Question Answering on Scholarly Knowledge Graphs
This addresses the challenge of querying scholarly knowledge for researchers, but it is incremental as it builds on existing BERT methods for a specific domain.
The authors tackled the problem of answering questions on scholarly knowledge graphs, which is difficult due to unstructured content, by presenting JarvisQA, a BERT-based system that retrieves direct answers from tabular data in articles, showing an improvement of two to three folds in performance compared to related methods.
Answering questions on scholarly knowledge comprising text and other artifacts is a vital part of any research life cycle. Querying scholarly knowledge and retrieving suitable answers is currently hardly possible due to the following primary reason: machine inactionable, ambiguous and unstructured content in publications. We present JarvisQA, a BERT based system to answer questions on tabular views of scholarly knowledge graphs. Such tables can be found in a variety of shapes in the scholarly literature (e.g., surveys, comparisons or results). Our system can retrieve direct answers to a variety of different questions asked on tabular data in articles. Furthermore, we present a preliminary dataset of related tables and a corresponding set of natural language questions. This dataset is used as a benchmark for our system and can be reused by others. Additionally, JarvisQA is evaluated on two datasets against other baselines and shows an improvement of two to three folds in performance compared to related methods.