Duplex adversarial networks for multiple-source domain adaptation

Zhou, Qiang; Zhou, Wenjiao; Wang, Shirui; Xing, Ying

doi:10.1016/j.knosys.2020.106569

Cited by 28 publications

(33 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, a related field to MLTL is multi-source domain adaptation (Mansour et al, 2009), where most prior work relies on the learning of domaininvariant features (Zhao et al, 2018;Chen and Cardie, 2018a). Ruder et al (2019) propose a general framework for selective sharing between domains, but their method learns static weights at the task level, while our model can dynamically select what to share at the instance level.…”

Section: Related Workmentioning

confidence: 99%

Multi-Source Cross-Lingual Model Transfer: Learning What to Share

Chen

Awadallah

Hassan

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks. Cross-lingual transfer learning (CLTL) is a viable method for building NLP models for a low-resource target language by leveraging labeled data from other (source) languages. In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.Unlike most existing methods that rely only on language-invariant features for CLTL, our approach coherently utilizes both languageinvariant and language-specific features at instance level. Our model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language 1 . This enables our model to learn effectively what to share between various languages in the multilingual setup. Moreover, when coupled with unsupervised multilingual embeddings, our model can operate in a zero-resource setting where neither target language training data nor cross-lingual resources are available. Our model achieves significant performance gains over prior art, as shown in an extensive set of experiments over multiple text classification and sequence tagging tasks including a large-scale industry dataset. Shared Feature Extractor Fs MoE Private Feature Extractor Fp MoE Task-Specific Predictor C Task Label Multilingual Word Representation Input Text J C Language Discriminator D Language Label J D 1 J D Gate Label 2 J g Forward and backward passes when updating the parameters of Fs, Fp and C Forward and backward passes when updating the parameters of D

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Source Cross-Lingual Model Transfer: Learning What to Share

Chen

Awadallah

Hassan

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Adversarial training methods (Ganin et al, 2016), which have also been applied to tasks where the space Y is not shared between source and target domains (Cohen et al, 2018), and multisource domain adaptation methods (Zhao et al, 2018;Guo et al, 2018) are complementary to our work and can contribute to higher performance.…”

Section: Related Workmentioning

confidence: 96%

Zero-Shot Entity Linking by Reading Entity Descriptions

Logeswaran

Chang

Lee

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

217

288

View full text Add to dashboard Cite

We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly specialized domains, and so no metadata or alias tables are assumed. In this setting, entities are only identified by text descriptions, and models must rely strictly on language understanding to resolve the new entities. First, we show that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities. Second, we propose a simple and effective adaptive pre-training strategy, which we term domainadaptive pre-training (DAP), to address the domain shift problem associated with linking unseen entities in a new domain. We present experiments on a new dataset that we construct for this task and show that DAP improves over strong pre-training baselines, including BERT. The data and code are available at https: //github.com/lajanugen/zeshel. 1

show abstract

“…Semantic segmentation applications recognise the relation between each image pixel and a suitable class label. Zhao et al [137] proposed the semantic segmentation algorithm under classification and regression methods for domain adaptation, whereas, Tsai et al [138] learned discriminative feature representations under space clustering. In [139–141], domain adaption for semantic segmentation are structured by learning the autoencoder.…”

Section: Unsupervised Domain Adaptation For Other Applicationsmentioning

confidence: 99%