TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/T5

T5

Reported on 109 benchmarks across 22 tasks · 13 papers · 28 SOTA

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

Natural Language Processing89 results

  • SummarizationonMuLD (VLSP)
    BLEU-4· 2022-02-15
    84
    SOTA
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • TranslationonMuLD (OpenSubtitles)
    BLEU-1· 2022-02-15
    34.07
    SOTA
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • TranslationonMuLD (OpenSubtitles)
    METEOR· 2022-02-15
    38.53
    SOTA
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • TranslationonMuLD (OpenSubtitles)
    Rouge-L· 2022-02-15
    35.35
    SOTA
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Grammatical Error CorrectiononCoNLL-2014 Shared Task
    F0.5· 2021-06-07
    68.87
    best: 72.8 (Ensembles of best 7 models + GRECO + GTP-rerank)
    SOTA
    A Simple Recipe for Multilingual Grammatical Error CorrectionarXiv:2106.03830
  • Text SimplificationonTurkCorpus
    METEOR· 2021-02-02
    0.649
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Text SimplificationonASSET
    METEOR· 2021-02-02
    0.581
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Data-to-Text GenerationonToTTo
    METEOR· 2021-02-02
    0.363
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Task-Oriented Dialogue SystemsonSGD
    METEOR· 2021-02-02
    0.331
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Machine TranslationonAlexa Point of View
    BLEU· 2020-10-06
    63
    SOTA
    Converting the Point of View of Messages Spoken to Virtual AssistantsarXiv:2010.02600
  • Natural Language InferenceonAX
    Accuracy· 2019-11-08
    53.1
    SOTA
    SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationarXiv:1911.03437
  • Natural Language InferenceonWeiboPolls
    BLEU-1· 2019-10-23
    37.77
    best: 37.87 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Natural Language InferenceonWeiboPolls
    BLEU-3· 2019-10-23
    25.86
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Natural Language InferenceonWeiboPolls
    ROUGE-1· 2019-10-23
    46.2
    best: 46.24 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Natural Language InferenceonWeiboPolls
    ROUGE-L· 2019-10-23
    43.32
    best: 43.34 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-1· 2019-10-23
    43.52
    best: 48.18 (Scrambled code + broken (alter))
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-2· 2019-10-23
    21.55
    best: 24.02 (Pegasus)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2019-10-23
    40.69
    best: 45.35 (Scrambled code + broken (alter))
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    BLEU-1· 2019-10-23
    37.34
    best: 42.04 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    BLEU-3· 2019-10-23
    21.06
    best: 22.78 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    ROUGE-1· 2019-10-23
    45.33
    best: 49.6 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    ROUGE-L· 2019-10-23
    42.69
    best: 46.71 (UniPoll)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Text2text GenerationonMTTN: Multi-Pair Text to Text Narratives for Prompt Generation
    ROUGE-1· 2023-01-21
    93.3203
    best: 93.8372 (MVP)
    MTTN: Multi-Pair Text to Text Narratives for Prompt GenerationarXiv:2301.10172
  • Data-to-Text GenerationonEventNarrative
    BLEU· 2022-04-13
    12.8
    best: 35.08 (GAP - Me,r+γ)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    BertScore· 2022-04-13
    89.59
    best: 93.68 (JointGT)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    METEOR· 2022-04-13
    22.77
    best: 27.72 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    ROUGE· 2022-04-13
    52.06
    best: 71.92 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    BLEU· 2022-04-13
    12.8
    best: 35.08 (GAP - Me,r+γ)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    BertScore· 2022-04-13
    89.59
    best: 93.68 (JointGT)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    METEOR· 2022-04-13
    22.77
    best: 27.72 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Data-to-Text GenerationonEventNarrative
    ROUGE· 2022-04-13
    52.06
    best: 71.92 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    BLEU· 2022-04-13
    12.8
    best: 35.08 (GAP - Me,r+γ)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    BertScore· 2022-04-13
    89.59
    best: 93.68 (JointGT)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    METEOR· 2022-04-13
    22.77
    best: 27.72 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    ROUGE· 2022-04-13
    52.06
    best: 71.92 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    BLEU· 2022-04-13
    12.8
    best: 35.08 (GAP - Me,r+γ)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    BertScore· 2022-04-13
    89.59
    best: 93.68 (JointGT)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    METEOR· 2022-04-13
    22.77
    best: 27.72 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • KG-to-Text GenerationonEventNarrative
    ROUGE· 2022-04-13
    52.06
    best: 71.92 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Question AnsweringonMuLD (NarrativeQA)
    BLEU-1· 2022-02-15
    17.67
    best: 19.84 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (NarrativeQA)
    BLEU-4· 2022-02-15
    55
    best: 62 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (NarrativeQA)
    METEOR· 2022-02-15
    3.36
    best: 4.52 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (NarrativeQA)
    Rouge-L· 2022-02-15
    19.03
    best: 22.09 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (HotpotQA)
    BLEU-1· 2022-02-15
    28.11
    best: 30.38 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (HotpotQA)
    BLEU-4· 2022-02-15
    13.63
    best: 16.76 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (HotpotQA)
    METEOR· 2022-02-15
    4.46
    best: 4.98 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Question AnsweringonMuLD (HotpotQA)
    Rouge-L· 2022-02-15
    27.61
    best: 30.49 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • SummarizationonMuLD (VLSP)
    BLEU-1· 2022-02-15
    28.85
    best: 46.74 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • SummarizationonMuLD (VLSP)
    METEOR· 2022-02-15
    7.98
    best: 9.58 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • SummarizationonMuLD (VLSP)
    Rouge-L· 2022-02-15
    16.55
    best: 19.52 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Text ClassificationonMuLD (Character Type)
    F1· 2022-02-15
    54.01
    best: 82.58 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • TranslationonMuLD (OpenSubtitles)
    BLEU-4· 2022-02-15
    1.63
    best: 20 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362
  • Relation ExtractiononDataset: Relationship extraction for knowledge graph creation from biomedical literature (Gene-Disease relationships)
    F1· 2022-01-05
    88
    best: 91 (DistilBERT)
    Comparison of biomedical relationship extraction methods and models for knowledge graph creationarXiv:2201.01647
  • Data-to-Text GenerationonEventNarrative
    CIDEr· 2021-10-30
    3
    best: 4.59 (GraphWriter)
    EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationarXiv:2111.00276
  • Data-to-Text GenerationonEventNarrative
    ChrF++· 2021-10-30
    56.76
    best: 64.71 (BART)
    EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationarXiv:2111.00276
  • KG-to-Text GenerationonEventNarrative
    CIDEr· 2021-10-30
    3
    best: 4.59 (GraphWriter)
    EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationarXiv:2111.00276
  • KG-to-Text GenerationonEventNarrative
    ChrF++· 2021-10-30
    56.76
    best: 64.71 (BART)
    EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationarXiv:2111.00276
  • Data-to-Text GenerationonWebNLG 2.0 (Constrained)
    BLEU· 2021-06-19
    58.66
    best: 67.08 (FactT5B)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebNLG 2.0 (Constrained)
    METEOR· 2021-06-19
    46.04
    best: 48.35 (T5B Baseline)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebNLG 2.0 (Constrained)
    ROUGE· 2021-06-19
    73.06
    best: 73.57 (JointGT (T5))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebQuestions
    BLEU· 2021-06-19
    28.78
    best: 30.02 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebQuestions
    METEOR· 2021-06-19
    30.55
    best: 32.05 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebQuestions
    ROUGE· 2021-06-19
    55.12
    best: 55.6 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebNLG 2.0 (Unconstrained)
    BLEU· 2021-06-19
    64.42
    best: 66.2 (GAP - Me,r+γ)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebNLG 2.0 (Unconstrained)
    METEOR· 2021-06-19
    46.58
    best: 47.25 (JointGT (T5))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonWebNLG 2.0 (Unconstrained)
    ROUGE· 2021-06-19
    74.77
    best: 76.36 (GAP - Me,r+γ)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonPathQuestion
    BLEU· 2021-06-19
    58.95
    best: 65.89 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonPathQuestion
    METEOR· 2021-06-19
    44.72
    best: 48.25 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonPathQuestion
    ROUGE· 2021-06-19
    76.58
    best: 78.87 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebNLG 2.0 (Constrained)
    BLEU· 2021-06-19
    58.66
    best: 67.08 (FactT5B)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebNLG 2.0 (Constrained)
    METEOR· 2021-06-19
    46.04
    best: 48.35 (T5B Baseline)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebNLG 2.0 (Constrained)
    ROUGE· 2021-06-19
    73.06
    best: 73.57 (JointGT (T5))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebQuestions
    BLEU· 2021-06-19
    28.78
    best: 30.02 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebQuestions
    METEOR· 2021-06-19
    30.55
    best: 32.05 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebQuestions
    ROUGE· 2021-06-19
    55.12
    best: 55.6 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebNLG 2.0 (Unconstrained)
    BLEU· 2021-06-19
    64.42
    best: 66.2 (GAP - Me,r+γ)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebNLG 2.0 (Unconstrained)
    METEOR· 2021-06-19
    46.58
    best: 47.25 (JointGT (T5))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonWebNLG 2.0 (Unconstrained)
    ROUGE· 2021-06-19
    74.77
    best: 76.36 (GAP - Me,r+γ)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonPathQuestion
    BLEU· 2021-06-19
    58.95
    best: 65.89 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonPathQuestion
    METEOR· 2021-06-19
    44.72
    best: 48.25 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • KG-to-Text GenerationonPathQuestion
    ROUGE· 2021-06-19
    76.58
    best: 78.87 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Data-to-Text GenerationonCleaned E2E NLG Challenge
    METEOR (Validation set)· 2021-02-02
    0.369
    best: 0.394 (LSTM)
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Natural Language InferenceonMultiNLI
    Matched· 2019-11-08
    92
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
    SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationarXiv:1911.03437
  • Natural Language InferenceonMultiNLI
    Mismatched· 2019-11-08
    91.7
    best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
    SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized OptimizationarXiv:1911.03437
  • Machine TranslationonWMT2014 English-French
    BLEU score· uses extra data· 2019-10-23
    43.4
    best: 46.4 (Transformer+BT (ADMIN init))
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    BLEU-1· 2019-10-23
    36.91
    best: 42.04 (UniPoll)
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    BLEU-3· 2019-10-23
    16.26
    best: 22.78 (UniPoll)
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    ROUGE-1· 2019-10-23
    44.46
    best: 49.6 (UniPoll)
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Question GenerationonWeiboPolls
    ROUGE-L· 2019-10-23
    42.06
    best: 46.71 (UniPoll)
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683

Adversarial26 results

  • Text GenerationonDART
    METEOR· 2021-02-02
    0.115
    best: 40.74 (T5B Baseline)
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Text GenerationonToTTo
    METEOR· 2021-02-02
    0.363
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Text GenerationonEventNarrative
    BLEU· 2022-04-13
    12.8
    best: 35.08 (GAP - Me,r+γ)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    BertScore· 2022-04-13
    89.59
    best: 93.68 (JointGT)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    METEOR· 2022-04-13
    22.77
    best: 27.72 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    ROUGE· 2022-04-13
    52.06
    best: 71.92 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    BLEU· 2022-04-13
    12.8
    best: 35.08 (GAP - Me,r+γ)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    BertScore· 2022-04-13
    89.59
    best: 93.68 (JointGT)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    METEOR· 2022-04-13
    22.77
    best: 27.72 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    ROUGE· 2022-04-13
    52.06
    best: 71.92 (GraphWriter)
    GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationarXiv:2204.06674
  • Text GenerationonEventNarrative
    CIDEr· 2021-10-30
    3
    best: 4.59 (GraphWriter)
    EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationarXiv:2111.00276
  • Text GenerationonEventNarrative
    ChrF++· 2021-10-30
    56.76
    best: 64.71 (BART)
    EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationarXiv:2111.00276
  • Text GenerationonWebNLG 2.0 (Constrained)
    BLEU· 2021-06-19
    58.66
    best: 67.08 (FactT5B)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebNLG 2.0 (Constrained)
    METEOR· 2021-06-19
    46.04
    best: 48.35 (T5B Baseline)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebNLG 2.0 (Constrained)
    ROUGE· 2021-06-19
    73.06
    best: 73.57 (JointGT (T5))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebQuestions
    BLEU· 2021-06-19
    28.78
    best: 30.02 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebQuestions
    METEOR· 2021-06-19
    30.55
    best: 32.05 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebQuestions
    ROUGE· 2021-06-19
    55.12
    best: 55.6 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebNLG 2.0 (Unconstrained)
    BLEU· 2021-06-19
    64.42
    best: 66.2 (GAP - Me,r+γ)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebNLG 2.0 (Unconstrained)
    METEOR· 2021-06-19
    46.58
    best: 47.25 (JointGT (T5))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonWebNLG 2.0 (Unconstrained)
    ROUGE· 2021-06-19
    74.77
    best: 76.36 (GAP - Me,r+γ)
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonPathQuestion
    BLEU· 2021-06-19
    58.95
    best: 65.89 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonPathQuestion
    METEOR· 2021-06-19
    44.72
    best: 48.25 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonPathQuestion
    ROUGE· 2021-06-19
    76.58
    best: 78.87 (JointGT (BART))
    JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge GraphsarXiv:2106.10502
  • Text GenerationonCommonGen
    METEOR· 2021-02-02
    0.291
    best: 0.301 (BART)
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672
  • Text GenerationonCleaned E2E NLG Challenge
    METEOR (Validation set)· 2021-02-02
    0.369
    best: 0.394 (LSTM)
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672

Methodology5 results

  • Data MiningonIMDb Movie Reviews
    Accuracy· 2023-08-07
    93.9
    best: 95.6 (ELECTRA)
    Analysis of the Evolution of Advanced Transformer-Based Language Models: Experiments on Opinion MiningarXiv:2308.03235
  • Data MiningonIMDb Movie Reviews
    F1· 2023-08-07
    94
    best: 95.6 (ELECTRA)
    Analysis of the Evolution of Advanced Transformer-Based Language Models: Experiments on Opinion MiningarXiv:2308.03235
  • Interpretable Machine LearningonIMDb Movie Reviews
    Accuracy· 2023-08-07
    93.9
    best: 95.6 (ELECTRA)
    Analysis of the Evolution of Advanced Transformer-Based Language Models: Experiments on Opinion MiningarXiv:2308.03235
  • Interpretable Machine LearningonIMDb Movie Reviews
    F1· 2023-08-07
    94
    best: 95.6 (ELECTRA)
    Analysis of the Evolution of Advanced Transformer-Based Language Models: Experiments on Opinion MiningarXiv:2308.03235
  • ClassificationonMuLD (Character Type)
    F1· 2022-02-15
    54.01
    best: 82.58 (Longformer)
    MuLD: The Multitask Long Document BenchmarkarXiv:2202.07362

Knowledge Base3 results

  • Text SummarizationonCNN / Daily Mail
    ROUGE-2· 2019-10-23
    21.55
    best: 24.02 (Pegasus)
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2019-10-23
    40.69
    best: 45.35 (Scrambled code + broken (alter))
    SOTA
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683
  • Text SummarizationonCNN / Daily Mail
    ROUGE-1· 2019-10-23
    43.52
    best: 48.18 (Scrambled code + broken (alter))
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerarXiv:1910.10683

Medical1 result

  • Information ExtractiononSemTabNet
    average Tree Similarity Score· 2024-06-27
    81.76
    SOTA
    Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIsarXiv:2406.19102

Speech1 result

  • DialogueonSGD
    METEOR· 2021-02-02
    0.331
    SOTA
    The GEM Benchmark: Natural Language Generation, its Evaluation and MetricsarXiv:2102.01672