SlangNet: A WordNet like resource for English Slang

SlangNet: A WordNet like Resource for English Slang Shehzaad Dhuliawala, Diptesh Kanojia, Pushpak Bhattacharyya Indian Institute of Technology Bombay Mumbai, India {shehzaadzd, diptesh, pb}@cse.iitb.ac.in Abstract We present a WordNet like structured resource for slang words and neologisms on the internet. The dynamism of language is often an indication that current language technology tools trained on today’s data, may not be able to process the language in the future. Our resource could be (1) used to augment the WordNet, (2) used in several Natural Language Processing (NLP) applications which make use of noisy data on the internet like Information Retrieval and Web Mining. Such a resource can also be used to distinguish slang word senses from conventional word senses. To stimulate similar innovations widely in the NLP community, we test the efficacy of our resource for detecting slang using standard bag of words Word Sense Disambiguation (WSD) algorithms (Lesk and Extended Lesk) for English data on the internet. Keywords: Slang, WordNet, Informal Text, Lexicon 1. Introduction The internet is an ardent platform for users to interact. It has given rise to several public forums and bulletins where users communicate with each other. The fact that the inter- net is global, allows for this userbase to not be confined to a particular region or location. Users from different coun- tries, of different races and languages can speak with each other. This vast diversity has allowed language to morph on the internet. One often notices words, phrases and col- loquialisms which pop into existence and are used in huge volumes over the internet. The following examples better illustrate the need to annotate novel senses for the following words: Sick (Adj): Used in a positive sense to denote something that is nice or awesome. Eg. The band’s new album is sick. Bae (Noun): Used to describe something or someone you like or find attractive. Also used to describe your ro- mantic partner. Eg. Don’t you hate it when your bae flirts with another guy. Text (Verb): Sending a short message over a mobile de- vice. Eg. Can you text me when you reach home? This motivates us to create a resource that could contribute to various NLP applications which work on noisy data col- lected from the internet. We utilize a popular online re- source, called Urban Dictionary, as a reference to create SlangNet. Urban Dictionary is an online, crowd sourced slang dictio- nary. It allows users to input definitions and examples for common slang words on the internet. The website has a user upvote and downvote system which decides the popu- larity of the definition. The site has a user base of 18 mil- lion unique readers and hosts about seven million words and phrases along with their definitions1. Due to no inter- nal or external validation, Urban Dictionary fails to control 1https://en.wikipedia.org/wiki/Urban_ Dictionary the quality of the definitions. Swerdfeger (Online)2 observe that the resource suffers from redundancy, self-references, opinions of users, spelling errors, grammatical errors, con- trasting definitions etc. The shortcomings of …

Content truncated to 500 words