SOTAVerified

Chunking

Chunking, also known as shallow parsing, identifies continuous spans of tokens that form syntactic units such as noun phrases or verb phrases.

Example:

| Vinken | , | 61 | years | old | | --- | ---| --- | --- | --- | | B-NLP| I-NP | I-NP | I-NP | I-NP |

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 447 papers

TitleStatusHype
Liger Kernel: Efficient Triton Kernels for LLM TrainingCode9
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and SuccessCode5
TrustRAG: An Information Assistant with Retrieval Augmented GenerationCode5
Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented GenerationCode4
Real-Time Execution of Action Chunking Flow PoliciesCode3
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation SystemCode3
Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical PerceptionCode3
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding ModelsCode3
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech SeparationCode3
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax TreeCode2
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document ReasoningCode2
LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question AnsweringCode2
Autoregressive Action Sequence Learning for Robotic ManipulationCode2
Bidirectional Decoding: Improving Action Chunking via Guided Test-Time SamplingCode2
LumberChunker: Long-Form Narrative Document SegmentationCode2
Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM modelsCode2
DadmaTools: Natural Language Processing Toolkit for Persian LanguageCode2
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document EmbeddingsCode1
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question AnsweringCode1
ALTo: Adaptive-Length Tokenizer for Autoregressive Mask GenerationCode1
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long VideosCode1
Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMsCode1
Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP DocumentsCode1
S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic AnalysisCode1
On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message PassingCode1
Attamba: Attending To Multi-Token StatesCode1
TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for NetworkCode1
CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data DiversityCode1
Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP StandardsCode1
Learning Variable Compliance Control From a Few Demonstrations for Bimanual Robot with Haptic Feedback Teleoperation SystemCode1
Dataset Decomposition: Faster LLM Training with Variable Sequence Length CurriculumCode1
Fast and Accurate Factual Inconsistency Detection Over Long DocumentsCode1
Sparse Modular Activation for Efficient Sequence ModelingCode1
Recurrent Attention Networks for Long-text ModelingCode1
ChordMixer: A Scalable Neural Attention Model for Sequences with Different LengthsCode1
NetKet 3: Machine Learning Toolbox for Many-Body Quantum SystemsCode1
tsflex: flexible time series processing & feature extractionCode1
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control CommunicationsCode1
Paradigm Shift in Natural Language ProcessingCode1
Improving Named Entity Recognition by External Context Retrieving and Cooperative LearningCode1
Unsupervised Technical Domain Terms Extraction using Term ExtractorCode1
Automated Concatenation of Embeddings for Structured PredictionCode1
AIN: Fast and Accurate Sequence Labeling with Approximate Inference NetworkCode1
Recurrent Chunking Mechanisms for Long-Text Machine Reading ComprehensionCode1
Capturing Global Informativeness in Open Domain Keyphrase ExtractionCode1
Review highlights: opinion mining on reviews: a hybrid model for rule selection in aspect extractionCode1
Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling TasksCode1
Semi-supervised Multitask Learning for Sequence LabelingCode1
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling—0
CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs—0
Show:102550
← PrevPage 1 of 9Next →
All datasetsCoNLL-2000Penn TreebankCoNLL 2003 (German)CoNLL 2003 (English)CoNLL 2003

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ACEExact Span F197.3—Unverified
2BERT-CRF (Replicated in AdaSeq)Exact Span F197.18—Unverified
3ELMo + MAT + Multi-TaskExact Span F197.04—Unverified
4CVT+Multi-Task+LargeExact Span F196.98—Unverified
5ELMo + Multi-TaskExact Span F196.83—Unverified
6FlairExact Span F196.72—Unverified
7SeqVATExact Span F195.45—Unverified
8Adversarial TrainingExact Span F195.25—Unverified
9BiLSTM-CRFExact Span F195.18—Unverified
#ModelMetricClaimedVerifiedStatus
1ACEF1 score97.3—Unverified
2Flair embeddingsF1 score96.72—Unverified
3JMTF1 score95.77—Unverified
4Low supervisionF1 score95.57—Unverified
5IntNet + BiLSTM-CRFF1 score95.29—Unverified
6Suzuki and IsozakiF1 score95.15—Unverified
7NCRF++F1 score95.06—Unverified
8BI-LSTM-CRF (Senna) (ours)F1 score94.46—Unverified
#ModelMetricClaimedVerifiedStatus
1ACEF195—Unverified
2Wang et al., 2020F194.4—Unverified
3AINF194.04—Unverified
#ModelMetricClaimedVerifiedStatus
1Wang et al., 2020F192—Unverified
2AINF191.71—Unverified
#ModelMetricClaimedVerifiedStatus
1Def2VecAUC93.07—Unverified