ML Research Wiki / Benchmarks / Natural Language Inference / FarsTail

FarsTail

Natural Language Inference Benchmark

Performance Over Time

📊 Showing 10 results | 📏 Metric: % Test Accuracy

Top Performing Models

Rank Model Paper % Test Accuracy Date Code
1 mBERT FarsTail: A Persian Natural Language Inference Dataset 83.38 2020-09-18 📦 dml-qom/FarsTail
2 ParsBERT FarsTail: A Persian Natural Language Inference Dataset 82.99 2020-09-18 📦 dml-qom/FarsTail
3 Translate-Source + fastText FarsTail: A Persian Natural Language Inference Dataset 78.13 2020-09-18 📦 dml-qom/FarsTail
4 LSTM + BERT (concat) FarsTail: A Persian Natural Language Inference Dataset 75.83 2020-09-18 📦 dml-qom/FarsTail
5 ESIM + BERT (FarsTail, MultiNLI) FarsTail: A Persian Natural Language Inference Dataset 74.62 2020-09-18 📦 dml-qom/FarsTail
6 ULMFiT FarsTail: A Persian Natural Language Inference Dataset 72.44 2020-09-18 📦 dml-qom/FarsTail
7 ESIM + fastText FarsTail: A Persian Natural Language Inference Dataset 71.16 2020-09-18 📦 dml-qom/FarsTail
8 Translate-Target + fastText FarsTail: A Persian Natural Language Inference Dataset 70.46 2020-09-18 📦 dml-qom/FarsTail
9 Decomposable Attention Model + word2vec FarsTail: A Persian Natural Language Inference Dataset 66.62 2020-09-18 📦 dml-qom/FarsTail
10 HBMP + word2vec FarsTail: A Persian Natural Language Inference Dataset 66.04 2020-09-18 📦 dml-qom/FarsTail

All Papers (10)

dml-qom/FarsTail
dml-qom/FarsTail
dml-qom/FarsTail
dml-qom/FarsTail

FarsTail: A Persian Natural Language Inference Dataset

2020
ESIM + BERT (FarsTail, MultiNLI)
dml-qom/FarsTail
dml-qom/FarsTail
dml-qom/FarsTail
dml-qom/FarsTail

FarsTail: A Persian Natural Language Inference Dataset

2020
Decomposable Attention Model + word2vec
dml-qom/FarsTail
dml-qom/FarsTail