paper-with-me

Papers

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling

2024-09-30 · David Grangier, Simin Fan, Skyler Seto, Pierre Ablin

Specialist language models (LMs) focus on a specific task or domain on which they often outperform generalist LMs of the same size. However, the specialist data needed to pretrain these models is only available in limited amount for most tasks. In this work, we build specialist models from large generalist training sets instead. We adjust the training distribution of the generalist data with guidance from the limited domain-specific data. We explore several approaches, with clustered importance sampling standing out. This method clusters the generalist dataset and samples from these clusters based on their frequencies in the smaller specialist dataset. It is scalable, suitable for pretraining and continued pretraining, it works well in multi-task settings. Our findings demonstrate improvements across different domains in terms of language modeling perplexity and accuracy on multiple-choice question tasks. We also present ablation studies that examine the impact of dataset sizes, clustering configurations, and model sizes.

📄 PDF Abstract BibTeX arXiv:2410.03735

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMultiple-choice

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

UBERT: A Novel Language Model for Synonymy Prediction at Scale in the UMLS Metathesaurus

2022-04-27 · Thilini Wijesiriwardene, Vinh Nguyen, Goonmeet Bajaj, Hong Yung Yip 외

The UMLS Metathesaurus integrates more than 200 biomedical source vocabularies. During the Metathesaurus construction process, synonymous terms are clustered into concepts by human editors, assisted by lexical similarity…

Language ModelingLanguage ModellingPredictionSentence

UBERT: A Novel Language Model for Synonymy Prediction at Scale in the UMLS Metathesaurus

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The UMLS Metathesaurus integrates more than 200 biomedical source vocabularies. During the Metathesaurus construction process, synonymous terms are clustered into concepts by human editors, assisted by lexical similarity…

Language ModelingLanguage ModellingPredictionSentence

PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data

2025-03-15 · Yunbo Long, Liming Xu, Ge Zheng, Alexandra Brintrup

Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy. However, heterogeneous data across diverse regions, driven by factors such as varying consumer behavio…

Demand ForecastingFeature ImportanceFederated LearningPrivacy Preserving+1

Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization

2025-05-30 · Luong Ho, Khanh Le, Vinh Pham, Bao Nguyen 외

Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability. Despite its importance, the integra…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+3

FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment

2026-02-02 · Riccardo Zaccone, Stefanos Laskaridis, Marco Ciccone, Samuel Horváth arxiv

The growing scale of deep neural networks, encompassing large language models (LLMs) and vision transformers (ViTs), has made training from scratch prohibitively expensive and deployment increasingly costly. These models…