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

Showing 101150 of 620 papers

TitleStatusHype
An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference NetworksCode0
Speaker attribution in German parliamentary debates with QLoRA-adapted large language modelsCode0
Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling ModelCode0
Graph Convolutional Networks for Named Entity RecognitionCode0
Capturing Argument Interaction in Semantic Role Labeling with Capsule NetworksCode0
A Primal Dual Formulation For Deep Learning With ConstraintsCode0
A Random Walk Approach to Selectional Preferences Based on Preference Ranking and PropagationCode0
Character-Level Models versus Morphology in Semantic Role LabelingCode0
Syntax-driven Approach for Semantic Role LabelingCode0
Syntax for Semantic Role Labeling, To Be, Or Not To BeCode0
Glyce: Glyph-vectors for Chinese Character RepresentationsCode0
High-order Semantic Role LabelingCode0
CogCompNLP: Your Swiss Army Knife for NLPCode0
Transition-based Semantic Role Labeling with Pointer NetworksCode0
Influence Functions for Sequence Tagging ModelsCode0
Large-Scale QA-SRL ParsingCode0
Extracting Victim Counts from TextCode0
Extracting Entities of Interest from Comparative Product ReviewsCode0
End-to-end Semantic Role Labeling with Neural Transition-based ModelCode0
Encoder-decoder based unified semantic role labeling with label-aware syntaxCode0
Enhancing Opinion Role Labeling with Semantic-Aware Word Representations from Semantic Role LabelingCode0
Frame- and Entity-Based Knowledge for Common-Sense Argumentative ReasoningCode0
Dict2vec : Learning Word Embeddings using Lexical DictionariesCode0
An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role LabelingCode0
Discovering collective narratives shifts in online discussionsCode0
Context-aware Frame-Semantic Role LabelingCode0
Deep Semantic Role Labeling: What Works and What's NextCode0
An Approach for Process Model Extraction By Multi-Grained Text ClassificationCode0
Deep Semantic Role Labeling with Self-AttentionCode0
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role LabelingCode0
A Span Selection Model for Semantic Role LabelingCode0
Demonyms and Compound Relational Nouns in Nominal Open IECode0
Dependency or Span, End-to-End Uniform Semantic Role LabelingCode0
Creation of a Balanced State-of-the-Art Multilayer Corpus for NLUCode0
Effectively Leveraging CLIP for Generating Situational Summaries of Images and VideosCode0
Generalizing Natural Language Analysis through Span-relation RepresentationsCode0
Learning Semantic Role Labeling from Compatible Label SequencesCode0
context2vec: Learning Generic Context Embedding with Bidirectional LSTM0
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling0
A Shortest-path Method for Arc-factored Semantic Role Labeling0
AnCora-UPF: A Multi-Level Annotation of Spanish0
Concept-based Selectional Preferences and Distributional Representations from Wikipedia Articles0
Computing Word Classes Using Spectral Clustering0
A Sequence-to-Sequence Model for Semantic Role Labeling0
Computational linking theory0
Computational Frameworks for Supporting Textual Inference0
A Semantics-based Approach to Disclosure Classification in User-Generated Online Content0
An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling0
Affordance Extraction and Inference based on Semantic Role Labeling0
Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA0
Show:102550
← PrevPage 3 of 13Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HeSyFuF188.59Unverified
2CRF2o + RoBERTaF188.32Unverified
3MRC-SRLF188.3Unverified
4ReCAT(pretrained on wikitext103)F188Unverified
5SRL-MM + XLNetF187.67Unverified
6CRF2o + BERTF187.66Unverified
7RoBERTa+RegCCRFF187.51Unverified
8RoBERTa+CRFF187.27Unverified
9BiLSTM-Span (Ensemble)F187Unverified
10BiLSTM-SpanF186.2Unverified
#ModelMetricClaimedVerifiedStatus
1MRC-SRLF190Unverified
2SRL-MM + XLNetF189.8Unverified
3CRF2o + RoBERTaF189.54Unverified
4HeSyFuF189.04Unverified
5CRF2o + BERTF189.03Unverified
6Mohammadshahi and Henderson (2021)F188.93Unverified
7BiLSTM-Span (Ensemble, predicates given)F188.5Unverified
8CRF2oF187.87Unverified
9Li et al. (2019) (Ensemble)F187.7Unverified
10BiLSTM-SpanF187.6Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-task w/ finetuneF192.1Unverified
2DeepStruct multi-taskF192Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-taskF195.5Unverified
2DeepStruct multi-task w/ finetuneF195.2Unverified
#ModelMetricClaimedVerifiedStatus
1DeepStruct multi-taskF197.2Unverified
2DeepStruct multi-task w/ finetuneF196Unverified
#ModelMetricClaimedVerifiedStatus
1Ours (High-Order model)F1 (Arg.)90.2Unverified
#ModelMetricClaimedVerifiedStatus
1HeSyFuAvg. F188.59Unverified