USE

Reported on 4 benchmarks across 2 tasks · 2 papers

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

Computer Code3 results

Code SearchonPACS-CoNaLa
MRR· 2020-08-27
0.181
best: 0.351 (Ensemble:USE-tuned+NCS)
Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent arXiv:2008.12193
Code SearchonPACS-StaQC-py
MRR· 2020-08-27
0.104
best: 0.126 (Ensemble:USE-tuned+NCS)
Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent arXiv:2008.12193
Code SearchonPACS-SO-DS
MRR· 2020-08-27
0.244
best: 0.323 (Ensemble:USE-tuned+NCS)
Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent arXiv:2008.12193

Natural Language Processing1 result

Subjectivity AnalysisonSUBJ
Accuracy· 2018-03-29
93.9
best: 97.34 (RoBERTa+DualCL)
Universal Sentence Encoder arXiv:1803.11175