Memristive computing for Tibetan spellchecker

doi:10.23919/JSEE.2026.000162

Abstract

Abstract:

This paper highlights a Tibetan syllable spelling check method based on memristive computing. Firstly, a rule-based syllable component recognization method is implemented to classify components of syllables into seven types, that is prefix letter, root letter, superscript letter, subscript letter, vowel letter, suffix letter, and farther suffix letter. In order to detect syllable formation errors in Tibetan text, a Tibetan spelling check method is presented based on component recognization by adding mapping principles. Then, a memristor crossbar array with an external control circuit is introduced to make memristive computing for Tibetan spelling check, by analyzing the total current value in a memristor crossbar array to implement rule-based matching and mapping processes. Finally, a stable memristive computing algorithm-based Tibetan spelling check is established. A simulation experiment on the memristor crossbar array demonstrates the stability of our memristive computing-based Tibetan spelling check method. Comparative experiments on 1274 of the most common Tibetan syllables show that the accuracy of our component recognization method is 97.19%, the F1-score of spelling check is 98.58%, beating other rule-based and statistics-based methods in precision and F1-score, demonstrating the accuracy of our method.

Key words: memristor, memristive computing, Tibetan syllable component recognization, Tibetan spelling check

Yongbin Yu, Yutong Liu, Jiarun Shen, Ma-bao Ban, Xiangxiang Wang, Drolma Tsering, Tsering Thupten, Cheng Huang, Tashi Dorje, Dongrub Rinchen, Duojie Renzeng, Luosang Gadeng, Tashi Karma, Tashi Nyima. Memristive computing for Tibetan spellchecker[J]. Journal of Systems Engineering and Electronics, 2026, 37(5): 1449-1462.

Figures/Tables 22

Fig 1

Fig 2

Table 1

Table 2

Table 3

Table 4

Table 5

Table 6

Fig 3

Fig 5

Table 7

Fig 4

Table 8

Fig 6

Fig 7

Fig 8

Fig 9

Fig 10

Fig 11

Table 9

Table 10

Fig 12

References 48

1	Chua L O Memristor-the missing circuit element. IEEE Trans. onCircuit Theory, 1971, 18 (5): 507. doi: 10.1109/TCT.1971.1083337
2	Chua L O How we predicted the memristor. Nature Electronics, 2018, 1, 322. doi: 10.1038/s41928-018-0074-4
3	Pan F, Gao S, Chen C, et al Recent progress in resistive random access memories: materials, switching mechanisms, and performance. Materials Science & Engineering R-reports, 2014, 83, 1.
4	Wang M, Cai S H, Pan C, et al Robust memristors based on layered two-dimensional materials. Nature Electronics, 2018, 1, 130. doi: 10.1038/s41928-018-0021-4
5	Zhang S J, Tao Y, Qin S W, et al Memristors based on two-dimensional h-BN materials: synthesis, mechanism, optimization and application. npj 2D Materials and Applications, 2024, 8, 81. doi: 10.1038/s41699-024-00519-z
6	Kvatinsky S, Friedman E G, Kolodny A, et al Team: threshold adaptive memristor model. IEEE Trans. onCircuits and Systems I: Regular Papers, 2013, 60 (1): 211. doi: 10.1109/TCSI.2012.2215714
7	Kvatinsky S, Ramadan M, Friedman E G, et al Vteam: a general model for voltage-controlled memristors. IEEE Trans. onCircuits and Systems II: Express Briefs, 2015, 62 (8): 786.
8	Yu Y B, Li B, Tang Q A novel cubic flux-controlled memristor model and its filter study. Journal of University of Electronic Science and Technology of China, 2021, 50 (3): 339.
9	Pal S, Bose S, Islam A Design of memristor based low power and highly reliable ReRAM cell. Microsystem Technologies, 2022, 28, 793. doi: 10.1007/s00542-019-04582-1
10	Tossoun B, Liang D, Cheung S, et al High-speed and energy-efficient non-volatile silicon photonic memory based on heterogeneously integrated memresonator. Nature Communications, 2024, 15, 551. doi: 10.1038/s41467-024-44773-7
11	Elshekh H, Wang H, Zhu S, et al Nonvolatile resistive switching memory behavior of the TiOx-based memristor. Chemical Physics, 2024, 580, 112217. doi: 10.1016/j.chemphys.2024.112217
12	Ghodke S S, Kumar S, Yadav S, et al Combinational logic circuits based on a power- and area-efficient memristor with low variability. Journal of Computational Electronics, 2024, 23, 131. doi: 10.1007/s10825-023-02117-6
13	Liu G Z, Shen S H, Jin P P, et al Design of memristor-based combinational logic circuits. Circuits, Systems, and Signal Processing, 2021, 40, 5825. doi: 10.1007/s00034-021-01770-1
14	Luo L, Li B C, Wang L D, et al Reconfigurable stateful logic circuit with Cu/CuI/Pt memristors for in-memory computing. IEEE Trans. onVery Large Scale Integration (VLSI) Systems, 2024, 32 (5): 835. doi: 10.1109/TVLSI.2024.3370176
15	Lin F L, Cheng Y C, Li Z Q, et al Data encryption/decryption and medical image reconstruction based on a sustainable biomemristor designed logic gate circuit. Materials Today Bio, 2024, 29, 101257. doi: 10.1016/j.mtbio.2024.101257
16	Woo K S, Han J, Yi S, et al Tunable stochastic memristors for energy-efficient encryption and computing. Nature Communications, 2024, 15, 3245. doi: 10.1038/s41467-024-47488-x
17	Leng X X, Wang X P, Du B X, et al. Real-time dynamic medical image encryption based on extended multi-scroll memristive Hopfield neural network[J]. Nonlinear Dynamics, 2025.
18	Wang X Y, Bao X G, Li X J, et al Crossbar array based on tri-valued memristors: its design and application. Nonlinear Dynamics, 2024, 112, 20353. doi: 10.1007/s11071-024-10126-8
19	Shi T, Zhang H, Cui S Y, et al Stochastic neuro-fuzzy system implemented in memristor crossbar arrays. Science Advances, 2024, 10, 3135. doi: 10.1126/sciadv.adl3135
20	Aguirre F, Sebastian A, Le G M, et al Hardware implementation of memristor-based artificial neural networks. Nature Communications, 2024, 15, 1974. doi: 10.1038/s41467-024-45670-9
21	Yu Y B, Tang H W, Feng X, et al Design of multilayer cellular neural network based on memristor crossbar and its application to edge detection. Journal of Systems Engineering and Electronics, 2023, 34 (3): 641. doi: 10.23919/JSEE.2022.000127
22	Huang Y, Ando T, Sebastian A, et al Memristor-based hardware accelerators for artificial intelligence. Nature Reviews Electrical Engineering, 2024, 1, 286. doi: 10.1038/s44287-024-00037-6
23	Peng H H, Gan L, Guo X Memristor-based spiking neural networks: cooperative development of neural network architecture/algorithms and memristors. Chip, 2024, 3, 100093. doi: 10.1016/j.chip.2024.100093
24	Kumar S, Wang X, Strachan J P, et al Dynamical memristors for higher-complexity neuromorphic computing. Nature Reviews Materials, 2022, 7, 575. doi: 10.1038/s41578-022-00434-z
25	Yu Y B, Yang N J, Yang C Y, et al Memristor bridge-based low pass filter for image processing. Journal of Systems Engineering and Electronics, 2019, 30 (3): 448. doi: 10.21629/JSEE.2019.03.02
26	Du J M, Sun B, Yang C, et al Ferroelectric memristor and its neuromorphic computing applications. Materials Today Physics, 2025, 50, 101607. doi: 10.1016/j.mtphys.2024.101607
27	Shen J R, Yu Y B, Wang X X, et al. Memristive binary firefly algorithm for white lung images segmentation[C]. 2023 International Conference on Neuromorphic Computing, 2023: 331.
28	Yu Y B, Yang C Y, Deng Q X, et al Memristive network-based genetic algorithm and its application to image edge detection. Journal of Systems Engineering and Electronics, 2021, 32 (5): 1062. doi: 10.23919/jsee.2021.000091
29	Shi T, Gao L, Tian Y, et al Memristor-based feature learning for pattern classification. Nature Communications, 2025, 16, 913. doi: 10.1038/s41467-025-56286-y
30	Zhang L H, Zhu J J, Man L M. Eastward development of Tibetans in China: a gravity-based approach with an application to population[C]. 2021 4th International Conference on Geoinformatics and Data Analysis, 2021: 1.
31	Lv H, Pu C, Duo L, et al T-LLaMA: a Tibetan large language model based on LLaMA2. Complex Intelligence, 2025, 11, 72. doi: 10.1007/s40747-024-01641-7
32	Zhou Q, Xu X N, Zhao Y Tibetan speech synthesis based on pre-trained mixture alignment FastSpeech2. Applied Sciences, 2024, 14 (15): 6834. doi: 10.3390/app14156834
33	Gong Z R, Xu X N, Zhao Y Tibetan–Chinese speech-to-speech translation based on discrete units. Scientific Reports, 2025, 15, 2592. doi: 10.1038/s41598-025-85782-w
34	Wang W L, Kun L W. A fast input method for Tibetan based on word in Unicode[C]. IMECS 2008: International Multiconference of Engineers and Computer Scientists, 2008: 374.
35	Wang W L, Duola. Formation of standard Tibetan syllables and comparison as well as analysis of the statistical results[C]. 2008 IEEE Conference on Cybernetics and Intelligent Systems, 2008: 379.
36	Huang H M, Da F P. Discussion on collation of Tibetan syllable[C]. 2010 International Conference on Asian Language Processing, 2010: 35.
37	Zhu J, Li T R, Ge S D J, et al Tibetan syllable rule model and applications. Acta Scientiarum Naturalium Universitatis Pekinensis, 2013, 49, 68.
38	Bianba W D, Zhuoga, Chen Y L, et al Study on recognition algorithms for Tibetan construction elements. Journal of Chinese Information Processing, 2014, 28, 104.
39	Brown C J. Improved neural word segmentation for standard Tibetan[C]. 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia, 2024: 12.
40	San M C, Cai Z J, Cai R Z M, et al. Analysis on types of spelling errors in true Tibetan characters[C]. 2020 2nd International Conference on Computer Science Communication and Network Security, 2021: 336.
41	Zhu J, Li T R, Liu S J The algorithm of spelling check base on TSRM. Journal of Chinese Information Processing, 2014, 28, 92.
42	Zhu J, Li T R. An approach for Tibetan text automatic proofreading and its system design[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2014: 142.
43	Liu H D, Hong J L, Nuo M H, et al Statistics and analysis on spell errors of Tibetan syllables based on a large scale web corpus. Journal of Chinese Information Processing, 2017, 31, 61.
44	Ahmadi S. Hunspell for Sorani Kurdish spell checking and morphological analysis[EB/OL]. https://arxiv.org/abs/2109.06374.
45	Stuart M, Christopher B, Marek R, et al. An extended sequence tagging vocabulary for grammatical error correction[C]. Findings of the Association for Computational Linguistics: European Chapter of the Association for Computational Linguistics (EACL) 2023, 2023: 1608.
46	Hue D Z X, Cai Z J, Ban M B A TC-LSTM based method for Tibetan spelling check. Journal of Chinese Information Processing, 2020, 31, 50.
47	Hua G C R, Jia S C, Bao M B, et al. Error correction of Tibetan verbs based on deep learning[C]. 2021 2nd International Conference on Artificial Intelligence and Computer Engineering, 2021: 221.
48	Chua L O, Kang S M Memristive devices and systems. Proceedings of the IEEE, 1976, 64 (2): 209. doi: 10.1109/PROC.1976.10092

Component	Character
Root letter	ཀ, ཁ, ག, ང, ཅ, ཆ, ཇ, ཉ, ཏ, ཐ, ད, ན, པ, ཕ, བ, མ, ཙ, ཚ, ཛ, ཝ, ཞ, ཟ, འ, ཡ, ར, ལ, ཤ, ས, ཧ, ཨ
Prefix letter	ག, ད, བ, མ, འ
Superscript letter	ར, ལ, ས
Subscript letter	◌ྱ, ◌ྲ, ◌ླ, ◌ྭ
Vowel letter	◌ི, ◌ུ, ◌ེ, ◌ོ
Suffix letter	ག, ང, ད, ན, བ, མ, འ, ར, ལ, ས
Farther suffix letter	ད, ས

Prefix letter	Root letter
ག	ཅ, ཏ, ཙ, ཉ, ད, ན, ཞ, ཟ, ཡ, ཤ, ས
ད	ཀ, པ, ག, བ, ང, མ
བ	ཀ, ཅ, ཏ, ཙ, ག, ང, ཇ, ཉ, ད, ན, ཛ, ཞ, ཟ, ཪ, ཤ, ས
མ	ཁ, ཆ, ཐ, ཚ, ག, ཇ, ད, ཛ, ང, ཉ, ན
འ	ག, ཇ, ད, བ, ཛ, ཁ, ཆ, ཐ, ཕ, ཚ

Superscript letter	Root letter
ར	◌ྐ, ◌ྒ, ◌ྔ, ◌ྗ, ◌ྟ, ◌ྡ, ◌ྣ, ◌ྦ, ◌ྨ, ◌ྕ, ◌ྫ, ◌ྙ
ལ	◌ྐ, ◌ྒ, ◌ྔ, ◌ྕ, ◌ྗ, ◌ྟ, ◌ྡ, ◌ྤ, ◌ྦ, ◌ྷ
ས	◌ྐ, ◌ྒ, ◌ྔ, ◌ྙ, ◌ྟ, ◌ྡ, ◌ྣ, ◌ྤ, ◌ྦ, ◌ྨ, ◌ྩ

Subscript letter	Root letter
◌ྱ	ཀ, ཁ, ག, པ, ཕ, བ, མ
◌ྲ	ཀ, ཁ, ག, ཏ, ཐ, ད, པ, ཕ, བ, མ, ས, ཧ
◌ླ	ཀ, ག, བ, ཟ, ཪ, ས
◌ྭ	ཀ, ཁ, ག, ཉ, ད, ཙ, ཚ, ཞ, ཟ, ར, ལ, ཤ, ཧ

Farther suffix letter	Suffix letter
ད	ན, ར, ལ
ས	ག, ང, བ, མ