paper-with-me

Papers

Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters

2022-12-20 · Eugene Yang, Suraj Nair, Dawn Lawrie, James Mayfield, Douglas W. Oard

A popular approach to creating a zero-shot cross-language retrieval model is to substitute a monolingual pretrained language model in the retrieval model with a multilingual pretrained language model such as Multilingual BERT. This multilingual model is fined-tuned to the retrieval task with monolingual data such as English MS MARCO using the same training recipe as the monolingual retrieval model used. However, such transferred models suffer from mismatches in the languages of the input text during training and inference. In this work, we propose transferring monolingual retrieval models using adapters, a parameter-efficient component for a transformer network. By adding adapters pretrained on language tasks for a specific language with task-specific adapters, prior work has shown that the adapter-enhanced models perform better than fine-tuning the entire model when transferring across languages in various NLP tasks. By constructing dense retrieval models with adapters, we show that models trained with monolingual data are more effective than fine-tuning the entire model when transferring to a Cross Language Information Retrieval (CLIR) setting. However, we found that the prior suggestion of replacing the language adapters to match the target language at inference time is suboptimal for dense retrieval models. We provide an in-depth analysis of this discrepancy between other cross-language NLP tasks and CLIR.

📄 PDF Abstract BibTeX arXiv:2212.10448

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalLanguage ModelingLanguage ModellingRetrieval

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Residual Connection 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Orthogonal Language and Task Adapters in Zero-Shot Cross-Lingual Transfer

2020-12-11 · Marko Vidoni, Ivan Vulić, Goran Glavaš

Adapter modules, additional trainable parameters that enable efficient fine-tuning of pretrained transformers, have recently been used for language specialization of multilingual transformers, improving downstream zero-s…

Cross-Lingual TransferNERPOSPOS Tagging+1

Zero-Shot Cross-Lingual Transfer using Prefix-Based Adaptation

2025-10-28 · Snegha A, Sayambhu Sen, Piyush Singh Pasi, Abhishek Singhania 외 arxiv

With the release of new large language models (LLMs) like Llama and Mistral, zero-shot cross-lingual transfer has become increasingly feasible due to their multilingual pretraining and strong generalization capabilities.…

Zero-Shot Cross-Lingual Transferparameter-efficient fine-tuning

Orthogonal Language and Task Adapters in Zero-Shot Cross-Lingual Transfer

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

Adapter modules have recently been used for efficient fine-tuning and language specialization of massively multilingual Transformers (MMTs), improving downstream zero-shot cross-lingual transfer. In this work, we propose…

Cross-Lingual TransferZero-Shot Cross-Lingual Transfer

Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting

2021-08-01 · ACL (RepL4NLP) 2021 8 · Irene Li, Prithviraj Sen, Huaiyu Zhu, Yunyao Li 외

Cross-lingual text classification (CLTC) is a challenging task made even harder still due to the lack of labeled data in low-resource languages. In this paper, we propose zero-shot instance-weighting, a general model-agn…

Classificationtext-classificationText ClassificationZero-Shot Learning

Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

2022-06-08 · Stratos Xenouleas, Alexia Tsoukara, Giannis Panagiotakis, Ilias Chalkidis 외

We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual tr…

Cross-Lingual TransferTopic ClassificationTranslationZero-Shot Cross-Lingual Transfer