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

2017/08/14 by Afshin Rahimi, Timothy Baldwin, Rahimi, Afshin +3
Computer Science · #Authorship Attribution and Profiling #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Social and Information Networks (cs.SI) #Speech Recognition and Synthesis #cs.CL #cs.IR #cs.SI

paper · pdf · doi:10.48550/arxiv.1708.04358

Conference on Empirical Methods in Natural Language Processing (EMNLP 2017) September 2017, Copenhagen, Denmark

arxiv created 2017/08/14 · openalex publication_date 2017/08/14 · arxiv updated 2017/08/16 · openalex created_date 2022/10/06 · openalex updated_date 2026/07/28

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.

Related

• A Neural Model for User Geolocation and Lexical Dialectology
• Density Estimation for Geolocation via Convolutional Mixture Density Network
• Fine-grained Geolocation Prediction of Tweets with Human Machine Collaboration
• Inferring the Origin Locations of Tweets with Quantitative Confidence
• Geolocation differences of language use in urban areas