Technical terminology: some linguistic properties and an algorithm for identification in text

Abstract

This paper identifies some linguistic properties of technical terminology, and uses them to formulate an algorithm for identifying technical terms in running text. The grammatical properties discussed are preferred phrase structures: technical terms consist mostly of noun phrases containing adjectives, nouns, and occasionally prepositions; rerely do terms contain verbs, adverbs, or conjunctions. The discourse properties are patterns of repetition that distinguish noun phrases that are technical terms, especially those multi-word phrases that constitute a substantial majority of all technical vocabulary, from other types of noun phrase.The paper presents a terminology indentification algorithm that is motivated by these linguistic properties. An implementation of the algorithm is described; it recovers a high proportion of the technical terms in a text, and a high proportaion of the recovered strings are vaild technical terms. The algorithm proves to be effective regardless of the domain of the text to which it is applied.

Disambiguating proteins, genes, and RNA in text: a machine learning approach

“…This filtering step eliminates only 0.9% of the valid gene and protein names from consideration and significantly increases the accuracy of the recognized terms. It is possible to replace this simple term extractor with a more sophisticated method, relying on frequency and distributional information (Justeson and Katz, 1995) and complementing that with techniques that utilize approximate string matching to identify term variants and new terms similar to old ones, such as the method proposed by Krauthammer et al (2000) specifically for biological terms.…”

Tagging Scientific Publications Using Wikipedia and Natural Language Processing Tools

“…We drop all entries according to this heuristic rule. Naturally, many far more sophisticated algorithms can be employed here, e.g., matching grammatical pattern devised to select true keywords, which could be employed, when the knowledge about the part-of-speech classification is available [12,13]. However, the simple stopword method worked well enough for us, especially that we are mostly aiming at labels for further applications in machine learning and hence we can afford having certain fraction of "bogus labels".…”

Relation Extraction for Open and Closed Domain Question Answering

“…a dependency pattern with semantic (UMLS) class labels for ARG1 and ARG2. To find the appriate semantic label for a complex argument, we first extract its main term using a linguistic filter adapted from (Justeson and Katz, 1995). The filter extracts a sub-string of the argument that matches the following POS-tag regular expression:…”