research-article

Free access

Domain adaptation with structural correspondence learning

Authors:

Fernando PereiraAuthors Info & Claims

EMNLP '06: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

Pages 120 - 128

Published: 22 July 2006 Publication History

Abstract

Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For many NLP tasks, however, we are confronted with new domains in which labeled data is scarce or non-existent. In such cases, we seek to adapt existing models from a resource-rich source domain to a resource-poor target domain. We introduce structural correspondence learning to automatically induce correspondences among features from different domains. We test our technique on part of speech tagging and show performance gains for varying amounts of source and target training data, as well as improvements in target domain parsing accuracy using our improved tagger.

References

[1]

R. Ando and T. Zhang. 2005a. A framework for learning predictive structures from multiple tasks and unlabeled data. JMLR, 6:1817--1853.

Digital Library

[2]

R. Ando and T. Zhang. 2005b. A high-performance semi-supervised learning method for text chunking. In ACL.

Digital Library

[3]

R. Ando. 2004. Exploiting unannotated corpora for tagging and chunking. In ACL. Short paper.

Digital Library

[4]

D. Blei, A. Ng, and M. Jordan. 2003. Latent dirichlet allocation. JMLR, 3:993--1022.

Digital Library

[5]

A. Blum and T. Mitchell. 1998. Combining labeled and unlabeled data with co-training. In Workshop on Computational Learning Theory.

Digital Library

[6]

P. Brown, V. Della Pietra, P. deSouza, J. Lai, and R. Mercer. 1992. Class-based n-gram models of natural language. Computational Linguistics, 18(4):467--479.

Digital Library

[7]

C. Chelba and A. Acero. 2004. Adaptation of maximum entropy capitalizer: Little data can help a lot. In EMNLP.

[8]

K. Crammer, Dekel O, J. Keshet, S. Shalev-Shwartz, and Y. Singer. 2006. Online passive-aggressive algorithms. JMLR, 7:551--585.

Digital Library

[9]

H. Daum'e III and D. Marcu. 2006. Domain adaptation for statistical classifiers. JAIR.

Digital Library

[10]

R. Florian, H. Hassan, A. Ittycheriah, H. Jing, N. Kambhatla, X. Luo, N. Nicolov, and S. Roukos. 2004. A statistical model for multilingual entity detection and tracking. In of HLT-NAACL.

[11]

L. Gillick and S. Cox. 1989. Some statistical issues in the comparison of speech recognition algorithms. In ICASSP.

[12]

R. Kuhn, P. Nguyen, J. C. Junqua, L. Goldwasser, N. Niedzielski, S. Fincke, K. Field, and M. Contolini. 1998. Eigenvoices for speaker adaptation. In ICSLP.

[13]

M. Lease and E. Charniak. 2005. Parsing biomedical literature. In IJCNLP.

Digital Library

[14]

M. Marcus, B. Santorini, and M. Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313--330.

Digital Library

[15]

R. McDonald, K. Crammer, and F. Pereira. 2005a. Flexible text segmentation with structured multilabel classification. In HLT-EMNLP.

Digital Library

[16]

R. McDonald, K. Crammer, and F. Pereira. 2005b. Online large-margin training of dependency parsers. In ACL.

Digital Library

[17]

S. Miller, J. Guinness, and A. Zamanian. 2004. Name tagging with word clusters and discriminative training. In HLT-NAACL.

[18]

F. Och. 2003. Minimum error rate training in statistical machine translation. In Proc. of ACL.

Digital Library

[19]

PennBioIE. 2005. Mining The Bibliome Project. http://bioie.ldc.upenn.edu/.

[20]

F. Pereira, N. Tishby, and L. Lee. 1993. Distributional clustering of english words. In ACL.

Digital Library

[21]

A. Ratnaparkhi. 1996. A maximum entropy model for part-of-speech tagging. In EMNLP.

[22]

B. Roark and M. Bacchiani. 2003. Supervised and unsupervised PCFG adaptation to novel domains. In HLT-NAACL.

Digital Library

[23]

B. Roark, M. Saraclar, M. Collins, and M. Johnson. 2004. Discriminative language modeling with conditional random fields and the perceptron algorithm. In ACL.

Digital Library

[24]

F. Sha and F. Pereira. 2003. Shallow parsing with conditional random fields. In HLT-NAACL.

Digital Library

[25]

K. Toutanova, D. Klein, C. D. Manning, and Y. Singer. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In NAACL.

Digital Library

Cited By

Yoo CKhudabukhsh AWilliams BChen YNeville J(2023)Auditing and robustifying COVID-19 misinformation datasets via anticontent samplingProceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v37i12.26780(15260-15268)Online publication date: 7-Feb-2023
https://dl.acm.org/doi/10.1609/aaai.v37i12.26780
Parvaresh AHosseinzadeh SFey D(2023)Resilience and Precision Assessment of Natural Language Processing Algorithms in Analog In-Memory Computing: A Hardware-Aware StudyProceedings of the 18th ACM International Symposium on Nanoscale Architectures10.1145/3611315.3633266(1-6)Online publication date: 18-Dec-2023
https://dl.acm.org/doi/10.1145/3611315.3633266
Chen YRao YChen SLei ZXie HLau RYin J(2023)Semi-Supervised Sentiment Classification and Emotion Distribution Learning Across DomainsACM Transactions on Knowledge Discovery from Data10.1145/357173617:5(1-30)Online publication date: 27-Feb-2023
https://dl.acm.org/doi/10.1145/3571736
Show More Cited By

Domain adaptation with structural correspondence learning
1. Computing methodologies
  1. Artificial intelligence
2. Hardware
  1. Power and energy
    1. Power estimation and optimization

Recommendations

Unsupervised Domain Adaptation With Label and Structural Consistency

Unsupervised domain adaptation deals with scenarios in which labeled data are available in the source domain, but only unlabeled data can be observed in the target domain. Since the classifiers trained by source-domain data would not be expected to ...
Domain adaptation for learning from label proportions using self-training
IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Learning from Label Proportions (LLP) is a machine learning problem in which the training data consist of bags of instances, and only the class label distribution for each bag is known. In some domains label proportions are readily available; for ...
Sparsity regularization label propagation for domain adaptation learning

Recently, domain adaptation learning (DAL) has shown surprising performance by utilizing labeled samples from the source (or auxiliary) domain to learn a robust classifier for the target domain of the interest which has a few or even no labeled samples. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image DL Hosted proceedings

EMNLP '06: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

July 2006

648 pages

ISBN:1932432736

Program Chairs:
Dan Jurafsky
Stanford University
,
Eric Gaussier
Xerox Research Centre Europe

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 22 July 2006

Qualifiers

Research-article

Acceptance Rates

EMNLP '06 Paper Acceptance Rate 73 of 234 submissions, 31%;

Overall Acceptance Rate 73 of 234 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

250
Total Citations
View Citations
4,076
Total Downloads

Downloads (Last 12 months)199
Downloads (Last 6 weeks)27

Reflects downloads up to 16 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yoo CKhudabukhsh AWilliams BChen YNeville J(2023)Auditing and robustifying COVID-19 misinformation datasets via anticontent samplingProceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v37i12.26780(15260-15268)Online publication date: 7-Feb-2023
https://dl.acm.org/doi/10.1609/aaai.v37i12.26780
Parvaresh AHosseinzadeh SFey D(2023)Resilience and Precision Assessment of Natural Language Processing Algorithms in Analog In-Memory Computing: A Hardware-Aware StudyProceedings of the 18th ACM International Symposium on Nanoscale Architectures10.1145/3611315.3633266(1-6)Online publication date: 18-Dec-2023
https://dl.acm.org/doi/10.1145/3611315.3633266
Chen YRao YChen SLei ZXie HLau RYin J(2023)Semi-Supervised Sentiment Classification and Emotion Distribution Learning Across DomainsACM Transactions on Knowledge Discovery from Data10.1145/357173617:5(1-30)Online publication date: 27-Feb-2023
https://dl.acm.org/doi/10.1145/3571736
An SBhat GGumussoy SOgras U(2023)Transfer Learning for Human Activity Recognition Using Representational Analysis of Neural NetworksACM Transactions on Computing for Healthcare10.1145/35639484:1(1-21)Online publication date: 16-Mar-2023
https://dl.acm.org/doi/10.1145/3563948
Huang TChen PZhang JLi RWang R(2022)A Transferable Time Series Forecasting Service Using Deep Transformer Model for Online SystemsProceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering10.1145/3551349.3560414(1-12)Online publication date: 10-Oct-2022
https://dl.acm.org/doi/10.1145/3551349.3560414
Li LYang LJiang HYan JLuo THua ZLiang GZuo CRoychoudhury ACadar CKim M(2022)AUGER: automatically generating review comments with pre-training modelsProceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering10.1145/3540250.3549099(1009-1021)Online publication date: 7-Nov-2022
https://dl.acm.org/doi/10.1145/3540250.3549099
Guo ALi XPang NZhao X(2022)Adversarial Cross-domain Community Question RetrievalACM Transactions on Asian and Low-Resource Language Information Processing10.1145/348729121:3(1-22)Online publication date: 10-Jan-2022
https://dl.acm.org/doi/10.1145/3487291
Zhang KLiu QHuang ZCheng MZhang KZhang MWu WChen EAmigo ECastells PGonzalo JCarterette BCulpepper JKazai G(2022)Graph Adaptive Semantic Transfer for Cross-domain Sentiment ClassificationProceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3477495.3531984(1566-1576)Online publication date: 6-Jul-2022
https://dl.acm.org/doi/10.1145/3477495.3531984
Lazaridou AKuncoro AGribovskaya EAgrawal DLiška ATerzi TGimenez Md'Autume CKocisky TRuder SYogatama DCao KYoung SBlunsom PRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)Mind the gapProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3542508(29348-29363)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3542508
Zhou JTsang IPan STan M(2021)Multi-class heterogeneous domain adaptationThe Journal of Machine Learning Research10.5555/3322706.336199820:1(2041-2071)Online publication date: 9-Mar-2021
https://dl.acm.org/doi/10.5555/3322706.3361998
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents