2017/07/05 by Yoram Bachrach, Andrej Zukov-Gregoric, Bachrach, Yoram +14
Computer Science · #68T50 #Computation and Language (cs.CL) #Expert finding and Q&A systems #FOS: Computer and information sciences #I.2.6 #I.2.7 #Natural Language Processing Techniques #Topic Modeling #acm:68T50 #cs.CL #msc:68T50
paper · pdf · doi:10.48550/arxiv.1707.01378
openalex publication_date 2017/07/05 · arxiv created 2017/09/20 · arxiv updated 2017/09/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose a new attention mechanism for neural based question answering, which depends on varying granularities of the input. Previous work focused on augmenting recurrent neural networks with simple attention mechanisms which are a function of the similarity between a question embedding and an answer embeddings across time. We extend this by making the attention mechanism dependent on a global embedding of the answer attained using a separate network. We evaluate our system on InsuranceQA, a large question answering dataset. Our model outperforms current state-of-the-art results on InsuranceQA. Further, we visualize which sections of text our attention mechanism focuses on, and explore its performance across different parameter settings.