Skip to main content
SpringerLink
Log in

Description and demonstration guided data augmentation for sequence tagging

  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

Fine-grained annotations are indispensable for sequence tagging tasks like named entity recognition and aspect-based sentiment analysis, which may incur extremely high time and labor costs. Recent efforts are towards data augmentation which aims to generate synthetic labeled instances. However, most existing methods adopt the random replacement or perturbation strategy under pre-defined constraints, and thus often lead to unstable performance. More importantly, these methods focus on producing more artificial samples yet neglect to make good use of real training samples. In this paper, we propose a novel description and demonstration guided data augmentation (D3A) approach for sequence tagging. On one hand, we collect dependency paths as descriptions to supervise the instance-level augmentation process, such that we can consistently generate high-quality synthetic data. On the other hand, we retrieve semantic or syntactic related features as demonstrations to enhance the learning capability of neural networks under limited training data. We conduct extensive experiments on four sequence tagging datasets with various sizes of training data. The results demonstrate that our proposed D3A approach can significantly improve the performance of sequence tagging, especially in low-resource scenarios.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. In this paper, the sequence tagger denotes a specific neural network for sequence tagging.

  2. In this paper, we use the B(beginning)-I(inside)-O(outside) tagging scheme throughout. Other schemes such as B-I-O-E(end)-S(single) can also be used as labels. The choice of tagging scheme does not affect the implementation of our method.

  3. For simplicity, we here use Backbone-Task (e.g., GloVe-ABSA) pairs for illustration.

  4. https://paperswithcode.com/sota/aspect-based-sentiment-analysis-on-semeval-7 for ABSA and https://paperswithcode.com/sota/named-entity-recognition-on-wnut-2016 for NER.

  5. https://github.com/howardhsu/BERT-for-RRC-ABSA.

  6. https://github.com/cuhksz-nlp/SANER. Since the best method CL-KL uses external resources, we select the second-best one SANER. We do not include the development set for training.

  7. We choose MR as the representative method because it performs well in most cases, and also because MR adopts the mention replacement strategy which is of the same type as ours.

References

  1. Asai, A., Hajishirzi, H.: Logic-guided data augmentation and regularization for consistent question answering. In: ACL, pp 5642–5650 (2020)

  2. Che, W., Zhao, Y., Guo, H., Su, Z., Liu, T.: Sentence compression for aspect-based sentiment analysis. IEEE ACM Trans. Audio Speech Lang. Process. 23(12), 2111–2124 (2015)

    Article  Google Scholar 

  3. Chen, Z., Qian, T.: Relation-aware collaborative learning for unified aspect-based sentiment analysis. In: ACL, pp 3685–3694 (2020)

  4. Dai, X., Adel, H.: An analysis of simple data augmentation for named entity recognition. In: COLING, pp 3861–3867 (2020)

  5. Derczynski, L., Nichols, E., van Erp, M., Limsopatham, N.: Results of the WNUT2017 shared task on novel and emerging entity recognition. In: NUT@EMNLP, pp 140–147 (2017)

  6. Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp 4171–4186 (2019)

  7. Ding, B., Liu, L., Bing, L., Kruengkrai, C., Nguyen, T.H., Joty, S.R., Si, L., Miao, C.: DAGA: data augmentation with a generation approach forlow-resource tagging tasks. In: EMNLP, pp 6045–6057 (2020)

  8. Fadaee, M., Bisazza, A., Monz, C.: Data augmentation for low-resource neural machine translation. In: ACL, pp 567–573 (2017)

  9. Feng, S.Y., Gangal, V., Wei, J., Chandar, S., Vosoughi, S., Mitamura, T., Hovy, E.H.: A survey of data augmentation approaches for NLP. In: ACL Findings, vol. ACL/IJCNLP 2021, pp 968–988 (2021)

  10. Guo, D., Kim, Y., Rush, A.M.: Sequence-level mixed sample data augmentation. In: EMNLP (2020)

  11. Huang, L., Sun, X., Li, S., Zhang, L., Wang, H.: Syntax-aware graph attention network for aspect-level sentiment classification. In: COLING, pp 799–810 (2020)

  12. Jiang, L., Yu, M., Zhou, M., Liu, X., Zhao, T.: Target-dependent twitter sentiment classification. In: ACL, pp 151–160 (2011)

  13. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: ICLR (2015)

  14. Kobayashi, S.: Contextual augmentation: Data augmentation by words with paradigmatic relations. In: NAACL-HLT, pp 452–457 (2018)

  15. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)

    Article  Google Scholar 

  16. Kruengkrai, C., Nguyen, T.H., Mahani, S.A., Bing, L.: Improving low-resource named entity recognition using joint sentence and token labeling. In: ACL, pp 5898–5905 (2020)

  17. Li, X., Bing, L., Li, P., Lam, W.: A unified model for opinion target extraction and target sentiment prediction. In: AAAI, pp 6714–6721 (2019)

  18. Lin, P., Yang, M., Lai, J.: Deep selective memory network with selective attention and inter-aspect modeling for aspect level sentiment classification. IEEE ACM Trans. Audio Speech Lang. Process. 29, 1093–1106 (2021)

    Article  Google Scholar 

  19. Lin, S., Gao, J., Zhang, S., He, X., Sheng, Y., Chen, J.: A continuous learning method for recognizing named entities by integrating domain contextual relevance measurement and Web farming mode of Web intelligence. World Wide Web 23(3), 1769–1790 (2020)

    Article  Google Scholar 

  20. Lin, Y., Fu, Y., Li, Y., Cai, G., Zhou, A.: Aspect-based sentiment analysis for online reviews with hybrid attention networks. World Wide Web 24 (4), 1215–1233 (2021)

    Article  Google Scholar 

  21. Longpre, S., Lu, Y., Tu, Z., DuBois, C.: An exploration of data augmentation and sampling techniques for domain-agnostic question answering. In: MRQA@EMNLP, pp 220–227 (2019)

  22. Luo, G., Huang, X., Lin, C.-Y., Nie, Z.: Joint entity recognition and disambiguation. In: EMNLP, pp 879–888 (2015)

  23. Luo, H., Li, T., Liu, B., Wang, B., Unger, H.: Improving aspect term extraction with bidirectional dependency tree representation. IEEE ACM Trans. Audio Speech Lang. Process. 27(7), 1201–1212 (2019)

    Article  Google Scholar 

  24. Ma, D., Li, S., Wu, F., Xie, X., Wang, H.: Exploring sequence-to-sequence learning in aspect term extraction. In: ACL, pp 3538–3547 (2019)

  25. Ma, D., Li, S., Zhang, X., Wang, H.: Interactive attention networks for aspect-level sentiment classification. In: IJCAI, pp 4068–4074 (2017)

  26. Manek, A.S., Shenoy, P.D., Mohan, M.C., Venugopal, K.R.: Aspect term extraction for sentiment analysis in large movie reviews using gini index feature selection method and SVM classifier. World Wide Web 20(2), 135–154 (2017)

    Article  Google Scholar 

  27. Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The stanford corenlp natural language processing toolkit. In: ACL, pp 55–60 (2014)

  28. Mitchell, M., Aguilar, J., Wilson, T., Durme, B.V.: Open domain targeted sentiment. In: EMNLP, pp 1643–1654 (2013)

  29. Nie, Y., Tian, Y., Wan, X., Song, Y., Dai, B.: Named entity recognition for social media texts with semantic augmentation. In: EMNLP, pp 1383–1391 (2020)

  30. Passos, A., Kumar, V., McCallum, A.: Lexicon infused phrase embeddings for named entity resolution. In: Proceedings of the Eighteenth Conference on Computational Natural Language Learning, CoNLL 2014, Baltimore, Maryland, USA, June 26-27, 2014, pp 78–86 (2014)

  31. Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., Al-Smadi, M., Al-Ayyoub, M., Zhao, Y., Qin, B., Clercq, O.D., Hoste, V., Apidianaki, M., Tannier, X., Loukachevitch, N.V., Kotelnikov, E.V., Bel, N., Zafra, S.M.J., Eryigit, G.: Semeval-2016 task 5: Aspect based sentiment analysis. In: NAACL-HLT, pp 19–30 (2016)

  32. Pontiki, M., Galanis, D., Papageorgiou, H., Manandhar, S., Androutsopoulos, I.: Semeval-2015 task 12: Aspect based sentiment analysis. In: SemEval, pp 486–495 (2015)

  33. Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I., Manandhar, S.: Semeval-2014 task 4: Aspect based sentiment analysis. In: SemEval, pp 27–35 (2014)

  34. Popescu, A.-M., Etzioni, O.: Extracting product features and opinions from reviews. In: EMNLP, pp 339–346 (2005)

  35. Ratinov, L.-A., Roth, D.: Design challenges and misconceptions in named entity recognition. In: CoNLL, pp 147–155 (2009)

  36. Sahin, G.G., Steedman, M.: Data augmentation via dependency tree morphing for low-resource languages. In: EMNLP, pp 5004–5009 (2018)

  37. Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: ACL (2016)

  38. Simard, P.Y., LeCun, Y., Denker, J.S., Victorri, B.: Transformation invariance in pattern recognition-tangent distance and tangent propagation. In: Neural Networks: Tricks of the Trade, pp 239–27 (1996)

  39. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  40. Strauss, B., Toma, B., Ritter, A., de Marneffe, M.-C., Xu, W.: Results of the WNUT16 named entity recognition shared task. In: NUT@COLING, pp 138–144 (2016)

  41. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CVPR, pp 1–9 (2015)

  42. Vicente, I.S., Saralegi, X., Agerri, R.: Elixa: A modular and flexible ABSA platform. In: SemEval@NAACL-HLT, pp 748–752 (2015)

  43. Wang, K., Shen, W., Yang, Y., Quan, X., Wang, R.: Relational graph attention network for aspect-based sentiment analysis. In: ACL, pp 3229–3238 (2020)

  44. Wei, J.W., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. In: EMNLP-IJCNLP, pp 6381–6387 (2019)

  45. Xu, H., Liu, B., Shu, L., Yu, P.S.: BERT post-training for review reading comprehension and aspect-based sentiment analysis. In: NAACL-HLT, pp 2324–2335 (2019)

  46. Xu, J., He, H., Sun, X., Ren, X., Li, S.: Cross-domain and semisupervised named entity recognition in chinese social media: A unified model. TASLP 26(11), 2142–2152 (2018)

    Google Scholar 

  47. Xue, W., Li, T., Rishe, N.: Aspect identification and ratings inference for hotel reviews. World Wide Web 20(1), 23–37 (2017)

    Article  Google Scholar 

  48. Yan, H., Deng, B., Li, X., Qiu, X.: TENER: adapting transformer encoder for named entity recognition. CoRR arXiv:1911.04474 (2019)

  49. Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: ICLR (2018)

  50. Zhang, M., Zhang, Y., Vo, D-T: Neural networks for open domain targeted sentiment. In: EMNLP, pp 612–621 (2015)

  51. Zhang, M., Qian, T.: Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis. In: EMNLP, pp 3540–3549 (2020)

  52. Zhang, R., Yu, Y., Zhang, C.: Seqmix: Augmenting active sequence labeling via sequence mixup. In: EMNLP, pp 8566–8579 (2020)

  53. Zhou, J.T., Zhang, H., Jin, D., Zhu, H., Fang, M., Goh, R.S.M., Kwok, K.: Dual adversarial neural transfer for low-resource named entity recognition. In: ACL, pp 3461–3471 (2019)

  54. Zhu, P., Chen, Z., Zheng, H., Qian, T.: Aspect aware learning for aspect category sentiment analysis. TKDD 13(6) (2019)

Download references

Acknowledgements

This work has been supported in part by the National Natural Science Foundation of China (NSFC) Projects (61572376, 62032016, 61972291).

Funding

National Natural Science Foundation of China Projects 61572376, 62032016, 61972291.

Author information

Authors and Affiliations

  1. School of Computer Science, Wuhan University, 16 Luojiashan Road, Wuhan, 430072, Hubei, China

    Zhuang Chen & Tieyun Qian

Authors
  1. Zhuang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tieyun Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Zhuang Chen and Tieyun Qian. The first draft of the manuscript was written by Zhuang Chen and revised by Tieyun Qian. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Tieyun Qian.

Ethics declarations

Financial interests

The authors declare they have no financial interests.

Non-financial interests

The authors declare they have no non-financial interests.

Additional information

Availability of data and material

The data and material used in this paper have been uploaded at https://github.com/NLPWM-WHU/D3A.

Code availability

The demo code of the proposed method in this paper has been uploaded at https://github.com/NLPWM-WHU/D3A.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Z., Qian, T. Description and demonstration guided data augmentation for sequence tagging. World Wide Web 25, 175–194 (2022). https://doi.org/10.1007/s11280-021-00978-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11280-021-00978-0

Keywords

Search

Navigation