Filters








1,651,146 Hits in 5.4 sec

Associative Domain Adaptation [article]

Philip Haeusser, Thomas Frerix, Alexander Mordvintsev, Daniel Cremers
2017 arXiv   pre-print
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical  ...  Finally, we show that the proposed association loss produces embeddings that are more effective for domain adaptation compared to methods employing maximum mean discrepancy as a similarity measure in embedding  ...  Figure 1 : Associative domain adaptation.  ... 
arXiv:1708.00938v1 fatcat:kltypociqbdf5hmhhk65k36lce

Associative Domain Adaptation

Philip Haeusser, Thomas Frerix, Alexander Mordvintsev, Daniel Cremers
2017 2017 IEEE International Conference on Computer Vision (ICCV)  
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical  ...  Finally, we show that the proposed association loss produces embeddings that are more effective for domain adaptation compared to methods employing maximum mean discrepancy as a similarity measure in embedding  ...  Figure 1 : Associative domain adaptation.  ... 
doi:10.1109/iccv.2017.301 dblp:conf/iccv/HausserFMC17 fatcat:wcxeuubahjbsfmuqjckzooikdq

Associative Partial Domain Adaptation [article]

Youngeun Kim, Sungeun Hong, Seunghan Yang, Sungil Kang, Yunho Jeon, Jiwon Kim
2020 arXiv   pre-print
Our Associative Partial Domain Adaptation (APDA) utilizes intra-domain association to actively select out non-trivial anomaly samples in each source-private class that sample-level weighting cannot handle  ...  Partial Adaptation (PDA) addresses a practical scenario in which the target domain contains only a subset of classes in the source domain.  ...  Associative Partial Domain Adaptation To address negative transfer in PDA, we propose Associative Partial Domain Adaptation (APDA). The overall flow of APDA can be seen in Fig. 2 .  ... 
arXiv:2008.03111v1 fatcat:saoukqvprfeojjeaqx2gwtywne

Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes

Marina Sedinkina, Nikolas Breitkopf, Hinrich Schütze
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We compare three approaches: (I) manual adaptation of the domain-general dictionary H4N, (ii) automatic adaptation of H4N and (iii) a combination consisting of first manual, then automatic adaptation.  ...  In particular, automatic adaptation performs better than manual adaptation.  ...  domain -and show that automatic domain adaptation performs better.  ... 
doi:10.18653/v1/p19-1034 dblp:conf/acl/SedinkinaBS19 fatcat:hgeisjhmx5bpldcjelulwaqy4q

Time Series Domain Adaptation via Sparse Associative Structure Alignment [article]

Ruichu Cai, Jiawei Chen, Zijian Li, Wei Chen, Keli Zhang, Junjian Ye, Zhuozhang Li, Xiaoyan Yang, Zhenjie Zhang
2021 arXiv   pre-print
To reduce the difficulty in the discovery of causal structure, we relax it to the sparse associative structure and propose a novel sparse associative structure alignment model for domain adaptation.  ...  Domain adaptation on time series data is an important but challenging task.  ...  Related Works In this section, we mainly focus on the existing techniques on unsupervised domain adaptation as well as time series domain adaptation. Domain Adaptation on Non-Time Series Data.  ... 
arXiv:2012.11797v2 fatcat:bft6joyvjfcazbaiigiszwpgs4

Frustratingly Easy Domain Adaptation

Hal Daumé III
2007 Annual Meeting of the Association for Computational Linguistics  
Moreover, it is trivially extended to a multidomain adaptation problem, where one has data from a variety of different domains.  ...  We describe an approach to domain adaptation that is appropriate exactly in the case when one has enough "target" data to do slightly better than just using only "source" data.  ...  Adaptation by Feature Augmentation In this section, we describe our approach to the domain adaptation problem.  ... 
dblp:conf/acl/Daume07 fatcat:rhmxxruwhndb5n7eqkfyoj6ica

Domain Adaptation by Constraining Inter-Domain Variability of Latent Feature Representation

Ivan Titov
2011 Annual Meeting of the Association for Computational Linguistics  
We consider a semi-supervised setting for domain adaptation where only unlabeled data is available for the target domain.  ...  Such a model would cluster features in both domains and ensure that at least some of the latent variables are predictive of the label on the source domain.  ...  specific to the domain-adaptation setting.  ... 
dblp:conf/acl/Titov11 fatcat:ssp5pnzozjfuvk36eqhyanu4bq

Topologically-associating domains: gene warehouses adapted to serve transcriptional regulation

Sergey V. Razin, Alexey A. Gavrilov, Yegor S. Vassetzky, Sergey V. Ulianov
2016 Transcription  
Structural-functional domains have long been hypothesized to occur in eukaryotic chromosomes, but their existence still remains controversial.  ...  However, after having appeared over the course of evolution, this "storage system" was adapted to serve other functions.  ...  (self-interacting) domains (TADs)  ... 
doi:10.1080/21541264.2016.1181489 pmid:27111547 pmcid:PMC4984688 fatcat:qvi2x6pquvcx7okmxfibvozmky

Adapting to All Domains at Once: Rewarding Domain Invariance in SMT

Hoang Cuong, Khalil Sima'an, Ivan Titov
2016 Transactions of the Association for Computational Linguistics  
Existing work on domain adaptation for statistical machine translation has consistently assumed access to a small sample from the test distribution (target domain) at training time.  ...  feature weights on out-of-domain data (rather than on the target domain).  ...  We conduct our experiments on three language pairs and explore adaptation to 9 domain adaptation tasks in total.  ... 
doi:10.1162/tacl_a_00086 fatcat:gyvznhzw4fei5i4jy6jdrnv4t4

Instance Weighting for Domain Adaptation in NLP

Jing Jiang, ChengXiang Zhai
2007 Annual Meeting of the Association for Computational Linguistics  
Domain adaptation is an important problem in natural language processing (NLP) due to the lack of labeled data in novel domains.  ...  We then propose a general instance weighting framework for domain adaptation.  ...  Domain Adaptation In this section, we define and analyze domain adaptation from a theoretical point of view.  ... 
dblp:conf/acl/JiangZ07 fatcat:ax34sgt5jreuxmfuzqxy574zpi

Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation [article]

Guoliang Kang, Yunchao Wei, Yi Yang, Yueting Zhuang, Alexander G. Hauptmann
2020 arXiv   pre-print
Experiment results on two representative domain adaptation benchmarks, i.e.  ...  Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations.  ...  Related Work Domain Adaptation. Domain Adaptation has been studied for decades [3, 2, 13, 35, 17, 6, 30] in theory and in various applications.  ... 
arXiv:2011.00147v1 fatcat:25fdgzqprregdm7uucuqw7yyoy

Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation

Benjamin Marie, Atsushi Fujita
2017 Transactions of the Association for Computational Linguistics  
We present a new framework to induce an in-domain phrase table from in-domain monolingual data that can be used to adapt a general-domain statistical machine translation system to the targeted domain.  ...  We experimented on the language pair English–French, both translation directions, in two domains and obtained consistently better results than a strong baseline system that uses an in-domain bilingual  ...  In order to circumvent the lack of in-domain parallel data, this paper presents a new method to adapt an existing SMT system to a specific domain by inducing an in-domain phrase table, i.e., a set of phrase  ... 
doi:10.1162/tacl_a_00075 fatcat:ljajkmckzzdqtc72ocwhz35u2i

Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models

Xiaolei Huang, Michael J. Paul
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Second, we propose a time-driven neural classification model inspired by methods for domain adaptation. Experiments on six corpora show how these methods can make classifiers more robust over time.  ...  This paper describes two complementary ways to adapt classifiers to shifts across time.  ...  Frustratingly easy domain adaptation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 256-263.  ... 
doi:10.18653/v1/p19-1403 dblp:conf/acl/HuangP19 fatcat:6otebknxaffyrn65drwwvel5aq

Automatic Domain Adaptation for Parsing

David McClosky, Eugene Charniak, Mark Johnson
2010 North American Chapter of the Association for Computational Linguistics  
We study this problem as a new task -multiple source parser adaptation. Our system trains on corpora from many different domains.  ...  Tested across six domains, our system outperforms all non-oracle baselines including the best domain-independent parsing model.  ...  The scale of the web demands an automatic solution to the domain detection and adaptation problems.  ... 
dblp:conf/naacl/McCloskyCJ10 fatcat:ofwgfpqsj5dtnbgi4ixdn3tbbu

Aspect-augmented Adversarial Networks for Domain Adaptation

Yuan Zhang, Regina Barzilay, Tommi Jaakkola
2017 Transactions of the Association for Computational Linguistics  
We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain.  ...  Moreover, all these prior approaches focus on in-domain classification. In this paper, however, we study the task in the context of domain adaptation.  ...  Therefore, we explore the task of adaptation from each of the five hotel aspects to the restaurant domain.  ... 
doi:10.1162/tacl_a_00077 fatcat:kl4ufg3ukrfp3aifkruw3tzmrm
« Previous Showing results 1 — 15 out of 1,651,146 results