An Attention Mechanism for Answer Selection Using a Combined Global and Local View

07/05/2017
by   Yoram Bachrach, et al.
0

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.

READ FULL TEXT
research
09/15/2017

Query-based Attention CNN for Text Similarity Map

In this paper, we introduce Query-based Attention CNN(QACNN) for Text Si...
research
08/08/2018

Learning to Focus when Ranking Answers

One of the main challenges in ranking is embedding the query and documen...
research
06/14/2019

Microsoft AI Challenge India 2018: Learning to Rank Passages for Web Question Answering with Deep Attention Networks

This paper describes our system for The Microsoft AI Challenge India 201...
research
06/12/2018

Focused Hierarchical RNNs for Conditional Sequence Processing

Recurrent Neural Networks (RNNs) with attention mechanisms have obtained...
research
06/03/2018

Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction

Attention is typically used to select informative sub-phrases that are u...
research
12/15/2021

LongT5: Efficient Text-To-Text Transformer for Long Sequences

Recent work has shown that either (1) increasing the input length or (2)...
research
03/23/2016

Recurrent Neural Network Encoder with Attention for Community Question Answering

We apply a general recurrent neural network (RNN) encoder framework to c...

Please sign up or login with your details

Forgot password? Click here to reset