicinal preparations, and these medicines are known as ethnomedicine. It has developed from experience gained over centuries. Species of ethnomedicinal plants are threatened in most of nations due to overexploitation, habitat loss, destructive harvesting techniques, unsustainable trade, and deforestation. Documented indigenous knowledge on ethnomedicine forms part of the documentary heritage of the nation. The chapter will provide a framework for design an information retrieval system for ethnomedicine or knowledge on medicinal plants that are used to manage human ailments. The framework will be prepared, established on the open source software (OSS), and is appropriate not only for documentation but also beneficial for retrieving domain-specific knowledge. The model provides a framework for resource integration digitally using Greenstone Digital Library (GSDL) software.

How Internal IT Capability Affects Open Innovation Performance: From Dynamic Capability Perspective

Information technology (IT) and open innovation has been one of hot topic in existing research respectively. However, there are lack empirical research on inner mechanism of internal IT capability affecting open innovation performance. According to dynamic capability theory, this paper puts internal IT capability, internal knowledge integration, firm social capital, and open innovation performance into a theoretical model. Through 232 surveys, the results indicate that internal knowledge integration plays a mediator role in the effect of internal IT capability on open innovation performance. Meanwhile, the relationship between internal IT capability and internal knowledge integration can be positively moderated by firm social capital. This study extends the research on open innovation and IT business value, and provides theoretical direction for practice.

Openness to innovation as a driver of knowledge integration in High-Tech SMEs, the roles of social capital and network competence

This paper studies an original analytical framework to address the implementation dynamics of open innovation practices by discussing their impacts on SMEs' social capital and knowledge integration. A total of 358 High-Tech SMEs in the Democratic Republic of Congo participated in the survey. The collected data were statistically analyzed using structural equation modeling (SEM) in Smart PLS to verify the postulated hypothesis. The results reveal that open innovation practices promote knowledge integration, and social capital partially mediates open innovation and knowledge integration capability. The results further indicate that network competence moderates the practice of open innovation and social capital interactions with external knowledge sources. The theoretical implications of this study contribute to advance the discussion on the antecedent of social capital and knowledge integration in SMEs in developing countries and propose network competence as a moderator. The study also highlights the social capital nature of open innovation and reinforces the knowledge of scholars.

Ciência e tecnologia de forma integrada (nota introdutória)

The construction of a multidisciplinary journal, from a perspective of knowledge integration, intends to highlight the points of contact between different areas of study, trying to overcome communication gaps and creating bridges between the social sciences, the arts, humanities and exact sciences. In this issue we present a diversity of approaches, not only in relation to the areas of knowledge, but also in relation to the different spaces of action of researchers with origins in Europe, Africa and the Americas.