Domain adaptation of POS taggers without handcrafted features

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Standard

Domain adaptation of POS taggers without handcrafted features. / Rodrigues, Irving M.; Fernandes, Eraldo R.; dos Santos, Cicero N.
IJCNN 2017: the International Joint Conference on Neural Networks. Piscataway: Institute of Electrical and Electronics Engineers Inc., 2017. p. 3331-3338 7966274 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2017).

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Harvard

Rodrigues, IM, Fernandes, ER & dos Santos, CN 2017, Domain adaptation of POS taggers without handcrafted features. in IJCNN 2017: the International Joint Conference on Neural Networks., 7966274, Proceedings of the International Joint Conference on Neural Networks, vol. 2017, Institute of Electrical and Electronics Engineers Inc., Piscataway, pp. 3331-3338, International Joint Conference on Neural Networks, Anchorage, United States, 14.05.17. https://doi.org/10.1109/IJCNN.2017.7966274

APA

Rodrigues, I. M., Fernandes, E. R., & dos Santos, C. N. (2017). Domain adaptation of POS taggers without handcrafted features. In IJCNN 2017: the International Joint Conference on Neural Networks (pp. 3331-3338). Article 7966274 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2017.7966274

Vancouver

Rodrigues IM, Fernandes ER, dos Santos CN. Domain adaptation of POS taggers without handcrafted features. In IJCNN 2017: the International Joint Conference on Neural Networks. Piscataway: Institute of Electrical and Electronics Engineers Inc. 2017. p. 3331-3338. 7966274. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2017.7966274

Bibtex

@inbook{00f48f8535564d51896ec4b3ba5d0cd0,
title = "Domain adaptation of POS taggers without handcrafted features",
abstract = "Unsupervised domain adaptation is an attractive option when labeled data is lacking for some domain of interest but is available for other domain. Part-of-speech (POS) tagging is often considered a solved task when enough labeled data is available in the domain of interest. However, when considering a domain adaptation scenario, this is far from true. Several approaches have been proposed for domain adaptation of POS taggers, however as far as we know, all of them are based on handcrafted features. In this work, we employ a machine learning method whose input is exclusively composed of the raw text. This method learns word- and character-level representations (embeddings), and has been successfully applied to intra-domain tasks. We show that this method achieves strong performances on the domain adaptation of English and Portuguese POS taggers.",
keywords = "Informatics, tagging, syntactics, training, Vocabulary, training data, Feature extraction, Business informatics",
author = "Rodrigues, {Irving M.} and Fernandes, {Eraldo R.} and {dos Santos}, {Cicero N.}",
year = "2017",
month = jun,
day = "30",
doi = "10.1109/IJCNN.2017.7966274",
language = "English",
isbn = "978-1-5090-6183-9",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3331--3338",
booktitle = "IJCNN 2017",
address = "United States",
note = "International Joint Conference on Neural Networks, IJCNN 2017 ; Conference date: 14-05-2017 Through 19-05-2017",
url = "https://ieeexplore.ieee.org/xpl/conhome/7958416/proceeding",

}

RIS

TY - CHAP

T1 - Domain adaptation of POS taggers without handcrafted features

AU - Rodrigues, Irving M.

AU - Fernandes, Eraldo R.

AU - dos Santos, Cicero N.

PY - 2017/6/30

Y1 - 2017/6/30

N2 - Unsupervised domain adaptation is an attractive option when labeled data is lacking for some domain of interest but is available for other domain. Part-of-speech (POS) tagging is often considered a solved task when enough labeled data is available in the domain of interest. However, when considering a domain adaptation scenario, this is far from true. Several approaches have been proposed for domain adaptation of POS taggers, however as far as we know, all of them are based on handcrafted features. In this work, we employ a machine learning method whose input is exclusively composed of the raw text. This method learns word- and character-level representations (embeddings), and has been successfully applied to intra-domain tasks. We show that this method achieves strong performances on the domain adaptation of English and Portuguese POS taggers.

AB - Unsupervised domain adaptation is an attractive option when labeled data is lacking for some domain of interest but is available for other domain. Part-of-speech (POS) tagging is often considered a solved task when enough labeled data is available in the domain of interest. However, when considering a domain adaptation scenario, this is far from true. Several approaches have been proposed for domain adaptation of POS taggers, however as far as we know, all of them are based on handcrafted features. In this work, we employ a machine learning method whose input is exclusively composed of the raw text. This method learns word- and character-level representations (embeddings), and has been successfully applied to intra-domain tasks. We show that this method achieves strong performances on the domain adaptation of English and Portuguese POS taggers.

KW - Informatics

KW - tagging

KW - syntactics

KW - training

KW - Vocabulary

KW - training data

KW - Feature extraction

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=85030974151&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2017.7966274

DO - 10.1109/IJCNN.2017.7966274

M3 - Article in conference proceedings

AN - SCOPUS:85030974151

SN - 978-1-5090-6183-9

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 3331

EP - 3338

BT - IJCNN 2017

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

T2 - International Joint Conference on Neural Networks

Y2 - 14 May 2017 through 19 May 2017

ER -

Recently viewed

Publications

  1. Case Study
  2. Numerical investigation of laser beam-welded AA2198 joints under different artificial ageing conditions
  3. Evaluation von Unterrichtsstandards
  4. Random walks on infinite self-similar graphs
  5. Do We Really Know The Benefit Of Machine Learning In Production Planning And Control? A Systematic Review Of Industry Case Studies
  6. The Role of Zn on the Elevated Temperature Compression Behavior of Mg5Nd
  7. Do protected areas networks ensure the supply of ecosystem services? Spatial patterns of two nature reserve systems in semi-arid Spain
  8. The multipole resonance probe
  9. A new approach to semantic sustainability assessment
  10. Restricted nonlinear approximation
  11. Risk preferences under heterogeneous environmental risk
  12. Dynamics of Supply Chains Under Mixed Production Strategies
  13. Adaptive Lehrerinterventionen beim mathematischen Modellieren
  14. Feasibility of a worker-directed web-based intervention for employees with depressive symptoms
  15. A review of FEM code accuracy for reliable extrusion process analysis
  16. The IRENA Project Navigator
  17. Classifying railway stations for strategic transport and land use planning
  18. A general result on absolute continuity of non-uniform self-similar measures on the real line
  19. B7-H1 Selectively Controls TH17 Differentiation and Central Nervous System Autoimmunity via a Novel Non-PD-1-Mediated Pathway
  20. Similar factors underlie tree abundance in forests in native and alien ranges
  21. Propagation of particles injected from interplanetary shocks
  22. Bifurcation loads of circular curved beams of glued-laminated timber with continuous lateral support
  23. MICSIM-4J - A General Microsimulation Model
  24. Analysis of observability of a differential equation system describing a synchronous electromagnetic drive
  25. Associations between the financial and industry expertise of audit committee members and Key Audit Matters within related audit reports
  26. Microstructure and hardness evolution of laser metal deposited AA5087 wall-structures
  27. The multi-criteria effectiveness evaluation of the robotic group based on 3D real-time vision system
  28. The ESBW Short Scale A Test for Assessing Teachers’ Standards-Based Educational Knowledge
  29. Intra-specific leaf trait responses to species richness at two different local scales
  30. Traits of butterfly communities change from specialist to generalist characteristics with increasing land-use intensity
  31. Abnormal extrusion texture and reversed yield asymmetry in a Mg–Y-Sm-Zn-Zr alloy
  32. Microstructure and creep properties of MEZ magnesium alloy processed by thixocasting
  33. Efficient Classification of Images with Taxonomies
  34. Anisotropic wavelet bases and thresholding
  35. Recent developments in the manufacture of complex components by influencing the material flow during extrusion
  36. Sensitivity of trace-element analysis by X-ray emission induced by 0.1-10 MeV electrons
  37. An extended kalman filter for temperature monitoring of a metal-polymer hybrid fibre based heater structure
  38. Revisiting Carbon Disclosure and Performance
  39. Aluminium-rich coring structures in Mg-Al alloys with carbon inoculation
  40. An EEG frequency tagging study on biological motion perception in children with DCD
  41. The Cox ring of the space of complete rank two collineations
  42. Microstructure, mechanical and corrosion properties of Mg-Gd-Zn alloys
  43. Peer Evaluation Can Reliably Measure Local Knowledge
  44. Helping to improve suggestion systems
  45. Study on Mg–Si–Sr ternary alloys for biomedical applications
  46. Robust Current Decoupling in a Permanent Magnet Motor Combining a Geometric Method and SMC