DeepAI AI Chat
Log In Sign Up

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

08/14/2017
by   Afshin Rahimi, et al.
0

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.

READ FULL TEXT

page 7

page 8

10/17/2017

Specialising Word Vectors for Lexical Entailment

We present LEAR (Lexical Entailment Attract-Repel), a novel post-process...
12/20/2014

Word Representations via Gaussian Embedding

Current work in lexical distributed representations maps each word to a ...
05/08/2017

Density Estimation for Geolocation via Convolutional Mixture Density Network

Nowadays, geographic information related to Twitter is crucially importa...
06/03/2016

Learning Stylometric Representations for Authorship Analysis

Authorship analysis (AA) is the study of unveiling the hidden properties...
08/22/2020

Approximation of probability density functions via location-scale finite mixtures in Lebesgue spaces

The class of location-scale finite mixtures is of enduring interest both...
05/31/2020

A Unified Feature Representation for Lexical Connotations

Ideological attitudes and stance are often expressed through subtle mean...