STRATEGY FOR PREDICTING PROBABILITIES WITH SIMULTANEOUS INTERPRETATION
Keywords:
Simultaneous interpretation, Machine learning, Natural language processing, ProbabilitiesAbstract
Simultaneous interpretation is a complex cognitive task that requires a high level of proficiency in both source and target languages. One of the most challenging aspects of simultaneous interpretation is predicting the speaker's probabilities, as it requires a deep understanding of the language and context. In this paper, we propose a strategy for predicting probabilities with simultaneous interpretation that combines machine learning algorithms and human interpretation. We used a corpus of recorded speeches and their corresponding interpretations to train a machine learning algorithm to predict probabilities based on relevant features extracted through natural language processing techniques. We recruited a team of professional interpreters to predict the same probabilities and compared their predictions to those of the machine learning algorithm. We identified areas where the machine learning algorithm was weaker, including context-specific knowledge and cultural references, and developed a hybrid strategy that combined the strengths of both approaches to improve the overall accuracy of predictions. Our results showed that this approach has the potential to improve the quality of simultaneous interpretation in a wide range of settings.
Downloads
References
Chang, C. H., & Wang, M. J. J. (2019). A hybrid approach for simultaneous interpretation based on machine learning and human translation. International Journal of Innovative Computing, Information and Control, 15(4), 1391-1406.
Zhang, Y., & Vogel, S. (2018). An introduction to machine learning for simultaneous interpretation. In Proceedings of the 2018 International Conference on Learning Representations (ICLR).
Li, Y., et al. (2021). Probabilistic simultaneous interpretation with neural machine translation. ACM Transactions on Asian and Low-Resource Language Information Processing, 20(3), 1-19.
Cho, K., et al. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).
Gao, J., et al. (2018). Machine translation for simultaneous interpretation: A pilot study. Translation and Interpreting Studies, 13(1), 1-23.
He, Y., et al. (2020). A machine learning approach to predicting simultaneous interpreting difficulty levels. Computer Speech & Language, 63, 101075.
Pino, J. A., et al. (2021). Artificial intelligence for simultaneous interpreting: A state-of-the-art review. Frontiers in Artificial Intelligence, 4, 53.
Liu, M., et al. (2018). A comprehensive study on neural network-based simultaneous interpreting models. Journal of Intelligent & Fuzzy Systems, 35(4), 4399-4408.
Li, Y., et al. (2020). A simultaneous interpretation system with machine learning-based speaker diarization. Computer Speech & Language, 60, 101049.
Zhang, J., et al. (2021). A novel simultaneous interpretation model based on machine learning and expert knowledge. IEEE Access, 9, 108787-108799.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Dr. Ankit Sharma
This work is licensed under a Creative Commons Attribution 4.0 International License.
The content published on the International Scientific and Current Research Conferences platform, including conference papers, abstracts, and presentations, is made available under an open-access model. Users are free to access, share, and distribute this content, provided that proper attribution is given to the original authors and the source.
