SOTAVerified

Coreference Resolution

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 880 papers

TitleStatusHype
The Role of Natural Language Processing Tasks in Automatic Literary Character Network ConstructionCode0
IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMsCode0
Data-driven Coreference-based Ontology BuildingCode0
Findings of the Third Shared Task on Multilingual Coreference ResolutionCode0
Solving the Challenge Set without Solving the Task: On Winograd Schemas as a Test of Pronominal Coreference ResolutionCode0
How Language Models Prioritize Contextual Grammatical Cues?Code0
CorPipe at CRAC 2024: Predicting Zero Mentions from Raw TextCode0
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding—0
J2N -- Nominal Adjective Identification and its ApplicationCode0
WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical CaseCode0
Show:102550
← PrevPage 2 of 88Next →
All datasetsWinograd Schema ChallengeOntoNotesCoNLL-2012GAPDWIEWikiCorefCoNLL12LitBankOntoGUMPreCoSTM-corefXWinograd EN

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaLM 540B (fine-tuned)Accuracy100—Unverified
2Vega v2 6B (KD-based prompt transfer)Accuracy98.6—Unverified
3UL2 20B (fine-tuned)Accuracy98.1—Unverified
4Turing NLR v5 XXL 5.4B (fine-tuned)Accuracy97.3—Unverified
5ST-MoE-32B 269B (fine-tuned)Accuracy96.6—Unverified
6DeBERTa-1.5BAccuracy95.9—Unverified
7T5-XXL 11B (fine-tuned)Accuracy93.8—Unverified
8ST-MoE-L 4.1B (fine-tuned)Accuracy93.3—Unverified
9RoBERTa-WinoGrande 355MAccuracy90.1—Unverified
10Flan-T5 XXL (zero -shot)Accuracy89.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Maverick_mesF183.6—Unverified
2seq2seqF183.3—Unverified
3ASP+T0-3BF182.3—Unverified
4caw-coref + RoBERTaF181.6—Unverified
5LingMessF181.4—Unverified
6wl-coref + RoBERTaF181—Unverified
7U-MEM + LongformerF180.9—Unverified
8longdoc S (OntoNotes + 60k pseudo-singletons)F180.6—Unverified
9G2GT SpanBERT-large reducedF180.5—Unverified
10G2GT SpanBERT-large overlapF180.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Maverick_mesAvg F183.6—Unverified
2seq2seqAvg F183.3—Unverified
3CorefQA + SpanBERT-largeAvg F183.1—Unverified
4ASP+T0-3BAvg F182.3—Unverified
5wl-coref + RoBERTaAvg F181—Unverified
6s2e + Longformer-LargeAvg F180.3—Unverified
7c2f + SpanBERT-LargeAvg F180.2—Unverified
8SpanBERT + Cluster MergingAvg F180.2—Unverified
9CorefQA + SpanBERT-baseAvg F179.9—Unverified
10U-MEM* + SpanBERT-largeAvg F179.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Coref-MTLOverall F192.72—Unverified
2ProBERTOverall F192.5—Unverified
3Maverick_incrOverall F191.2—Unverified
4Full EnsembleOverall F190.2—Unverified
5PeTraF185.3—Unverified
#ModelMetricClaimedVerifiedStatus
1REXELAvg. F195.12—Unverified
2JointAvg. F191.6—Unverified
3KB-bothAvg. F191.5—Unverified
#ModelMetricClaimedVerifiedStatus
1Maverick_mesF166.8—Unverified
2longdoc S (ON + PreCo + LitBank + 30k pseudo-singletons)F162.5—Unverified
3longdoc S (OntoNotes + PreCo + LitBank)F160.3—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-task w/ finetuneAverage F173.1—Unverified
2DeepStruct multi-taskAverage F160.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Maverick_incrAvg F178.3—Unverified
2longdoc S (OntoNotes + PreCo + LitBank)F178.2—Unverified
#ModelMetricClaimedVerifiedStatus
1MTL-corefAvg F168.2—Unverified
2SpanBERTAvg F164.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Maverick_incrF188—Unverified
2longdoc S (OntoNotes + PreCo + LitBank)F187.6—Unverified
#ModelMetricClaimedVerifiedStatus
1BFCR + SpanBERT + Transfer LearningCoNLL F161.4—Unverified
2BFCR + SpanBERTCoNLL F150.4—Unverified
#ModelMetricClaimedVerifiedStatus
1mT0-13BAccuracy81.29—Unverified
2BLOOMZAccuracy69.08—Unverified
#ModelMetricClaimedVerifiedStatus
1mT0-13BAccuracy78.31—Unverified
2BLOOMZAccuracy68.67—Unverified
#ModelMetricClaimedVerifiedStatus
1longdoc S (OntoNotes + PreCo + LitBank)F142.9—Unverified
#ModelMetricClaimedVerifiedStatus
1dali-full-anaphoraAvg F177.9—Unverified