Marie and BERT─A Knowledge Graph Embedding Based Question Answering System for Chemistry

Abstract

This paper presents a novel Knowledge Graph Question Answering (KGQA) system for chemistry implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the system operates on multiple embedding spaces, which use various embedding methods, and queries the embedding spaces in parallel. With the answers returned from multiple embedding spaces, the system leverages a score alignment model to adjust the answer scores and re-rank the answers. Further, the system implements an algorithm to derive implicit multi-hop relations to handle the complexities of deep ontologies and improve multi-hop question answering. The system also implements a BERT-based bi-directional entity-linking model to enhance the robustness and accuracy of the entity-linking module. The system uses a joint numerical embedding model to handle numerical filtering questions efficiently. Further, it can invoke semantic agents to perform dynamic calculations autonomously. Finally, the KGQA system handles numerous chemical reaction mechanisms using semantic parsing supported by a Linked Data Fragment server. This paper evaluates the accuracy of each module within the KGQA system with a chemistry question dataset.