paper-with-me

Papers

Gradual Fine-Tuning for Low-Resource Domain Adaptation

2021-03-03 · EACL (AdaptNLP) 2021 4 · Haoran Xu, Seth Ebner, Mahsa Yarmohammadi, Aaron Steven White, Benjamin Van Durme, Kenton Murray

Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We demonstrate that gradually fine-tuning in a multi-stage process can yield substantial further gains and can be applied without modifying the model or learning objective.

📄 PDF Abstract BibTeX arXiv:2103.02205

Code (2)

fe1ixxu/Gradual-Finetune 공식 구현 pytorch
isi-boston/ed-pooling pytorch

Tasks

Domain Adaptation

Similar Papers 제목 키워드 기반

SemiAdapt and SemiLoRA: Efficient Domain Adaptation for Transformer-based Low-Resource Language Translation with a Case Study on Irish

2025-10-21 · Josh McGiff, Nikola S. Nikolov arxiv

Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally expensive when fine-tuning large multilingu…

parameter-efficient fine-tuningMachine TranslationTransfer LearningDomain Adaptation

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning

2025-06-06 · Yangui Fang, Jing Peng, Xu Li, Yu Xi 외

Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain Adaptationspeech-recognition+1

A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction

2025-05-27 · Bogdan Bogachov, Yaoyao Fiona Zhao

Despite recent advancements in domain adaptation techniques for large language models, these methods remain computationally intensive, and the resulting models can still exhibit hallucination issues. Most existing adapta…

Domain AdaptationHallucinationLanguage ModelingLanguage Modelling+1

Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation

2024-11-11 · Yao Ma, Samuel Louvan, Zhunxuan Wang

Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection p…

Domain AdaptationMulti-Source Unsupervised Domain AdaptationNatural Language InferenceSentiment Analysis+1

A Unified Speaker Adaptation Approach for ASR

2021-10-16 · EMNLP 2021 11 · Yingzhu Zhao, Chongjia Ni, Cheung-Chi Leung, Shafiq Joty 외

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Fur…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition