@article{Yoshikawa_Mineshima_Noji_Bekki_2019, title={Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/4730}, DOI={10.1609/aaai.v33i01.33017410}, abstractNote={<p>In logic-based approaches to reasoning tasks such as Recognizing Textual Entailment (RTE), it is important for a system to have a large amount of knowledge data. However, there is a tradeoff between adding more knowledge data for improved RTE performance and maintaining an efficient RTE system, as such a big database is problematic in terms of the memory usage and computational complexity. In this work, we show the processing time of a state-of-the-art logic-based RTE system can be significantly reduced by replacing its search-based axiom injection (abduction) mechanism by that based on Knowledge Base Completion (KBC). We integrate this mechanism in a Coq plugin that provides a proof automation tactic for natural language inference. Additionally, we show empirically that adding new knowledge data contributes to better RTE performance while not harming the processing speed in this framework.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Yoshikawa, Masashi and Mineshima, Koji and Noji, Hiroshi and Bekki, Daisuke}, year={2019}, month={Jul.}, pages={7410-7417} }