Search Results for author: Sebastian Brarda

Found 2 papers, 1 papers with code

Sequential Attention: A Context-Aware Alignment Function for Machine Reading

no code implementations WS 2017 Sebastian Brarda, Philip Yeres, Samuel R. Bowman

In this paper we propose a neural network model with a novel Sequential Attention layer that extends soft attention by assigning weights to words in an input sequence in a way that takes into account not just how well that word matches a query, but how well surrounding words match.

Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.