Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/FastText

FastText

Reported on 40 benchmarks across 7 tasks · 5 papers · 6 SOTA

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

Natural Language Processing33 results

Sentiment AnalysisonTweetEval
Hate· 2020-04-30
50.6
best: 52.6 (LSTM)
SOTA
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Sentiment AnalysisonAmazon Review Polarity
Accuracy· 2016-07-06
94.6
best: 97.37 (BERT large)
SOTA
Bag of Tricks for Efficient Text Classification arXiv:1607.01759
Sentiment AnalysisonAmazon Review Full
Accuracy· 2016-07-06
60.2
best: 65.83 (BERT large)
SOTA
Bag of Tricks for Efficient Text Classification arXiv:1607.01759
Text ClassificationonYahoo! Answers
Accuracy· 2016-07-06
72.3
best: 77.62 (BERT-ITPT-FiT)
SOTA
Bag of Tricks for Efficient Text Classification arXiv:1607.01759
Text ClassificationonLot-insts
Accuracy· 2023-02-19
74.93
best: 83.73 (Character-BERT+RS)
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset arXiv:2302.09509
Text ClassificationonLot-insts
Macro-F1· 2023-02-19
44.38
best: 65.9 (Character-BERT+RS)
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset arXiv:2302.09509
Sentiment AnalysisonTweetEval
ALL· 2020-10-23
58.1
best: 67.9 (BERTweet)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Sentiment AnalysisonTweetEval
Emoji· 2020-10-23
25.8
best: 33.4 (BERTweet)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Sentiment AnalysisonTweetEval
Emotion· 2020-10-23
65.2
best: 79.5 (RoB-RT)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Sentiment AnalysisonTweetEval
Irony· 2020-10-23
63.1
best: 82.1 (BERTweet)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Sentiment AnalysisonTweetEval
Offensive· 2020-10-23
73.4
best: 80.5 (RoB-RT)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Sentiment AnalysisonTweetEval
Sentiment· 2020-10-23
62.9
best: 73.4 (BERTweet)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Sentiment AnalysisonTweetEval
Stance· 2020-10-23
65.4
best: 71.2 (BERTweet)
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification arXiv:2010.12421
Word Sense DisambiguationonWiC-TSV
Task 1 Accuracy: all· 2020-04-30
53.7
best: 77.8 (transformers)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 1 Accuracy: domain specific· 2020-04-30
50.6
best: 81 (transformers)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 1 Accuracy: general purpose· 2020-04-30
56.2
best: 75.2 (transformers)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 2 Accuracy: all· 2020-04-30
52.7
best: 72.7 (CTLR)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 2 Accuracy: domain specific· 2020-04-30
47.7
best: 81.5 (CTLR)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 2 Accuracy: general purpose· 2020-04-30
56.8
best: 68.6 (Bert-base)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 3 Accuracy: all· 2020-04-30
53.4
best: 85.3 (Human)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 3 Accuracy: domain specific· 2020-04-30
49
best: 89.2 (Human)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Word Sense DisambiguationonWiC-TSV
Task 3 Accuracy: general purpose· 2020-04-30
57.1
best: 82.1 (Human)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 1 Accuracy: all· 2020-04-30
53.7
best: 77.8 (transformers)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 1 Accuracy: domain specific· 2020-04-30
50.6
best: 81 (transformers)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 1 Accuracy: general purpose· 2020-04-30
56.2
best: 75.2 (transformers)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 2 Accuracy: all· 2020-04-30
52.7
best: 72.7 (CTLR)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 2 Accuracy: domain specific· 2020-04-30
47.7
best: 81.5 (CTLR)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 2 Accuracy: general purpose· 2020-04-30
56.8
best: 68.6 (Bert-base)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 3 Accuracy: all· 2020-04-30
53.4
best: 85.3 (Human)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 3 Accuracy: domain specific· 2020-04-30
49
best: 89.2 (Human)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Entity LinkingonWiC-TSV
Task 3 Accuracy: general purpose· 2020-04-30
57.1
best: 82.1 (Human)
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context arXiv:2004.15016
Sentiment AnalysisonYelp Fine-grained classification
Error· 2016-07-06
36.1
best: 27.05 (XLNet)
Bag of Tricks for Efficient Text Classification arXiv:1607.01759
Text ClassificationonDBpedia
Error· 2016-07-06
1.4
best: 0.62 (XLNet)
Bag of Tricks for Efficient Text Classification arXiv:1607.01759

Methodology4 results

ClassificationonYahoo! Answers
Accuracy· 2016-07-06
72.3
best: 77.62 (BERT-ITPT-FiT)
SOTA
Bag of Tricks for Efficient Text Classification arXiv:1607.01759
ClassificationonLot-insts
Accuracy· 2023-02-19
74.93
best: 83.73 (Character-BERT+RS)
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset arXiv:2302.09509
ClassificationonLot-insts
Macro-F1· 2023-02-19
44.38
best: 65.9 (Character-BERT+RS)
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset arXiv:2302.09509
ClassificationonDBpedia
Error· 2016-07-06
1.4
best: 0.62 (XLNet)
Bag of Tricks for Efficient Text Classification arXiv:1607.01759

Audio3 results

Language IdentificationonNordic Language Identification
Accuracy· 2020-12-11
0.9711
SOTA
Discriminating Between Similar Nordic Languages arXiv:2012.06431
Emotion RecognitiononCPED
Accuracy of Sentiment· 2016-07-06
48.62
best: 51.5 (BERT+AVG+MLP)
Bag of Tricks for Efficient Text Classification arXiv:1607.01759
Emotion RecognitiononCPED
Macro-F1 of Sentiment· 2016-07-06
30.33
best: 48.02 (BERT+AVG+MLP)
Bag of Tricks for Efficient Text Classification arXiv:1607.01759