paper-with-me

홈 › Papers

GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval

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

Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et al., 2021b), the performance of dense retrievers severely degrades under a domain shift. This limits the usage of dense retrieval approaches to only a few domains with large training datasets.In this paper, we propose the novel unsupervised domain adaptation method Generative Pseudo Labeling (GPL), which combines a query generator with pseudo labeling from a cross-encoder. On six representative domain-specialized datasets, we find the proposed GPL can outperform an out-of-the-box state-of-the-art dense retrieval approach by up to 8.9 points nDCG@10. GPL requires less (unlabeled) data from the target domain and is more robust in its training than previous methods.We further investigate the role of six recent pre-training methods in the scenario of domain adaptation for retrieval tasks, where only three could yield improved results. The best approach, TSDAE (Wang et al., 2021) can be combined with GPL, yielding another average improvement of 1.0 points nDCG@10 across the six tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationRetrievalUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
TSDAE TSDAE is an unsupervised sentence embedding method. During training, TSDAE encodes corrupted sentences into fixed-sized vectors and requires the decoder to reconstruct the…

Similar Papers 제목 키워드 기반

GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval

2021-12-14 · NAACL 2022 7 · Kexin Wang, Nandan Thakur, Nils Reimers, Iryna Gurevych

Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previou…

Domain AdaptationRetrievalUnsupervised Domain AdaptationZero-shot Text Search

ATPL: Mutually enhanced adversarial training and pseudo labeling for unsupervised domain adaptation

2022-08-17 · Knowledge-Based Systems 2022 8 · Changan Yi, Haotian Chen, Yonghui Xu, Yong liu 외

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to a related but unlabeled target domain. Most existing approaches either adversarially reduce the domain shift or use pseudo-labels …

Domain AdaptationUnsupervised Domain Adaptation

Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling

2021-09-19 · Cheng Chen, Quande Liu, Yueming Jin, Qi Dou 외

Domain adaptation typically requires to access source domain data to utilize their distribution information for domain alignment with the target data. However, in many real-world scenarios, the source data may not be acc…

DenoisingDomain AdaptationImage SegmentationSemantic Segmentation+1

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

2019-11-18 · Qian Wang, Toby P. Breckon

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different…

ClusteringDomain AdaptationStructured PredictionUnsupervised Domain Adaptation

Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

2020-12-07 · Bingyu Liu, Yuhong Guo, Jieping Ye, Weihong Deng

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few lab…

Domain AdaptationQ-Learningreinforcement-learningReinforcement Learning (RL)+2