Labelling databases

Step 3. Once the Dir. Marketing approves the request to sample, implementation of the request shall be delegated by the Dir. Marketing to a Marketing Representative (Market Rep.). The Market Rep. shall check the MSDS/label database for an approved MSDS and label for the experimental sample. If an MSDS and label are available, the Market Rep. shall print out a label and an MSDS, and proceed to Step 5. 

Step 2. The Pilot Plant Director shall provide copies of all information collected in Step 1 to the MRC, who shall evaluate health and environmental risk data concerning the R D substance and update the MSDS and product label if appropriate. (Regulatory information about the experimental product is entered in the product database, which feeds the MSDS/label database, by the MRC. The MSDS Specialist prepares the new MSDS and label in accordance with the procedure for making MSDS and labels.)... 

We will consider the full issue of how to train an HMM in Section 15.1.8. For now, let us simply assume that we can calculate the transition probabilities and observation probabilities by simply counting occurrences in a labelled database. To see how the tagging operates consider the issue of resolving the classic POS homograph record. This can be a norm or a verb, and a trained HMM would tell us for instance ... 

Lee, Y. j., Lee, S., Kim, J. J., and Ko, H. J. A computational algorithm for FO contour generation in Korean developed with prosodically labeled databases using K-ToBI system. In Proceedings of the International Conference on Spoken Language Processing 1998 (1998). 

---