BiMPM

Reported on 5 benchmarks across 3 tasks · 2 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Semantic Textual SimilarityonQuora Question Pairs
Accuracy· 2017-02-13
88.17
best: 92.4 (data2vec)
SOTA
Bilateral Multi-Perspective Matching for Natural Language Sentences arXiv:1702.03814
Paraphrase IdentificationonQuora Question Pairs
Accuracy· 2017-02-13
88.17
best: 92.4 (data2vec)
SOTA
Bilateral Multi-Perspective Matching for Natural Language Sentences arXiv:1702.03814
Natural Language InferenceonV-SNLI
Accuracy· 2018-06-14
86.41
best: 90.5 (MMBT)
Grounded Textual Entailment arXiv:1806.05645
Natural Language InferenceonSNLI
% Test Accuracy· 2017-02-13
87.5
best: 94.7 (UnitedSynT5 (3B))
Bilateral Multi-Perspective Matching for Natural Language Sentences arXiv:1702.03814
Natural Language InferenceonSNLI
% Train Accuracy· 2017-02-13
90.9
best: 99.7 (+ Unigram and bigram features)
Bilateral Multi-Perspective Matching for Natural Language Sentences arXiv:1702.03814