The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Transfer Learning for Cross-Language Text Categorization through Active Correspondences Construction
Open accessAbstract
Most existing heterogeneous transfer learning (HTL) methods for cross-language text classification rely on sufficient cross-domain instance correspondences to learn a mapping across heterogeneous feature spaces, and assume that such correspondences are given in advance. However, in practice, correspondences between domains are usually unknown. In this case, extensively manual efforts are required to establish accurate correspondences across multilingual documents based on their content and meta-information. In this paper, we present a general framework to integrate active learning to construct correspondences between heterogeneous domains for HTL, namely HTL through active correspondences construction (HTLA). Based on this framework, we develop a new HTL method. On top of the new HTL method, we further propose a strategy to actively construct correspondences between domains. Extensive experiments are conducted on various multilingual text classification tasks to verify the effectiveness of HTLA.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In earlier research works, transfer learning has been used to cope with cross-language text classification.
“In earlier research works, transfer learning has been used to cope with cross-language text classification [147][148][149][150].”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [148]
Distribution variation in feature space where the data language changes can lead to a performance drop.
“Distribution variation in feature space where the data language changes can lead to a performance drop [147][148][149][150].”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [148]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning with Augmented Features for Heterogeneous Domain Adaptation
Duan, L., Xu, D., & Tsang, I. (2012) · arXiv · doi:10.48550/arxiv.1206.4660 · Cited by 320
Self-citation
Flagged first, then by citations
Research works printed but not linked: 24
- Avron, H.; Kale, S.; Kasiviswanathan, S. P.; and Sindhwani, V. 2012. Efficient and practical stochastic subgradient descent for nuclear norm regularization. In ICML .
- Platt, J. C.; Toutanova, K.; and Yih, W.-t. 2010. Translingual document representations from discriminative projections. In EMNLP , 251-261.
- Borgwardt, K. M.; Gretton, A.; Rasch, M. J.; Kriegel, H.-P.; Sch¨ olkopf, B.; and Smola, A. J. 2006. Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14):e49-e57.
- Cai, J.-F.; Cand` es, E. J.; and Shen, Z. 2010. A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization 20(4):1956-1982.
- Chang, C.-C., and Lin, C.-J. 2011. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2:27:1-27:27.
- Chattopadhyay, R.; Fan, W.; Davidson, I.; Panchanathan, S.; and Ye, J. 2013. Joint transfer and batch-mode active learning. In ICML , 253-261.
- Dai, W.; Chen, Y.; Xue, G.-R.; Yang, Q.; and Yu, Y. 2008. Translated learning: Transfer learning across different feature spaces. In NIPS , 353-360.
- Daum´ e III, H. 2007. Frustratingly easy domain adaptation. In ACL , 256-263.
- Gong, B.; Grauman, K.; and Sha, F. 2013. Connecting the dots with landmarks: Discriminatively learning domaininvariant features for unsupervised domain adaptation. In ICML , 222-230.
- Kulis, B.; Saenko, K.; and Darrell, T. 2011. What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In CVPR , 1785-1792.
- Nie, J.-Y.; Simard, M.; Isabelle, P.; and Durand, R. 1999. Cross-language information retrieval based on parallel texts and automatic mining of parallel texts from the web. In SIGIR , 74-81.
- Pan, S. J., and Yang, Q. 2010. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10):1345-1359.
- Prettenhofer, P., and Stein, B. 2010. Cross-language text classification using structural correspondence learning. In ACL , 1118-1127.
- Rai, P.; Saha, A.; Daum´ e III, H.; and Venkatasubramanian, S. 2010. Domain adaptation meets active learning. In NAACL HLT 2010 Workshop on ALNLP , 27-32.
- Shi, X.; Fan, W.; and Ren, J. 2008. Actively transfer domain knowledge. In ECML/PKDD . 342-357.
- Sriperumbudur, B. K., and Lanckriet, G. R. G. 2009. On the convergence of the concave-convex procedure. In NIPS , 1759-1767.
- Vinokourov, A.; Shawe-Taylor, J.; and Cristianini, N. 2002. Inferring a semantic representation of text via cross-language correlation analysis. In NIPS , 1473-1480.
- Wang, C., and Mahadevan, S. 2011. Heterogeneous domain adaptation using manifold alignment. In IJCAI , 1541-1546.
- Wang, Z.; Crammer, K.; and Vucetic, S. 2012. Breaking the curse of kernelization: Budgeted stochastic gradient descent for large-scale svm training. J. Mach. Learn. Res. 13(1):3103-3131.
- Wang, X.; Huang, T.-K.; and Schneider, J. 2014. Active transfer learning under model shift. In ICML , 1305-1313.
- Xiao, M., and Guo, Y. 2013. A novel two-step method for cross language representation learning. In NIPS , 1259-1267.
- Zhao, L.; Pan, S. J.; Xiang, E. W.; Zhong, E.; Lu, Z.; and Yang, Q. 2013. Active transfer learning for cross-system recommendation. In AAAI .
- Zhou, J. T.; Pan, S. J.; Tsang, I. W.; and Yan, Y . 2014a. Hybrid heterogeneous transfer learning through deep learning. In AAAI , 2213-2220.
- Zhou, J. T.; Tsang, I. W.; Pan, S. J.; and Tan, M. 2014b. Heterogeneous domain adaptation for multiple classes. In AISTATS , 1095-1103.
Cited by
Sorted by citations
Online grooming detection: A comprehensive survey of child exploitation in chat logs
Borj, P. R., Raja, K., & Bours, P. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110039 · Cited by 38
Metadata
- Authors
- Zhou, J., Pan, S., Tsang, I., & Ho, S.-S.
- Affiliations
- Institute of High Performance Computing (SG)
- Nanyang Technological University (SG)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2016-03-02
- Volume
- 30
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2568148245
- Cited by
- 50
- References
- 1
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 1 · 2022: 3 · 2021: 5 · 2020: 8 · 2019: 12 · 2018: 10 · 2017: 5 · 2016: 4
- FWCI
- 5.57
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- UTS ePRESS (University of Technology Sydney) (submittedVersion)
- Funders
- Nanyang Technological University (Tier-1 grant, M4081532.020)
- Ministry of Education, India
- Australian Research Council (LP150100671, FT130100746)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- heterogeneous transfer learning, multilingual text classification, active learning (machine learning), heterogeneous feature spaces
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
