paper-with-me

Papers token-classification

“token-classification” 태그가 달린 논문 99편 · 필터 해제

Nested Named Entity Recognition as Single-Pass Sequence Labeling

2025-05-22 · Alberto Muñoz-Ortiz, David Vilares, Caio Corro, Carlos Gómez-Rodríguez

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+2

The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks

2025-05-15 · Benedikt Ebing, Goran Glavaš

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+1

MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores

2025-04-23 · Fengwei Zhou, Jiafei Song, Wenjin Jason Li, Gengjian Xue 외

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 Classification

Robust and Fine-Grained Detection of AI Generated Texts

2025-04-16 · Ram Mohan Rao Kadiyala, Siddartha Pullakhandam, Kanwal Mehreen, Drishti Sharma 외

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 Classification

Improving Applicability of Deep Learning based Token Classification models during Training

2025-03-28 · Anket Mehra, Malte Prieß, Marian Himstedt

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 Classification

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

2025-02-27 · Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen 외

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 Classification

LettuceDetect: A Hallucination Detection Framework for RAG Applications

2025-02-24 · Ádám Kovács, Gábor Recski

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+3

Learning the Language of NVMe Streams for Ransomware Detection

2025-02-07 · Barak Bringoltz, Elisha Halperin, Ran Feraru, Evgeny Blaichman 외

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 Classification

GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian

2024-12-29 · Aleksei Dorkin, Kairit Sirts

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+3

POS-tagging to highlight the skeletal structure of sentences

2024-11-21 · Grigorii Churakov

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+5

Bangla Grammatical Error Detection Leveraging Transformer-based Token Classification

2024-11-13 · Shayekh Bin Islam, Ridwanul Hasan Tanvir, Sihat Afnan

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 Classification

AutoTrain: No-code training for state-of-the-art models

2024-10-21 · Abhishek Thakur

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+8

ChuLo: Chunk-Level Key Information Representation for Long Document Processing

2024-10-14 · Yan Li, Soyeon Caren Han, Yue Dai, Feiqi Cao

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+5

BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation

2024-10-13 · Peijia Qin, Ruiyi Zhang, Pengtao Xie

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+1

GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes

2024-10-10 · Maximus Powers, Umang Mavani, Harshitha Reddy Jonala, Ansh Tiwari 외

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 Classification

Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation

2024-10-01 · Bhargav Shandilya, Alexis Palmer

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+5

TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning

2024-09-19 · Shivam Shandilya, Menglin Xia, Supriyo Ghosh, Huiqiang Jiang 외

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+5

Preserving Empirical Probabilities in BERT for Small-sample Clinical Entity Recognition

2024-09-05 · Abdul Rehman, Jian Jun Zhang, Xiaosong Yang

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+2

The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts

2024-08-31 · I. de Rodrigo, A. Sanchez-Cuadrado, J. Boal, A. J. Lopez-Lopez

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 Classification

Event Extraction for Portuguese: A QA-driven Approach using ACE-2005

2024-08-29 · Luís Filipe Cunha, Ricardo Campos, Alípio Jorge

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
1–20 / 99 다음 →