Papers with SPOT
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. |
Adding SPICE to Life: Speaker Profiling in Multiparty Conversations (2024.lrec-main)
Copied to clipboard
| Challenge: | Prior studies assumed the speaker’s persona’s immediate availability, a premise not universally applicable. |
| Approach: | They propose to synthesize persona attributes for each dialogue participant by combining three core tasks: persona discovery, persona-type identification, and persona value extraction. |
| Outcome: | The proposed task synthesizes persona attributes for each dialogue participant . the resulting model is compared against a baseline model and the proposed model is robust. |
SPOT: Zero-Shot Semantic Parsing Over Property Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Graphs (KGs) are becoming increasingly popular as a means of storing structured data. |
| Approach: | They propose a method to generate training data for semantic parsing over Property Graphs without human annotations by matching tree patterns to the KG and paraphrasing the query program with an LLM. |
| Outcome: | The proposed method generates training data for parsing over Property Graphs without human annotations on two property graph benchmarks utilizing the Cypher query language. |