Fine and Ultra-Fine Entity Type Embeddings for Question Answering

Abstract

We describe our system for the SeMantic AnsweR (SMART) Type prediction task 2020 for both the DBpedia and Wikidata Question Answer Type datasets. The SMART task challenge introduced fine-grained and ultra-fine entity typing to question answering by releasing two datasets for question classification using DBpedia and Wikidata classes. We propose a flexible framework for both entity types using paragraph vectors and word embeddings to obtain high quality contextualized question representations. We augment the document similarity provided by paragraph vectors with semantic modeling and sentence alignment using word embeddings. For the answer category prediction, we achieved a maximum accuracy score of 85% for Wikidata and 88% for DBpedia. For the answer types prediction, we achieved a maximum MRR of 40% for Wikidata and a maximum nDCG@5 of 54% for DBpedia datasets.