paper-with-me

Papers

Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding

2019-11-01 · IJCNLP 2019 11 · Quynh Do, Judith Gaspers

A typical cross-lingual transfer learning approach boosting model performance on a language is to pre-train the model on all available supervised data from another language. However, in large-scale systems this leads to high training times and computational requirements. In addition, characteristic differences between the source and target languages raise a natural question of whether source data selection can improve the knowledge transfer. In this paper, we address this question and propose a simple but effective language model based source-language data selection method for cross-lingual transfer learning in large-scale spoken language understanding. The experimental results show that with data selection i) source data and hence training speed is reduced significantly and ii) model performance is improved.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferLanguage ModelingLanguage ModellingSpoken Language UnderstandingTransfer Learning

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…

Similar Papers 제목 키워드 기반

Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data. Existing evaluations of cross-lingual generalisability of …

Cross-Lingual TransferPart-Of-Speech TaggingPOSPOS Tagging+1

Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages

2022-05-01 · ACL 2022 5 · Wietse de Vries, Martijn Wieling, Malvina Nissim

Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data. Existing evaluations of zero-shot cross-lingual generalisa…

Cross-Lingual TransferPart-Of-Speech TaggingPOSPOS Tagging+2

Budget-Xfer: Budget-Constrained Source Language Selection for Cross-Lingual Transfer to African Languages

2026-03-29 · Tewodros Kederalah Idris, Roald Eiselen, Prasenjit Mitra arxiv

Cross-lingual transfer learning enables NLP for low-resource languages by leveraging labeled data from higher-resource sources, yet existing comparisons of source language selection strategies do not control for total tr…

Cross-Lingual TransferSentiment Analysis

NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer

2020-08-04 · SEMEVAL 2020 · Hwijeen Ahn, Jimin Sun, Chan Young Park, Jungyun Seo

This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different threshol…

Cross-Lingual TransferData AugmentationLanguage IdentificationTranslation

Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection

2021-09-09 · EMNLP 2021 11 · Thuy-Trang Vu, Xuanli He, Dinh Phung, Gholamreza Haffari

This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We prop…

Contrastive LearningDomain AdaptationMachine TranslationNMT+2