Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings

Apoorv Saxena, Aditay Tripathi, Partha Talukdar


Abstract
Knowledge Graphs (KG) are multi-relational graphs consisting of entities as nodes and relations among them as typed edges. Goal of the Question Answering over KG (KGQA) task is to answer natural language queries posed over the KG. Multi-hop KGQA requires reasoning over multiple edges of the KG to arrive at the right answer. KGs are often incomplete with many missing links, posing additional challenges for KGQA, especially for multi-hop KGQA. Recent research on multi-hop KGQA has attempted to handle KG sparsity using relevant external text, which isn’t always readily available. In a separate line of research, KG embedding methods have been proposed to reduce KG sparsity by performing missing link prediction. Such KG embedding methods, even though highly relevant, have not been explored for multi-hop KGQA so far. We fill this gap in this paper and propose EmbedKGQA. EmbedKGQA is particularly effective in performing multi-hop KGQA over sparse KGs. EmbedKGQA also relaxes the requirement of answer selection from a pre-specified neighborhood, a sub-optimal constraint enforced by previous multi-hop KGQA methods. Through extensive experiments on multiple benchmark datasets, we demonstrate EmbedKGQA’s effectiveness over other state-of-the-art baselines.
Anthology ID:
2020.acl-main.412
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4498–4507
Language:
URL:
https://aclanthology.org/2020.acl-main.412
DOI:
10.18653/v1/2020.acl-main.412
Bibkey:
Cite (ACL):
Apoorv Saxena, Aditay Tripathi, and Partha Talukdar. 2020. Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4498–4507, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings (Saxena et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.412.pdf
Video:
 http://slideslive.com/38929421
Code
 malllabiisc/EmbedKGQA +  additional community code