Bilateral Multi-Perspective Matching for Natural Language Sentences

13 Feb 2017Zhiguo WangWael HamzaRadu Florian

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Paraphrase Identification Quora Question Pairs BiMPM Accuracy 88.17 # 8
Natural Language Inference SNLI BiMPM % Test Accuracy 87.5 # 19
% Train Accuracy 90.9 # 32
Parameters 1.6m # 2
Natural Language Inference SNLI BiMPM Ensemble % Test Accuracy 88.8 # 12
% Train Accuracy 93.2 # 20
Parameters 6.4m # 2

Methods used in the Paper