Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
This work addresses a specific bottleneck in KBQA for users needing accurate answers to ordinal questions, representing an incremental advancement over existing methods.
The paper tackles the problem of embedding-based Knowledge Base Question Answering (KBQA) models lacking numerical reasoning skills, particularly for ordinal constrained questions, by proposing NT-NSM, a framework that enhances NSM with numerical reasoning, resulting in substantial performance improvements on benchmarks.
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.