SPARQL-QA-v2 system for Knowledge Base Question Answering

Accessing the large volumes of information available in public knowledge bases might be complicated for those users unfamiliar with formal languages, such as the SPARQL query language and the ontology definition languages. This issue can be overcome by providing systems able to answer questions posed in natural language on a knowledge base, a task that is called Knowledge Base Question Answering (KBQA) in the literature. More in detail, many KBQA systems aim at translating automatically questions into the corresponding SPARQL queries to be executed over the knowledge base to get the answers. Effective state-of-the-art KBQA systems are based on neural-machine translation but easily fail to recognize words that are Out Of the Vocabulary (OOV) of the training set. This is a serious issue while querying large ontologies where the list of entities is huge and easily evolves over time. In this paper, we present the SPARQL-QA-v2 system that combines in an innovative way Named Entity Linking, Named Entity Recognition, and Neural Machine Translation for addressing the problem of generating SPARQL queries from questions posed in natural language. We demonstrate empirically that SPARQL-QA-v2 is effective and resilient to OOV words and delivers state-of-the-art performance in well-known datasets for question answering over DBpedia and Wikidata knowledge bases.

Automated summary

Accessing large volumes of information in public knowledge bases can be complicated for users unfamiliar with formal languages like SPARQL. KBQA systems aim to overcome this issue by answering questions in natural language and translating them into SPARQL queries. However, current state-of-the-art KBQA systems struggle with out-of-vocabulary words, which is a serious issue when querying large ontologies.