The paper describes a computational approach for guessing the meanings of previously unaccounted words in an implemented system for natural language processing. Interested in comparing the results to what is known about human guessing, it reviews a largely educational approach, partially based on cognitive psychology, to teaching humans, mostly children, to acquire new vocabulary from contextual clues, as well as the lexicographic efforts to account for neologisms. It then goes over the previous NLP efforts in processing new words and establishes the difference—mostly, much richer semantic resources—of the proposed approach. Finally, the results of a computer experiment that guesses the meaning of a non-existent word, placed as the direct object of 100 randomly selected verbs, from the known meanings of these verbs, with methods of the ontological semantics technology, are presented and discussed. While the results are promising percentage-wise, ways to improve them within the approach are briefly outlined.

Keywords: lexical blends, neologisms, computational lexicography, social media, Twitter. We present a method for identifying English lexical blends — words such as complisult (compliment + insult) and globesity (global + obesity) — from social media, specifically Twitter. Our method is based on observations about words and phrases that are commonly used to introduce new words and corpus patterns that are often used to describe the meaning of lexical blends, and leverages the massive volume of data that is readily-available for analysis through Twitter. We run our method for 5 weeks and identify 976 candidate lexical blends; analysis of a sample of these candidates indicates that approximately 57 % are blends. We further discuss a small number of blends identified by our method that are in regular usage on Twitter but which are not recorded in any of a number of dictionaries searched. 1. Lexical blends Lexical blends are words such as glamping (glamorous + camping), sexting (sex + texting), and sleepiphany (sleep + epiphany) that are formed by combining a prefix of one source word with a suffix of another. Blends exhibit some variation with examples being observed in which neither source word is, one source word is, and both source words are entirely present