MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension

28 Jul 2017 Boyuan Pan Hao Li Zhou Zhao Bin Cao Deng Cai Xiaofei He

Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and name entity of the words, which are very crucial to the quality of encoding... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Question Answering SQuAD1.1 MEMEN (single model) EM 78.234 # 73
F1 85.344 # 77
Question Answering SQuAD1.1 MEMEN (single model) EM 78.234 # 73
F1 85.344 # 77
Question Answering SQuAD1.1 MEMEN (ensemble) EM 75.370 # 98
F1 82.658 # 105
Question Answering TriviaQA MEMEN EM 43.16 # 5
F1 46.90 # 7

Methods used in the Paper