Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering

25 Jul 2017 Yi Tay Luu Anh Tuan Siu Cheung Hui

The dominant neural architectures in question answer retrieval are based on recurrent or convolutional encoders configured with complex word matching layers. Given that recent architectural innovations are mostly new word interaction layers or attention-based matching mechanisms, it seems to be a well-established fact that these components are mandatory for good performance... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Question Answering SemEvalCQA HyperQA P@1 0.809 # 1
MAP 0.795 # 1
Question Answering TrecQA HyperQA MAP 0.770 # 4
MRR 0.825 # 3
Question Answering WikiQA HyperQA MAP 0.712 # 4
MRR 0.727 # 4
Question Answering YahooCQA CNN P@1 0.413 # 7
MRR 0.632 # 7
Question Answering YahooCQA HyperQA P@1 0.683 # 2
MRR 0.801 # 3
Question Answering YahooCQA LSTM P@1 0.465 # 6
MRR 0.669 # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet