Papers with OSM

2 papers
SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalism (2025.acl-demo)

Copied to clipboard

Challenge: Existing tools to query OSM data require familiarity with complex query languages, creating barriers for non-technical users.
Approach: They propose to use a semantic bundling system to make querying OSM more accessible through intuitive scene descriptions.
Outcome: The proposed system interprets user inputs as structured representations of geospatial object configurations using fine-tuned Large Language Models (LLMs) with results displayed in an interactive map interface.
Location Name Extraction from Targeted Text Streams using Gazetteer-based Statistical Language Models (C18-1)

Copied to clipboard

Challenge: Location name extraction tool (LNEx) is a statistical language for extracting location names from informal and unstructured social media data.
Approach: They propose a location name extraction tool that extracts location names from social media data . they use n-gram statistics and location-related dictionaries to evaluate an observed n in targeted text .
Outcome: The proposed tool outperforms state-of-the-art taggers on 4,500 event-specific tweets . it improves the average F-Score by 33-179%, outperforming all tagger .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations