Spatial Language Representation with Multi-Level Geocoding

08/21/2020
by   Sayali Kulkarni, et al.
0

We present a multi-level geocoding model (MLG) that learns to associate texts to geographic locations. The Earth's surface is represented using space-filling curves that decompose the sphere into a hierarchy of similarly sized, non-overlapping cells. MLG balances generalization and accuracy by combining losses across multiple levels and predicting cells at each level simultaneously. Without using any dataset-specific tuning, we show that MLG obtains state-of-the-art results for toponym resolution on three English datasets. Furthermore, it obtains large gains without any knowledge base metadata, demonstrating that it can effectively learn the connection between text spans and coordinates - and thus can be extended to toponymns not present in knowledge bases.

READ FULL TEXT
research
05/11/2021

Doing Natural Language Processing in A Natural Way: An NLP toolkit based on object-oriented knowledge base and multi-level grammar base

We introduce an NLP toolkit based on object-oriented knowledge base and ...
research
04/27/2020

Multi-level neural networks for PDEs with uncertain parameters

A novel multi-level method for partial differential equations with uncer...
research
04/14/2022

Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model

Row completion is the task of augmenting a given table of text and numbe...
research
10/24/2018

Multi-level Memory for Task Oriented Dialogs

Recent end-to-end task oriented dialog systems use memory architectures ...
research
03/14/2023

Canonical Sphere Bases for Simplicial and Cubical Complexes

Sphere-bases are constructed for the ℤ_2 vector space formed by the k-di...
research
11/28/2019

All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning

The main problems of few-shot learning are how to learn a generalized re...

Please sign up or login with your details

Forgot password? Click here to reset