Papers token-classification
“token-classification” 태그가 달린 논문 99편 · 필터 해제
Nested Named Entity Recognition as Single-Pass Sequence Labeling
We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to st…
named-entity-recognitionNamed Entity RecognitionNested Named Entity RecognitionStructured Prediction+2The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks
Translation-based strategies for cross-lingual transfer XLT such as translate-train -- training on noisy target language data translated from the source language -- and translate-test -- evaluating on noisy source langua…
Cross-Lingual Transfertoken-classificationToken ClassificationTranslation+1MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores
Recent advances in large language models have significantly improved their ability to process long-context input, but practical applications are challenged by increased inference time and resource consumption, particular…
Long-Context Understandingtoken-classificationToken ClassificationRobust and Fine-Grained Detection of AI Generated Texts
An ideal detection system for machine generated content is supposed to work well on any generator as many more advanced LLMs come into existence day by day. Existing systems often struggle with accurately identifying AI-…
token-classificationToken ClassificationImproving Applicability of Deep Learning based Token Classification models during Training
This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. Th…
document understandingtoken-classificationToken ClassificationBeyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a…
Image Generationtoken-classificationToken ClassificationLettuceDetect: A Hallucination Detection Framework for RAG Applications
Retrieval Augmented Generation (RAG) systems remain vulnerable to hallucinated answers despite incorporating external knowledge sources. We present LettuceDetect a framework that addresses two critical limitations in exi…
8kGPUHallucinationRAG+3Learning the Language of NVMe Streams for Ransomware Detection
We apply language modeling techniques to detect ransomware activity in NVMe command sequences. We design and train two types of transformer-based models: the Command-Level Transformer (CLT) performs in-context token clas…
Language ModelingLanguage Modellingtoken-classificationToken ClassificationGliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian
We present GliLem -- a novel hybrid lemmatization system for Estonian that enhances the highly accurate rule-based morphological analyzer Vabamorf with an external disambiguation module based on GliNER -- an open vocabul…
Information RetrievalLEMMALemmatizationNER+3POS-tagging to highlight the skeletal structure of sentences
This study presents the development of a part-of-speech (POS) tagging model to extract the skeletal structure of sentences using transfer learning with the BERT architecture for token classification. The model, fine-tune…
Machine TranslationMorphological AnalysisPart-Of-Speech TaggingPOS+5Bangla Grammatical Error Detection Leveraging Transformer-based Token Classification
Bangla is the seventh most spoken language by a total number of speakers in the world, and yet the development of an automated grammar checker in this language is an understudied problem. Bangla grammatical error detecti…
Grammatical Error Detectiontoken-classificationToken ClassificationAutoTrain: No-code training for state-of-the-art models
With the advancements in open-source models, training (or finetuning) models on custom datasets has become a crucial part of developing solutions which are tailored to specific industrial or open-source applications. Yet…
Classificationimage-classificationImage ClassificationLanguage Modeling+8ChuLo: Chunk-Level Key Information Representation for Long Document Processing
Transformer-based models have achieved remarkable success in various Natural Language Processing (NLP) tasks, yet their ability to handle long documents is constrained by computational limitations. Traditional approaches…
ChunkingClassificationDocument Classificationdocument understanding+5BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation
Parameter-efficient fine-tuning (PEFT) of large language models (LLMs) has gained considerable attention as a flexible and efficient way of adapting LLMs to downstream tasks. Among these methods, weighted decomposed low-…
Natural Language Understandingparameter-efficient fine-tuningText Generationtoken-classification+1GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes
The detection of bias in natural language processing (NLP) is a critical challenge, particularly with the increasing use of large language models (LLMs) in various domains. This paper introduces GUS-Net, an innovative ap…
Bias Detectiontoken-classificationToken ClassificationBoosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation
The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential to partially bridge …
DescriptiveInductive BiasLanguage ModelingLanguage Modelling+5TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning
The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficienc…
Code SummarizationComputational EfficiencyQuestion Answeringreinforcement-learning+5Preserving Empirical Probabilities in BERT for Small-sample Clinical Entity Recognition
Named Entity Recognition (NER) encounters the challenge of unbalanced labels, where certain entity types are overrepresented while others are underrepresented in real-world datasets. This imbalance can lead to biased mod…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+2The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts
This paper introduces the MERIT Dataset, a multimodal (text + image + layout) fully labeled dataset within the context of school reports. Comprising over 400 labels and 33k samples, the MERIT Dataset is a valuable resour…
document understandingtoken-classificationToken ClassificationEvent Extraction for Portuguese: A QA-driven Approach using ACE-2005
Event extraction is an Information Retrieval task that commonly consists of identifying the central word for the event (trigger) and the event's arguments. This task has been extensively studied for English but lags behi…
Event ExtractionInformation RetrievalQuestion Answeringtoken-classification+1