Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions

Mai, Gengchen; Janowicz, Krzysztof; Zhu, Rui; Cai, Ling; Lao, Ni

doi:10.5194/agile-giss-2-8-2021

Cited by 49 publications

(14 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We fuse geo-knowledge and GPT by encoding the geo-knowledge of location descriptions into a prompt and feed it to a GPT model to guide its behavior. Learning from previous research on geographic question-answering (Mai et al 2021), we create the prompt in the form of a series of question-answering statements based on the geo-knowledge of location description categories and their examples shown in Table 1. A snippet of the prompt is provided in Table 2, and we also include the full prompt in the supplementary Table S1 which contains 22 tweet examples in 11 categories (i.e., two examples per category).…”

Section: Fusing Geo-knowledge and Gptmentioning

confidence: 99%

Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages

Hu,

Mai,

Cundy

et al. 2023

International Journal of Geographical Information Science

Self Cite

View full text Add to dashboard Cite

Social media messages posted by people during natural disasters often contain important location descriptions, such as the locations of victims. Recent research has shown that many of these location descriptions go beyond simple place names, such as city names and street names, and are difficult to extract using typical named entity recognition (NER) tools. While advanced machine learning models could be trained, they require large labeled training datasets that can be time-consuming and labor-intensive to create. In this work, we propose a method that fuses geoknowledge of location descriptions and a Generative Pre-trained Transformer (GPT) model, such as ChatGPT and GPT-4. The result is a geo-knowledge-guided GPT model that can accurately extract location descriptions from disaster-related social media messages. Also, only 22 training examples encoding geo-knowledge are used in our method. We conduct experiments to compare this method with nine alternative approaches on a dataset of tweets from Hurricane Harvey. Our method demonstrates an over 40% improvement over typically used NER approaches. The experiment results also show that geo-knowledge is indispensable for guiding the behavior of GPT models. The extracted location descriptions can help disaster responders reach victims more quickly and may even save lives.

show abstract

Section: Fusing Geo-knowledge and Gptmentioning

confidence: 99%

Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages

Hu,

Mai,

Cundy

et al. 2023

International Journal of Geographical Information Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…GeoQA is a sub-domain of Question Answering (QA) that focuses on generating answers to geographic questions [9,23]. Diverse information sources such as textual information [7,24], geodatabases [3], and spatially-enabled knowledge bases [8] have been investigated to enable GeoQA.…”

Section: Related Workmentioning

confidence: 99%

Translating Place-Related Questions to GeoSPARQL Queries

Hamzei

Tomko

Winter

2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

Many place-related questions can only be answered by complex spatial reasoning, a task poorly supported by factoid question retrieval. Such reasoning using combinations of spatial and non-spatial criteria pertinent to place-related questions is increasingly possible on linked data knowledge bases. Yet, to enable question answering based on linked knowledge bases, natural language questions must first be re-formulated as formal queries. Here, we first present an enhanced version of YAGO2geo, the geospatially-enabled variant of the YAGO2 knowledge base, by linking and adding more than one million places from OpenStreetMap data to YAGO2. We then propose a novel approach to translate the place-related questions into logical representations, theoretically grounded in the core concepts of spatial information. Next, we use a dynamic template-based approach to generate fully executable GeoSPARQL queries from the logical representations. We test our approach using the Geospatial Gold Standard dataset and report substantial improvements over existing methods.

show abstract

“…Encoding polygon geometries into the embedding space is a logical next step. It is very useful for several geospatial tasks which require comparing polygon geometries such as geographic entity alignment (Trisedya et al 2019), spatial topological reasoning (Regalia et al 2019), and geographic question answering (Mai et al 2019b(Mai et al , 2020a(Mai et al , 2021.…”

Section: Polygonmentioning

confidence: 99%

A Review of Location Encoding for GeoAI: Methods and Applications

Mai,

Janowicz,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A common need for artificial intelligence models in the broader geoscience is to represent and encode various types of spatial data, such as points (e.g., points of interest), polylines (e.g., trajectories), polygons (e.g., administrative regions), graphs (e.g., transportation networks), or rasters (e.g., remote sensing images), in a hidden embedding space so that they can be readily incorporated into deep learning models. One fundamental step is to encode a single point location into an embedding space, such that this embedding is learning-friendly for downstream machine learning models such as support vector machines and neural networks. We call this process location encoding. However, there lacks a systematic review on the concept of location encoding, its potential applications, and key challenges that need to be addressed. This paper aims to fill this gap. We first provide a formal definition of location encoding, and discuss the necessity of location encoding for GeoAI research from a machine learning perspective. Next, we provide a comprehensive survey and discussion about the current landscape of location encoding research. We classify location encoding models into different categories based on their inputs and encoding methods, and compare them based on whether they are parametric, multi-scale, distance preserving, and direction aware. We demonstrate that existing location encoding models can be unified under a shared formulation framework. We also discuss the application of location encoding for different types of spatial data. Finally, we point out several challenges in location encoding research that need to be solved in the future.

show abstract

Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions

Cited by 49 publications

References 49 publications

Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages

Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages

Translating Place-Related Questions to GeoSPARQL Queries

A Review of Location Encoding for GeoAI: Methods and Applications

Contact Info

Product

Resources

About