The F-measure scores of ChemSpot trained on scientific abstracts annotated using a guideline different from the ones used for the patent corpora, indicate that these models are not adequate to recognize entities from patents, and accentuate the need for more annotated patent corpora for chemical NER.
"I'm a scientist and I've been trained on scientific principles, and that's what I use [to locate groundwater]," says Tim Parker, a hydrogeologist and independent consultant based in Sacramento.
This observation indicates that models trained on scientific abstracts are not quite as capable of recognizing chemical entities from patents.
Both tools were trained on scientific abstracts, but the training corpora comprise different articles and were annotated based on different annotation guidelines [31].
In this paper, we take this idea one step further and perform a cross-text-genre evaluation by assessing the performance of chemical NER tools trained on scientific articles a problem much better researched on patent corpora.
Three actions are envisaged: Capacity building through a flexible and sustainable training programme on scientific writing and OA publishing; creation of training tools based on semantic web technologies; development of a network of supporting institutions.
Furthermore, we have developed seven principles of training based on scientific literature and our own experience, which are (1) to avoid or to minimize the incidence of injuries; (2) overcompensation; (3) periodization; (4) progressive loading; (5) individuality; (6) specificity; and (7) unity.
Mesfin Kassa Admassie, who works for a large population, health, and environment consortium in Ethopia, and Angelina Davydova, a journalist and university professor from St .Petersburg, Russia, both work closely with environmental journalists, training them on scientific issues and working with the media to influence policy makers and educate the public.
It includes the development and implementation of a flexible and sustainable training programme on scientific writing and OA publishing (including repository building) for the diffusion of health information.
The VBC PhD Programme offers a flexible curriculum structure with an initial training course, lectures on scientific topics as well as technical and complementary skills training.
