IJLLC | Natural Language Understanding of Low-Resource Languages in Voice Assistants: Advancements, Challenges and Mitigation Strategies

Indexing and Abstracting

Natural Language Understanding of Low-Resource Languages in Voice Assistants: Advancements, Challenges and Mitigation Strategies

Ashlesha V Kadam

International Journal of Language, Literature and Culture (IJLLC), Vol-3,Issue-5, September - October 2023, Pages 20-23, 10.22161/ijllc.3.5.3

Download | Downloads : 7 | Total View : 417

Article Info: Received: 18 Aug 2023, Received in revised form: 21 Sep 2023, Accepted: 01 Oct 2023, Available online: 08 Oct 2023

Abstract:

This paper presents an exploration of low resource languages and the specific challenges that arise in natural language understanding of these by a voice assistant. While voice assistants have made significant strides when it comes to their understanding of mainstream languages, this paper focuses on extending this understanding to low resource languages in order to maintain diversity of linguistics and also delight the customer. In this paper, the specific nuances of natural language understanding when it comes to these low resource languages has been discussed. The paper also proposes techniques to overcome some of the challenges in voice assistants understanding low resource language models. The proposed methods and future direction presented in this doc are poised to drive advancements in voice technology and promote inclusivity by ensuring that voice assistants are accessible to speakers of underrepresented languages.

Keywords:

Low resource languages, NLU, voice assistant, voice technology

References:

Tawfiq Ammari, Jofish Kaye, Janice Y. Tsai, and Frank Bentley. 2019. Music, Search, and IoT: How People (Really) Use Voice Assistants. ACM Trans. Comput.-Hum. Interact. 26, 3, Article 17 (June 2019), 28 pages. https://doi.org/10.1145/3311956
Ashlesha Vishnu Kadam, Designing Thoughtful Experiences for Kids on Voice Assistants, International Journal of Artificial Intelligence & Machine Learning (IJAIML), 2(1), 2023, pp. 75-81. https://doi.org/10.17605/OSF.IO/HKTS8
Hoy MB. Alexa, Siri, Cortana, and more: an introduction to voice assistants. Med Ref Serv Quart. 2018;37(1):81–8
Alexandre Magueresse, Vincent Carles, Evan Heetderks, “Low-resource Languages: A Review of Past Work and Future Challenges”, arXiv:2006.07264
https://keyreply.com/blog/conversational-ai-low-resource-languages/
https://vtiya.medium.com/is-your-language-a-low-resouce-language-c17da390909f
https://blog.neurotech.africa/low-resource-languages-vs-conversational-artificial-intelligence/
Ashlesha Vishnu Kadam, “Designing Thoughtful Experiences for Kids on Voice Assistants”, International Journal of Artificial Intelligence & Machine Learning (IJAIML) Volume 2, Issue 01, Jan-Dec 2023, pp. 75-81. DOI: https://doi.org/10.17605/OSF.IO/HKTS8
https://www.miquido.com/blog/what-are-voice-assistants/
Brown, Cozby, et al., “Research Methods in Human Development”, Page 37, Psychological Abstracts, Vol. 79, #19842, p. 2397
https://homepage.cs.uri.edu/faculty/wolfe/book/Readings/Reading13.htm
Duong, L., Kanayama, H., Ma, T., & Bird, S. (2018). A comparative study of language representation methods for low-resource languages. arXiv preprint arXiv:1808.08437
Futrell, R., Gibson, E., & Fedorenko, E. (2022). Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality. Proceedings of the National Academy of Sciences, 119(23), e2122604119. doi: 10.1073/pnas.2122604119.
Svetko, Y., & Callison-Burch, C. (2017). Opportunities and challenges in working with low-resource languages. In Proceedings of the 2017 Joint Summer Workshop on Machine Learning and Human Language Technologies (pp. 1-9). Carnegie Mellon University.
Gardner-Chloros, P. (2009). Code-switching. Cambridge University Press
Bender, E. M., & Koller, A. (2020). Low-Resource Natural Language Processing. arXiv preprint arXiv:2002.11794
Haifeng Wang, Jiwei Li, Hua Wu, Eduard Hovy, Yu Sun, Pre-Trained Language Models and Their Applications,
Engineering, 2022
https://www.v7labs.com/blog/transfer-learning-guide
Thai, Jimerson, et al., “Synthetic Data Augmentation for Improving Low Resource ASR”, Rochester Institute of Technology, https://par.nsf.gov/servlets/purl/10161886
Ragni, A. & Knill, Kate & Rath, Shakti & Gales, M.J.F.. (2014). Data augmentation for low resource languages. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 810-814.
Bohan Li, Yutai Hou, Wanxiang Che, “Data augmentation approaches in natural language processing: A survey”,
AI Open, Volume 3, 2022, Pages 71-90, ISSN 2666-6510, https://doi.org/10.1016/j.aiopen.2022.03.001.
Catherine Gitau, VUkosi Marivate, “Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili”, https://arxiv.org/abs/2306.07414
Xinyi Wang, “Data Efficient Multilingual Natural Language Processing”, Carnegie Mellon University, https://www.lti.cs.cmu.edu/sites/default/files/wang%2C%20cindy%20-%20Thesis.pdf

Diwan, Vaideeswaran, et al., “Multilingual and code-switching ASR challenges for low resource Indian languages”, https://arxiv.org/abs/2104.00235

Yang, L., Wang, Q., Yu, Z., Kulkarni, A., Sanghai, S., Shu, B., Elsas, J., & Kanagal, B. (2021). MAVE: A Product Dataset for Multi-source Attribute Value Extraction. arXiv preprint arXiv:2112.08663.
Subendhu Rongali, “Low Resource Language Understanding in Voice Assistants”, https://scholarworks.umass.edu/dissertations_2/2717/
Mehrish, A., Majumder, N., Bhardwaj, R., Mihalcea, R., & Poria, S. (2023). A Review of Deep Learning Techniques for Speech Processing. Information Fusion, 101869. doi: 10.1016/j.inffus.2023.101869.
Gabriel Nicholas, Aliya Bhatia, “Lost in Translation – Large Language Models in non-English Content Analysis”, May 2023
Dwivedi, Kshetri, et al., Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy, International Journal of Information Management, Volume 71, 2023, 102642, ISSN 0268-4012, https://doi.org/10.1016/j.ijinfomgt.2023.102642