Simple Models for Word Formation in Slang

Abstract

We propose generative models for three types of extra-grammatical word formation phenomena abounding in English slang: Blends, Clippings, and Reduplicatives. Adopting a datadriven approach coupled with linguistic knowledge, we propose simple models with state of the art performance on human annotated gold standard datasets. Overall, our models reveal insights into the generative processes of word formation in slang -insights which are increasingly relevant in the context of the rising prevalence of slang and non-standard varieties on the Internet.

Making “fetch” happen: The influence of social and linguistic context on nonstandard word growth and decline

“…We also provide a distribution of the words across word generation categories in Table 3, including compounds and clippings in similar proportions to prior work (Kulkarni and Wang, 2018). Because the growth and decline words exhibit similar proportions of category counts, we do not ex- pect that this will be a significant confound in differentiating growth from decline.…”

How Slang Contributes to Euphemism in Communication: A Case Study of Widal Slang Language (WSL) of Sundanese Society in Sukabumi, West Java Indonesia

“…Some researchers have conducted studies on slang language. Kulkarni and Wang [2] have analyzed the slang word formation in English. They proposed three types of word formation in English Slang; blend, clipping, and reduplicative.…”

Slang Detection and Identification

“…An independent line of work has explored generative models (Kulkarni and Wang, 2018) for slang word formation that captures processes such as blending, clipping, and reduplication. This work uses long short-term memory (LSTM) (Hochreiter and Schmidhuber, 1997) models to generate slang words in terms of string components according to type-sensitive characteristics.…”