SwissAlps at SemEval-2017 Task 3: Attention-based Convolutional Neural Network for Community Question Answering
TL
TL;DR
The method builds on a siamese CNN architecture which is extended by two attention mechanisms and achieves 7th place obtaining a MAP score of 86:24 points on the Question-Comment Similarity subtask.
Abstract
In this paper we propose a system for reranking answers for a given question. Our method builds on a siamese CNN architecture which is extended by two attention mechanisms. The approach was evaluated on the datasets of the SemEval-2017 competition for Community Question Answering (cQA), where it achieved 7th place obtaining a MAP score of 86:24 points on the Question-Comment Similarity subtask.
References12 items
1
SemEval-2017 Task 3: Community Question Answering
2
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
3
LSTM-based Deep Learning Models for non-factoid answer selection
4
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks
5