Fast Gated Neural Domain Adaptation: Language Model as a Case Study

2016-12-01 · COLING 2016 12 · Jian Zhang, Xiaofeng Wu, Andy Way, Qun Liu

Neural network training has been shown to be advantageous in many natural language processing applications, such as language modelling or machine translation. In this paper, we describe in detail a novel domain adaptation mechanism in neural network training. Instead of learning and adapting the neural network on millions of training sentences {--} which can be very time-consuming or even infeasible in some cases {--} we design a domain adaptation gating mechanism which can be used in recurrent neural networks and quickly learn the out-of-domain knowledge directly from the word vector representations with little speed overhead. In our experiments, we use the recurrent neural network language model (LM) as a case study. We show that the neural LM perplexity can be reduced by 7.395 and 12.011 using the proposed domain adaptation mechanism on the Penn Treebank and News data, respectively. Furthermore, we show that using the domain-adapted neural LM to re-rank the statistical machine translation n-best list on the French-to-English language pair can significantly improve translation quality.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationLanguage ModelingLanguage Modelling Machine Translation Translation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization

2015-10-15 · Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang

This paper addresses classification tasks on a particular target domain in which labeled training data are only available from source domains different from (but related to) the target. Two closely related frameworks, do…

Domain Adaptation Domain Generalization General Classification Object Recognition+1

Source -Free Domain Adaptation for Speaker Verification in Data-Scarce Languages and Noisy Channels

2024-06-09 · Shlomo Salo Elia, Aviad Malachi, Vered Aharonson, Gadi Pinkas

Domain adaptation is often hampered by exceedingly small target datasets and inaccessible source data. These conditions are prevalent in speech verification, where privacy policies and/or languages with scarce speech res…

Domain Adaptation Source-Free Domain Adaptation Speaker Verification

TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models

2026-07-10 · Tianyou Jiang, Ziyu Zhou arxiv

Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretrain…

MedTS-TTT: Test-Time Training for Medical Time Series Classification

2026-06-19 · Mingzhi Chen, Yiyu Gui, Guibo Luo arxiv

Medical time series (MedTS) signals such as electroencephalography (EEG) and electrocardiography (ECG) support many clinical applications. However, substantial subject-level heterogeneity often induces subject-level dist…

Time Series Classification Domain Adaptation

Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments

2025-06-20 · Yasir Ali Farrukh, Syed Wali, Irfan Khan, Nathaniel D. Bastian

Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA…

Domain Adaptation Unsupervised Domain Adaptation