Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions. This paper proposes a new embedding-based KBQA framework which particularly takes numerical reasoning into account. We present NumericalTransformer on top of NSM, a state-of-the-art embedding-based KBQA model, to create NT-NSM. To enable better training, we propose two pre-training tasks with explicit numerical-oriented loss functions on two generated training datasets and a template-based data augmentation method for enriching ordinal constrained QA dataset. Extensive experiments on KBQA benchmarks demonstrate that with the help of our training algorithm, NT-NSM is empowered with numerical reasoning skills and substantially outperforms the baselines in answering ordinal constrained questions.
@article{arxiv.2112.06109,
title = {Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models},
author = {Yu Feng and Jing Zhang and Xiaokang Zhang and Lemao Liu and Cuiping Li and Hong Chen},
journal= {arXiv preprint arXiv:2112.06109},
year = {2022}
}