Abstract
In multi-label classification problems, the predominant approach is to transform the problem into a single-label classification problem that can result in the affirmative classification of multiple labels of a single sample. However, for data such as image, video, or text segment - a realistic scenario is that of a distribution across multiple labels for any particular sample. This work adopts a label distribution approach to determine the segments of text that need emphasis. Additionally, it focuses on short text samples that make it challenging to understand the context and the author’s intent. A context-aware approach is proposed by employing a composite embedding, thereby obtaining contextual information while also focusing on fine-grained details about the text samples. The proposed model outperforms the selected baseline by a significant amount, rendering the amalgamation of the context-aware embeddings and the non-binary nature of the Label Distribution Learning fittest for estimating emphasis.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, M.L., Li, Y.K., Liu, X.Y., et al.: Binary relevance for multi-label learning: an overview. Front. Comput. Sci. 12, 191–202 (2018)
Geng, X.: Label distribution learning. IEEE Trans. Knowl. Data Eng. 28(7), 1734–1748 (2016)
Shen W., Zhao, K., Guo, Y., Yuille, A.L.: Label distribution learning forests. In: Advances in Neural Information Processing Systems, pp. 834–843 (2017)
Geng, X., Hou, P.: Pre-release prediction of crowd opinion on movies by label distribution learning. In: IJCAI, pp. 3511–3517 (2015)
Gao, B., Xing, C., Xie, C., Wu, J., Geng, X.: Deep label distribution learning with label ambiguity. IEEE Trans. Image Process. 26(6), 2825–2838 (2017)
Chen, K., Kämäräinen, J.-K.: Learning with ambiguous label distribution for apparent age estimation. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10113, pp. 330–343. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54187-7_22
Ling, M., Geng, X.: Soft video parsing by label distribution learning. Front. Comput. Sci. 13(2), 302–317 (2019)
Xue, D., et al.: Personality recognition on social media with label distribution learning. IEEE Access 5, 13478–13488 (2017)
Ardehaly, E.M., Culotta, A.: Mining the demographics of political sentiment from Twitter using learning from label proportions. In: 2017 IEEE International Conference on Data Mining (ICDM), pp. 733–738. IEEE (2017)
Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C.: A survey on deep transfer learning. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 270–279. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01424-7_27
Ruder, S., Peters, M.E., Swayamdipta, S., Wolf, T.: Transfer learning in natural language processing. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials, pp. 15–18 (2019)
Okazaki, N.: CRFsuite: a Fast Implementation of Conditional Random Fields (CRFs) (2007). http://www.chokkan.org/software/crfsuite/
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)
Zhang, L., et al.: Emphasis detection for voice dialogue applications using multi-channel convolutional bidirectional long short-term memory network. In: 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 210–214. IEEE (2018)
Heba, A., Pellegrini, T., Jorquera, T., André-Obrecht, R., Lorré, J.-P.: Lexical emphasis detection in spoken French using F-Banks and neural networks. In: Camelin, N., Estève, Y., Martín-Vide, C. (eds.) SLSP 2017. LNCS (LNAI), vol. 10583, pp. 241–249. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68456-7_20
Do, Q.T., Sakti, S., Nakamura, S.: Toward expressive speech translation: a unified sequence-to-sequence LSTMs approach for translating words and emphasis. In: INTERSPEECH, pp. 2640–2644 (2017)
Mass, Y., et al.: Word emphasis prediction for expressive text to speech. In: INTERSPEECH, pp. 2868–2872 (2018)
Ning, Y., et al.: Learning cross-lingual knowledge with multilingual BLSTM for emphasis detection with limited training data. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5615–5619. IEEE (2017)
Shirani, A., et al.: Learning emphasis selection for written text in visual media from crowd-sourced label distributions. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1167–1172 (2019)
Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of NAACL (2018)
Cer, D., et al.: Universal Sentence Encoder. arXiv preprint arXiv:1803.11175 (2018)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Meghana, Das, B. (2021). Detection of Emphasis Words in Short Texts – A Context Aware Label Distribution Learning Approach. In: Luhach, A.K., Jat, D.S., Bin Ghazali, K.H., Gao, XZ., Lingras, P. (eds) Advanced Informatics for Computing Research. ICAICR 2020. Communications in Computer and Information Science, vol 1393. Springer, Singapore. https://doi.org/10.1007/978-981-16-3660-8_32
Download citation
DOI: https://doi.org/10.1007/978-981-16-3660-8_32
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3659-2
Online ISBN: 978-981-16-3660-8
eBook Packages: Computer ScienceComputer Science (R0)