paper-with-me

Papers

Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data

2023-07-14 · Akshat Gupta, Xiaomo Liu, Sameena Shah

Domain adaptation is an important and widely studied problem in natural language processing. A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain. In this paper, we instead solve this problem from a dataset perspective. We modify the source domain dataset with simple lexical transformations to reduce the domain shift between the source dataset distribution and the target dataset distribution. We find that models trained on the transformed source domain dataset performs significantly better than zero-shot models. Using our proposed transformations to convert standard English to tweets, we reach an unsupervised part-of-speech (POS) tagging accuracy of 92.14% (from 81.54% zero shot accuracy), which is only slightly below the supervised performance of 94.45%. We also use our proposed transformations to synthetically generate tweets and augment the Twitter dataset to achieve state-of-the-art performance for POS tagging.

📄 PDF Abstract BibTeX arXiv:2307.10210

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationPart-Of-Speech TaggingPOSPOS TaggingUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Unsupervised Domain Adaptation Using Approximate Label Matching

2016-02-16 · Jordan T. Ash, Robert E. Schapire, Barbara E. Engelhardt

Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution. In this work, we present ap…

Domain AdaptationUnsupervised Domain Adaptation

Iterative Constrained Back-Translation for Unsupervised Domain Adaptation of Machine Translation

2022-10-01 · COLING 2022 10 · Hongxiao Zhang, Hui Huang, Jiale Gao, Yufeng Chen 외

Back-translation has been proven to be effective in unsupervised domain adaptation of neural machine translation (NMT). However, the existing back-translation methods mainly improve domain adaptability by generating in-d…

Domain AdaptationMachine TranslationNMTSentence+3

Unsupervised Domain Adaptation with Random Walks on Target Labelings

2017-06-16 · Twan van Laarhoven, Elena Marchiori

Unsupervised Domain Adaptation (DA) is used to automatize the task of labeling data: an unlabeled dataset (target) is annotated using a labeled dataset (source) from a related domain. We cast domain adaptation as the pro…

Domain AdaptationUnsupervised Domain Adaptation

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

2019-06-24 · Jun Wen, Nenggan Zheng, Junsong Yuan, Zhefeng Gong 외

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reduc…

Domain AdaptationUnsupervised Domain Adaptation

SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

2020-12-21 · ICCV 2021 10 · Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

Many existing approaches for unsupervised domain adaptation (UDA) focus on adapting under only data distribution shift and offer limited success under additional cross-domain label distribution shift. Recent work based o…

Domain AdaptationPseudo LabelUnsupervised Domain Adaptation