Semantic Role Labeling

Semantic role labeling aims to model the predicate-argument structure of a sentence and is often described as answering "Who did what to whom". BIO notation is typically used for semantic role labeling.

Example:

| Housing | starts | are | expected | to | quicken | a | bit | from | August’s | pace | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | B-ARG1 | I-ARG1 | O | O | O | V | B-ARG2 | I-ARG2 | B-ARG3 | I-ARG3 | I-ARG3 |

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 276–300 of 620 papers

Title	Date	Tasks	Status	Hype
Deep contextualized word representations	Feb 15, 2018	Citation Intent ClassificationConversational Response Selection	CodeCode Available	1
Deep Semantic Role Labeling with Self-Attention	Dec 5, 2017	GPUNatural Language Understanding	CodeCode Available	0
Ensemble Technique Utilization for Indonesian Dependency Parser	Nov 1, 2017	Dependency ParsingSemantic Role Labeling	—Unverified	0
Can Discourse Relations be Identified Incrementally?	Nov 1, 2017	Discourse ParsingLanguage Modeling	—Unverified	0
Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework	Nov 1, 2017	General ClassificationImage Captioning	—Unverified	0
Transferring Semantic Roles Using Translation and Syntactic Information	Oct 3, 2017	Semantic Role LabelingTranslation	—Unverified	0
FrameFOR -- Uma Base de Conhecimento de Frames Sem\^anticos para Per\' de Inform\'atica (FrameFOR - a Knowledge Base of Semantic Frames for Digital Forensics)[In Portuguese]	Oct 1, 2017	Semantic Role Labeling	—Unverified	0
Cross-Lingual SRL Based upon Universal Dependencies	Sep 1, 2017	Semantic ParsingSemantic Role Labeling	—Unverified	0
MEANT 2.0: Accurate semantic MT evaluation for any output language	Sep 1, 2017	Machine TranslationSemantic Role Labeling	—Unverified	0
Syntax Aware LSTM model for Semantic Role Labeling	Sep 1, 2017	Feature EngineeringMachine Translation	—Unverified	0
A Joint Sequential and Relational Model for Frame-Semantic Parsing	Sep 1, 2017	Knowledge DistillationMachine Translation	—Unverified	0
Dict2vec : Learning Word Embeddings using Lexical Dictionaries	Sep 1, 2017	General ClassificationKnowledge Graphs	CodeCode Available	0
CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles	Sep 1, 2017	Machine TranslationQuestion Answering	—Unverified	0
Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings	Aug 1, 2017	Natural Language InferenceRepresentation Learning	—Unverified	0
The Rich Event Ontology	Aug 1, 2017	Question AnsweringSemantic Role Labeling	—Unverified	0
Assessing the performance of Olelo, a real-time biomedical question answering application	Aug 1, 2017	Document SummarizationInformation Retrieval	—Unverified	0
Graph Methods for Multilingual FrameNets	Aug 1, 2017	Semantic Role LabelingSentence	—Unverified	0
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints	Jul 29, 2017	General ClassificationSemantic Role Labeling	CodeCode Available	1
Gradient-based Inference for Networks with Output Constraints	Jul 26, 2017	Constituency ParsingSemantic Role Labeling	—Unverified	0
Domain Specific Automatic Question Generation from Text	Jul 1, 2017	Dependency ParsingQuestion Generation	—Unverified	0
A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data	Jul 1, 2017	Chinese Semantic Role LabelingMachine Translation	—Unverified	0
Deep Semantic Role Labeling: What Works and What's Next	Jul 1, 2017	Predicate DetectionSemantic Role Labeling	CodeCode Available	0
Docforia: A Multilayer Document Model	May 1, 2017	Coreference ResolutionDependency Parsing	—Unverified	0
Automatic semantic role labeling on non-revised syntactic trees of journalistic texts	Apr 10, 2017	Semantic Role Labeling	—Unverified	0
Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments	Apr 10, 2017	Common Sense ReasoningSemantic Role Labeling	—Unverified	0

Show:10 25 50

← PrevPage 12 of 25Next →

All datasets OntoNotes CoNLL 2005 CoNLL05 Brown CoNLL05 WSJ CoNLL12 CoNLL-2009 CoNLL-2012

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	HeSyFu	F1	88.59	—	Unverified
2	CRF2o + RoBERTa	F1	88.32	—	Unverified
3	MRC-SRL	F1	88.3	—	Unverified
4	ReCAT(pretrained on wikitext103)	F1	88	—	Unverified
5	SRL-MM + XLNet	F1	87.67	—	Unverified
6	CRF2o + BERT	F1	87.66	—	Unverified
7	RoBERTa+RegCCRF	F1	87.51	—	Unverified
8	RoBERTa+CRF	F1	87.27	—	Unverified
9	BiLSTM-Span (Ensemble)	F1	87	—	Unverified
10	BiLSTM-Span	F1	86.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MRC-SRL	F1	90	—	Unverified
2	SRL-MM + XLNet	F1	89.8	—	Unverified
3	CRF2o + RoBERTa	F1	89.54	—	Unverified
4	HeSyFu	F1	89.04	—	Unverified
5	CRF2o + BERT	F1	89.03	—	Unverified
6	Mohammadshahi and Henderson (2021)	F1	88.93	—	Unverified
7	BiLSTM-Span (Ensemble, predicates given)	F1	88.5	—	Unverified
8	CRF2o	F1	87.87	—	Unverified
9	Li et al. (2019) (Ensemble)	F1	87.7	—	Unverified
10	BiLSTM-Span	F1	87.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeepStruct multi-task w/ finetune	F1	92.1	—	Unverified
2	DeepStruct multi-task	F1	92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeepStruct multi-task	F1	95.5	—	Unverified
2	DeepStruct multi-task w/ finetune	F1	95.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeepStruct multi-task	F1	97.2	—	Unverified
2	DeepStruct multi-task w/ finetune	F1	96	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Ours (High-Order model)	F1 (Arg.)	90.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HeSyFu	Avg. F1	88.59	—	Unverified