End-to-End Learning for Answering Structured Queries Directly over Text


Nov 17, 2018 AKBC 2019 Conference Blind Submission readers: everyone Show Bibtex
  • Keywords: structured queries, text databases, triple pattern fragments, SPARQL, question answering
  • TL;DR: Answering structured queries (e.g. SPARQL) directly over text without a database using question answering techniques.
  • Abstract: Structured queries expressed in languages (such as SQL, SPARQL, or XQuery) offer a convenient and explicit way for users to express their information needs for a number of tasks. In this work, we present an approach to answer these directly over text data without storing results in a database. We specifically look at the case of knowledge bases where queries are over entities and the relations between them. Our approach combines distributed query answering (e.g. Triple Pattern Fragments) with models built for extractive question answering. Importantly, by applying distributed querying answering we are able to simplify the model learning problem. We train models for a large portion (572) of the relations within Wikidata and achieve an average 0.70 F1 measure across all models. We also present a systematic method to construct the necessary training data for this task from knowledge graphs and describe a prototype implementation.
  • Archival status: Archival
  • Subject areas: Information Extraction, Question Answering, Databases, Semantic Web
0 Replies