A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data

ACL 2016 Adam TrischlerZheng YeXingdi YuanJing HePhillip BachmanKaheer Suleman

Understanding unstructured text is a major goal within natural language processing. Comprehension tests pose questions based on short text passages to evaluate such understanding... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Question Answering MCTest-160 syntax, frame, coreference, and word embedding features Accuracy 75.27% # 1
Question Answering MCTest-500 syntax, frame, coreference, and word embedding features Accuracy 69.94% # 2
Question Answering MCTest-500 Parallel-Hierarchical Accuracy 71% # 1