Transformer Based Geocoding
This work addresses geocoding for applications needing location prediction from text, but it is incremental as it applies an existing transformer method to a specific domain.
The paper tackled geocoding from free text by framing it as a sequence-to-sequence problem and trained a T5 transformer model on geo-tagged wikidump data, achieving a model with publicly available code and checkpoints.
In this paper, we formulate the problem of predicting a geolocation from free text as a sequence-to-sequence problem. Using this formulation, we obtain a geocoding model by training a T5 encoder-decoder transformer model using free text as an input and geolocation as an output. The geocoding model was trained on geo-tagged wikidump data with adaptive cell partitioning for the geolocation representation. All of the code including Rest-based application, dataset and model checkpoints used in this work are publicly available.