Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking

HLT-NAACL, pp. 1268-1278, 2016.

Cited by: 48|Bibtex|Views16
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

In this paper, we study, compare and combine two state-of-the-art approaches to automatic feature engineering: Convolution Tree Kernels (CTKs) and Convolutional Neural Networks (CNNs) for learning to rank answer sentences in a Question Answering (QA) setting. When dealing with QA, the key aspect is to encode relational information between...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments