Enhancing Question Answering over Knowledge Base Using Dynamical Relation Reasoning

Cheng, Liao; Chen, Ziheng; Ren, Jiangtao

doi:10.1109/ijcnn48605.2020.9207428

Cited by 3 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows the workflow of the proposed method to translate place-related questions to structured queries 4 . The workflow starts with extracting encodings to identify and annotate place-related semantics.…”

Section: Methodsmentioning

confidence: 99%

“…They produced GeoSPARQL queries out of the parsing results using a dynamic approach for query generation, yet the queries were not directly executable, as they lacked ontology mapping and concept identification. While recent studies in translating open-domain questions to structured queries [e.g., 32,22,4] show that DNN models perform much better in comparison to traditional rule-based methods, the small Gold Standard dataset seems to be insufficient for training a DNN model. Consequently, the method proposed by [27] performed better over the same dataset.…”

Section: Related Workmentioning

confidence: 99%

“…http://overpass-turbo.eu/ 2 OSM data keys: https://wiki.openstreetmap.org/wiki/Category:Key_descriptions 3 Available at https://github.com/hamzeiehsan/Questions-To-GeoSPARQL4 Demo is available at: https://tomko.org/demo/…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Methodsmentioning

confidence: 99%