Name entity recognition

Batchelor, C.R. and Corbett, P.T. 2007. Semantic enrichment of journal articles using chimerical named entity recognition. Proceedings of the ACL 2007, demo and poster sessions, Prague, lune 2007, pp. 45—48. 

In principle, four different basic approaches for named entity recognition can be distinguished ... 

Therefore, automated methods for the detection and extraction of chemical information in scientific text are required. Although chemical named entity recognition is dealt with in detail in Chapter 3 of this book, we briefly summarize the principles underlying chemical named entity recognition. We also briefly elucidate on the need for reconstruction of chemical information from chemical structure depictions, as detailed in Chapter 4. 

When discussing chemical named entity recognition, distinguishing between the different nomenclatures types used for chemical entities in text is inevitable. Basically, there are five classes ... 

The first publications in this area were from the 1980s and 1990s.41 42 This area of research now uses the general principles of natural language processing (NLP) and, specifically, named entity extraction (NER) enhanced with specific developments for chemical and biochemical name recognition.43 44 Chapter 7 of this book is devoted to NLP and NER approaches applied to the extraction of chemical information, and we will not discuss these approaches in more detail here. 

NLP techniques provide the basis to extract this kind of more detailed information. In the past years approaches have been developed that are mainly focused on the biomedical domain to extract protein-protein interactions60 and gene-disease relations.61 They are based upon the correct recognition of the named entities taking part in the relationship. Dedicated patterns have to be developed to identify all the phrasal constructs that are indicative of relationships between chemical and biomedical entities available in text being of interest for academic researchers and the pharmaceutical industry. 

Much effort has been devoted toward efficient chemical text mining. A chemically intelligent tool is OSCAR4 (Open Source Chemical Analysis Routine), designed for chemistry-specific NLP [85]. It performs chemical NLP, chemical entity recognition (CER), chemical name recognition by direct lookup or ML. Its parsers... 

Basic Mechanisms of Adhesion Acid-Base Interactions. The understanding of polymer adhesion has been greatly advanced in recent years by the recognition of the central role of acid-base interactions. The concept of an acid was broadened by G. N. Lewis to include those atoms, molecules, or ions in which at least one atom has a vacant orbital into which a pair of electrons can be accepted. Similarly, a base is regarded as an entity which possesses a pair of electrons which are not already Involved in a covalent bond. The products of acid-base interactions have been called coordination compounds, adducts, acid-base complexes, and other such names. The concept that... 

Recognition of chemical entities in text (drug names, chemical descriptors, registry numbers, common and brand names, etc.)... 

Thus, a system for the recognition of medical entities in text has to offer functionalities beyond simple string matching—namely, context-dependent disambiguation—to support the mapping of entities in text to concepts in medical ontologies. 

Recognition of the relationships between these complex compounds led to the formulation of coordination theory and the naming of coordination compounds using additive nomenclature. Each coordination compound either is, or contains, a coordination entity (or complex) that consists of a central atom to which other groups are bound. 

On the other hand, several investigators (6, 7) have taken another approach, based on pattern recognition. These dichotomous models search for agreement between dependent variables i.e., whether a chemical entity or substructure can be associated with a particular toxic property. For example, certain N-nitrosamine groups are associated with tumors in animals. Since this consideration is not dependent on a relationship between the endpoint and the dose, the quantitative term is dropped from QSAR and the effort simply named SAR. This approach is best expressed by the dependent equation ... 

---