Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering
This work addresses answer triggering, a critical component for real-world question answering systems, but appears incremental as it builds on prior work by Yang et al. (2015).
The paper tackles the problem of answer triggering in question answering systems by proposing a hierarchical gated recurrent neural tensor (HGRNT) model, achieving an F-value of 42.6% which surpasses the baseline by over 10%.
In this paper, we focus on the problem of answer triggering ad-dressed by Yang et al. (2015), which is a critical component for a real-world question answering system. We employ a hierarchical gated recurrent neural tensor (HGRNT) model to capture both the context information and the deep in-teractions between the candidate answers and the question. Our result on F val-ue achieves 42.6%, which surpasses the baseline by over 10 %.