"Old is gold: Linguistic Driven Approach for Entity and Relation Linking of Short Text"

At the DICE colloquium on Friday, July 19th, 2019, Ria Hari Gusmita presented a paper “Old is gold: Linguistic Driven Approach for Entity and Relation Linking of Short Text”  by Ahmad Sakor, Isaiah Onando Mulang', Kuldeep Singh, Saeedeh Shekarpour, Maria-Esther Vidal, Jens Lehmann, and Sören Auer, accepted at NAACL2019.

This paper describes a framework for jointly linking entities and relations within a short text into their mentions of a knowledge graph using a light-weight linguistic approach. The framework benefits a knowledge graph built from the fusion of DBpedia and Wikidata and enriched by traditional linguistic resource and semantic dictionaries. Furthermore, it is suitable for low-resource languages as it does not require training data.

Abstract:

Short texts challenge NLP tasks such as named entity recognition, disambiguation, linking and relation inference because they do not provide sufficient context or are partially malformed (e.g. wrt capitalization, long tail entities, implicit relations). In this work, we present the Falcon approach which effectively maps entities and relations within a short text to its mentions of a background knowledge graph. Falcon overcomes the challenges of a short text using a light-weight linguistic approach relying on a background knowledge graph. Falcon performs joint entity and relation linking of a short text by leveraging several fundamental principles of English morphology (e.g. compounding, headword identification) and utilizes an extended knowledge graph created by merging entities and relations from various knowledge sources. It uses the context of entities for finding relations and does not require training data. Our empirical study using several standard benchmarks and datasets show that Falcon significantly outperforms state-of-the-art entity and relation linking for short text query inventories.

 

 

527efb333