Learning to Explain Non-Standard English Words and Phrases

TL;DR

This paper introduces a neural sequence-to-sequence model that automatically explains new non-standard English words and phrases using a large dataset from UrbanDictionary, advancing beyond keyword matching methods.

Contribution

It presents a novel dual encoder neural model that generates explanations for unseen non-standard expressions based on context, improving automatic understanding of slang.

Findings

Model produces reasonable definitions for new expressions

Uses large crowdsourced dataset from UrbanDictionary

Dual encoder approach effectively captures context and expression features

Abstract

We describe a data-driven approach for automatically explaining new, non-standard English expressions in a given sentence, building on a large dataset that includes 15 years of crowdsourced examples from UrbanDictionary.com. Unlike prior studies that focus on matching keywords from a slang dictionary, we investigate the possibility of learning a neural sequence-to-sequence model that generates explanations of unseen non-standard English expressions given context. We propose a dual encoder approach---a word-level encoder learns the representation of context, and a second character-level encoder to learn the hidden representation of the target non-standard expression. Our model can produce reasonable definitions of new non-standard English expressions given their context with certain confidence.