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/DeepStruct multi-task

DeepStruct multi-task

Reported on 52 benchmarks across 9 tasks · 1 paper · 13 SOTA

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

Natural Language Processing39 results

Relation ExtractiononACE2005
Entity F1· 2022-05-21
90.2
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononNYT
Relation F1· 2022-05-21
93.7
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononACE2005
Argument Cl· 2022-05-21
63.9
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononACE2005
Argument Id· 2022-05-21
67.5
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Semantic Role LabelingonCoNLL05 WSJ
F1· 2022-05-21
95.5
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Semantic Role LabelingonCoNLL12
F1· 2022-05-21
97.2
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Named Entity Recognition (NER)onCoNLL03
F1· 2022-05-21
93.1
best: 93.3 (UniNER-7B)
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Event ExtractiononACE2005
Argument Cl· 2022-05-21
63.9
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Event ExtractiononACE2005
Argument Id· 2022-05-21
67.5
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononTACRED
F1· 2022-05-21
74.9
best: 86.6 (RAG4RE)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononFewRel
F1 (10-way 1-shot)· 2022-05-21
92.2
best: 97.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononFewRel
F1 (10-way 5-shot)· 2022-05-21
94.6
best: 99.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononFewRel
F1 (5-way 1-shot)· 2022-05-21
93.6
best: 98.4 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononFewRel
F1 (5-way 5-shot· 2022-05-21
96.4
best: 100 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononACE2005
Relation F1· 2022-05-21
58.9
best: 66.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononNYT
Entity F1· 2022-05-21
95.4
best: 95.9 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononCoNLL04
Entity F1· 2022-05-21
88.4
best: 90.7 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononCoNLL04
Relation F1· 2022-05-21
72.8
best: 78.3 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononADE Corpus
Entity F1· 2022-05-21
90.5
best: 91.1 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ExtractiononADE Corpus
Relation F1· 2022-05-21
83.6
best: 83.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ClassificationonTACRED
F1· 2022-05-21
74.9
best: 76.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ClassificationonFewRel
F1 (10-way 1-shot)· 2022-05-21
92.2
best: 97.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ClassificationonFewRel
F1 (10-way 5-shot)· 2022-05-21
94.6
best: 99.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ClassificationonFewRel
F1 (5-way 1-shot)· 2022-05-21
93.6
best: 98.4 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Relation ClassificationonFewRel
F1 (5-way 5-shot· 2022-05-21
96.4
best: 100 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononWeb
F1· 2022-05-21
50.8
best: 91.2 (DeepEx (zero-shot))
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononPenn Treebank
F1· 2022-05-21
54.5
best: 451 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononNYT
F1· 2022-05-21
43.6
best: 85.5 (DeepEx (zero-shot))
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononACE2005
Trigger Cl· 2022-05-21
69.2
best: 71.9 (Text2Event - T5-large)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Open Information ExtractiononACE2005
Trigger Id· 2022-05-21
72.7
best: 73.5 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Semantic Role LabelingonCoNLL05 Brown
F1· 2022-05-21
92
best: 92.1 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Named Entity Recognition (NER)onGENIA
F1· 2022-05-21
80.2
best: 81.77 (PIQN)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Named Entity Recognition (NER)onOntoNotes
F1· 2022-05-21
87.6
best: 87.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Coreference ResolutiononCoNLL12
Average F1· 2022-05-21
60.6
best: 73.1 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Coreference ResolutiononCoNLL12
B3· 2022-05-21
57.7
best: 71.3 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Coreference ResolutiononCoNLL12
CEAFϕ4· 2022-05-21
60.2
best: 73.1 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Coreference ResolutiononCoNLL12
MUC· 2022-05-21
63.9
best: 74.9 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Event ExtractiononACE2005
Trigger Cl· 2022-05-21
69.2
best: 71.9 (Text2Event - T5-large)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Event ExtractiononACE2005
Trigger Id· 2022-05-21
72.7
best: 73.5 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475

Medical12 results

Information ExtractiononACE2005
Argument Cl· 2022-05-21
63.9
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononACE2005
Argument Id· 2022-05-21
67.5
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononACE2005
Entity F1· 2022-05-21
90.2
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononNYT
Relation F1· 2022-05-21
93.7
SOTA
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononACE2005
Trigger Cl· 2022-05-21
69.2
best: 71.9 (Text2Event - T5-large)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononACE2005
Trigger Id· 2022-05-21
72.7
best: 73.5 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononACE2005
Relation F1· 2022-05-21
58.9
best: 66.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononNYT
Entity F1· 2022-05-21
95.4
best: 95.9 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononCoNLL04
Entity F1· 2022-05-21
88.4
best: 90.7 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononCoNLL04
Relation F1· 2022-05-21
72.8
best: 78.3 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononADE Corpus
Entity F1· 2022-05-21
90.5
best: 91.1 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475
Information ExtractiononADE Corpus
Relation F1· 2022-05-21
83.6
best: 83.8 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475

Speech1 result

DialogueonMULTIWOZ 2.1
Joint Acc· 2022-05-21
53.5
best: 54.2 (DeepStruct multi-task w/ finetune)
DeepStruct: Pretraining of Language Models for Structure Prediction arXiv:2205.10475