Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks

TL;DR

This paper introduces a neural network model using Gaussian mixtures to embed locations in a continuous space, improving geolocation accuracy and lexical dialectology analysis from Twitter data.

Contribution

It presents a novel neural network approach with mixture density outputs for continuous location embedding, outperforming traditional methods in geolocation and dialectology tasks.

Findings

Outperforms regression-based geolocation methods

Provides better uncertainty estimates in location predictions

Effective in lexical dialectology using Twitter data

Abstract

We propose a method for embedding two-dimensional locations in a continuous vector space using a neural network-based model incorporating mixtures of Gaussian distributions, presenting two model variants for text-based geolocation and lexical dialectology. Evaluated over Twitter data, the proposed model outperforms conventional regression-based geolocation and provides a better estimate of uncertainty. We also show the effectiveness of the representation for predicting words from location in lexical dialectology, and evaluate it using the DARE dataset.