paper-with-me

홈 › Papers

A Study of Residual Adapters for Multi-Domain Neural Machine Translation

2020-11-01 · WMT (EMNLP) 2020 11 · Minh Quang Pham, Josep Maria Crego, François Yvon, Jean Senellart

Domain adaptation is an old and vexing problem for machine translation systems. The most common approach and successful to supervised adaptation is to fine-tune a baseline system with in-domain parallel data. Standard fine-tuning however modifies all the network parameters, which makes this approach computationally costly and prone to overfitting. A recent, lightweight approach, instead augments a baseline model with supplementary (small) adapter layers, keeping the rest of the mode unchanged. This has the additional merit to leave the baseline model intact, and adaptable to multiple domains. In this paper, we conduct a thorough analysis of the adapter model in the context of a multidomain machine translation task. We contrast multiple implementations of this idea on two language pairs. Our main conclusions are that residual adapters provide a fast and cheap method for supervised multi-domain adaptation; our two variants prove as effective as the original adapter model, and open perspective to also make adapted models more robust to label domain errors.

📄 PDF Abstract BibTeX

Code (1)

qmpham/experiments 공식 구현

Tasks

Domain AdaptationMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Latent Domain Learning with Dynamic Residual Adapters

2020-06-01 · Lucas Deecke, Timothy Hospedales, Hakan Bilen

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic feat…

Domain Adaptationimage-classificationImage ClassificationStyle Transfer

Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving

2026-08-04 · Xiang Li, Pengcheng Wang, Huazheng Wang, Saurabh Bagchi arxiv

Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a critical system dilemma between serving efficiency and task performanc…

Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters

2021-10-18 · WMT (EMNLP) 2021 11 · Asa Cooper Stickland, Alexandre Bérard, Vassilina Nikoulina

Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pai…

Cross-Lingual TransferDomain AdaptationMachine TranslationNMT+1

Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters

2021-05-16 · ACL ARR May 2021 5 · Anonymous

Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pai…

Cross-Lingual TransferDomain AdaptationMachine TranslationNMT+1

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters

2026-05-08 · Abdulvahap Mutlu, Şengül Doğan, Türker Tuncer arxiv

Manifold-Constrained Hyper-Connections (mHC) introduce a stability-motivated variant of multi stream residual mixing by constraining residual stream mixing matrices to the manifold of doubly stochastic matrices via Sinkh…