Natural-language recognition

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. 

Hodge, G., Nelson, T., and Vleduts-Stokolov, N. 1989. Automatic recognition of chemical names in natural language text. Paper presented at the 198th American Chemical Society National Meeting, Dallas, TX, April 7-9. 

Kim, J.-D., Ohta, T., Tsuruoka, Y., Tateisi, Y., Collier, N. 2004. Introduction to the Bio-Entity Recognition Task at JNLPBA. Proceedings of the International Workshop on Natural Language Processing in Biomedicine and its Applications (JNLPBA-04), pp. 70-75. 

Copies of the TNO peroxide test databases have been provided to E27.07 and the new versions of CHETAH are expected to contain an extensive database as well as pattern-recognition techniques for estimating the hazard of new materials. The CHETAH software will continue to rely on bond energy data and group contribution calculations to estimate energy release potential. Hopefully, the new versions will also incorporate natural language expert system-type front ends so that the CHETAH program(s) will see expanded use in both analytical and tutorial modes. Copies of the LEILA (8) dissertation have also been provided to E27.07 as an example of an expert system approach to selection and use of appropriate theories and computational methods for the solution of problems in chemical kinetics. 

JURAFSKY, D., AND MARTIN, J. H. Speech and Language Processing An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice-Hall, 2000. 

Morphisms are related to faithful maps, which lead naturally to the notion of a faithfully embedded closed subset. Such subsets provide an appropriate language for an attempt to establish so-called recognition theorems. These theorems deal with the question of which schemes are quotient schemes of thin schemes. We shall come back to recognition theorems and their role in scheme theory later in this preface. 

We have seen above a simple synthetic grammar wherein the productions are directly derived from chemical reactions and the resulting language of synthesiz-able structures is the set of all molecules that can be synthesized from some specified precursor by application of the reactions. In the simple case of 1-alkanols and 1-bromoalkanes the recognition problem is trivial—we can answer it in a time proportional to the length of the molecule. We are naturally curious as to what is the minimally complex grammar needed to... 

---