Antonio Zamora


Antonio Zamora is a consultant in the fields of computer programming, chemical information science, and computational linguistics who worked about chemical search systems and automatic spelling correction algorithms.

Career

Zamora studied chemistry at the University of Texas, and served in the U.S. Army during the Vietnam era from 1962 to 1965. He studied medical technology at the Medical Field Service School in Fort Sam Houston and worked in hematology at Brooke Army Medical Center.
After concluding his military service, he worked at Chemical Abstracts Service in Columbus, Ohio as an editor of one of the first computer-produced publications in the United States. While working for CAS, he gained a master's degree in Computer Science from Ohio State University, and began working in their programming department; eventually he transferred to the research department where he was able to combine his chemical background with programming.
He contributed to the development of a chemical registry system, chemical structure input systems, devised an algorithm for determining the Smallest Set of Smallest Rings, a cheminformatics term for the minimal cycle basis of a molecular graph, experimental automatic abstracting, indexing programs, and spelling aid algorithms.
In 1982 he joined IBM Corporation as a senior programmer working on spell checkers and multilingual information retrieval tools.
After his retirement from IBM in 1996, Zamora established Zamora Consulting, LLC and worked as a consultant for the American Chemical Society, the National Library of Medicine, and the US Department of Energy to support semantic enhancements for search engines.

Post-retirement

In his retirement Zamora has also self-published a science fiction book, and several small books while investigating the Carolina Bays; in his 2017 paper "A model for the geomorphology of the Carolina Bays" he proposed that the "Carolina Bays are the remodeled remains of oblique conical craters formed on ground liquefied by the seismic shock waves of secondary impacts of glacier ice boulders ejected by an extraterrestrial impact on the Laurentide Ice Sheet". His research was based on geometrical analysis of the Carolina Bays using Google Earth in combination with LiDAR data. The theory is not widely accepted. Many other theories have been proposed to account for their formation..

SPEEDCOP project

Zamora carried out pioneering research on the automatic spelling correction SPEEDCOP project ; the project was supported by National Science Foundation at Chemical Abstracts Service and extracted over 50,000 misspellings from approximately 25,000,000 words of text from seven scientific and scholarly databases.
The purpose of the project was to automatically correct spelling errors, predominantly typing errors, in a database of scientific abstracts. For each word in a dictionary, a key is computed consisting of the first letter, followed by the consonant letters in order of occurrence, followed by the vowel letters in order of occurrence, each letter recorded once only, e.g. inoculation will produce a key INCLTOUA, the keys are sorted in order. The key of each word in the text is compared with the dictionary keys and if no exact match is found it compares with keys either side to find a probable match. The use of the key reduces the portion of the dictionary that has to be searched.

Awards

Papers