SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–325 of 620 papers

TitleStatusHype
Syntax Aware LSTM Model for Chinese Semantic Role Labeling—0
Integer Linear Programming formulations in Natural Language Processing—0
Assessing SRL Frameworks with Automatic Training Data Expansion—0
Understanding the Semantics of Narratives of Interpersonal Violence through Reader Annotations and Physiological Reactions—0
Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering—0
Resource-Lean Modeling of Coherence in Commonsense Stories—0
Out-of-domain FrameNet Semantic Role Labeling—0
Improving Chinese Semantic Role Labeling using High-quality Surface and Deep Case Frames—0
Legal NERC with ontologies, Wikipedia and curriculum learning—0
Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations—0
Paraphrasing Revisited with Neural Machine Translation—0
The Semantic Proto-Role Linking Model—0
End-to-End Learning for Structured Prediction Energy Networks—0
Encoding Sentences with Graph Convolutional Networks for Semantic Role LabelingCode0
Feature Generation for Robust Semantic Role Labeling—0
Improving Chinese SRL with Heterogeneous Annotations—0
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role LabelingCode0
An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role LabelingCode0
The Treebanked Conspiracy. Actors and Actions in Bellum Catilinae—0
Graph Convolutional Networks for Named Entity RecognitionCode0
Skip-Prop: Representing Sentences with One Vector Per Proposition—0
Multilingual Aliasing for Auto-Generating Proposition Banks—0
Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training—0
Improving Statistical Machine Translation with Selectional Preferences—0
Deeper syntax for better semantic parsing—0
Show:102550
← PrevPage 13 of 25Next →
All datasetsOntoNotesCoNLL 2005CoNLL05 BrownCoNLL05 WSJCoNLL12CoNLL-2009CoNLL-2012

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HeSyFuF188.59—Unverified
2CRF2o + RoBERTaF188.32—Unverified
3MRC-SRLF188.3—Unverified
4ReCAT(pretrained on wikitext103)F188—Unverified
5SRL-MM + XLNetF187.67—Unverified
6CRF2o + BERTF187.66—Unverified
7RoBERTa+RegCCRFF187.51—Unverified
8RoBERTa+CRFF187.27—Unverified
9BiLSTM-Span (Ensemble)F187—Unverified
10BiLSTM-SpanF186.2—Unverified
#ModelMetricClaimedVerifiedStatus
1MRC-SRLF190—Unverified
2SRL-MM + XLNetF189.8—Unverified
3CRF2o + RoBERTaF189.54—Unverified
4HeSyFuF189.04—Unverified
5CRF2o + BERTF189.03—Unverified
6Mohammadshahi and Henderson (2021)F188.93—Unverified
7BiLSTM-Span (Ensemble, predicates given)F188.5—Unverified
8CRF2oF187.87—Unverified
9Li et al. (2019) (Ensemble)F187.7—Unverified
10BiLSTM-SpanF187.6—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-task w/ finetuneF192.1—Unverified
2DeepStruct multi-taskF192—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-taskF195.5—Unverified
2DeepStruct multi-task w/ finetuneF195.2—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-taskF197.2—Unverified
2DeepStruct multi-task w/ finetuneF196—Unverified
#ModelMetricClaimedVerifiedStatus
1Ours (High-Order model)F1 (Arg.)90.2—Unverified
#ModelMetricClaimedVerifiedStatus
1HeSyFuAvg. F188.59—Unverified