STUDENT (kompyuter dasturi)

STUDENT bu algebrik masalalardagi muammolarini hal qilish uchun ishlab chiqilgan dastlabki sun'iy intellekt dasturi. Bu dastur Lispda Daniel Bobrow tomonidan 1964-yilda doktorlik dissertatsiyasi sifatida yozilgan (Bobrow 1964). Ushbu dastur oʻrta maktab algebra kitoblarida uchraydigan masalalarni oʻqish va ularga yechim topish uchun moʻljallangan^[1]. Dastur koʻpincha tabiiy tilni qayta ishlashda (NLP) sunʼiy intellektning dastlabki yutugʻi sifatida tilga olinadi.

Texnik tavsifi

1960-yillarda kompyuterlar asosan faqat universitetlarda tadqiqot kontekstida mavjud edi. MITdagi MAC loyihasi doirasida STUDENT dasturi matematik savollarga javob beruvchi dasturiy taʼminotning dastlabki namunasi boʻlib, ushbu tizim tabiiy tilni qayta ishlash va symbolic programming (ramziy dasturlash)ni oʻz ichiga oladi^[2]. Matematik masalalarni yechishga qaratilgan bu kabi boshqa tizimlarni ishlab chiqish 1960-yillarda qattiq disk va dasturiy taʼminotda ham amalga oshirildi: masalan, Philips, Baseball va Synthex tizimlari^[3].

STUDENT tizimi matematik masalalarni yechish uchun quyidagicha harakatlanadi: dastlab masala yozma ravishda, yaʼni soʻzlar bilan tizimga kiritiladi, dastur masalani yechgandan soʻng javobni raqamlar bilan ifodalaydi. Bu shaklni oʻzgartirish evristikadan iborat qatlamli quvur liniyasida amalga oshiriladi. Dastlab, ingliz tilidagi jumlalar yadroli jumlalarga aylantiriladi, ularning har biri bitta maʼlumotni oʻz ichiga oladi. Keyinchalik, yadro jumlalar matematik ifodalarga aylantiriladi^[4]. Transformatsiyani qoʻllab-quvvatlaydigan bilimlar bazasi 52 ta faktni oʻz ichiga oladi^{[manba kerak]}^[5]

STUDENT dasturi mantiqiy xulosaga ega qoidaga asoslangan tizimdan foydalanadi^[6]. Qoidalar dasturchi tomonidan oldindan dasturlashtirilgan va tabiiy tilni tahlil qilish imkoniyatiga ega.

Machine learning (Mashinali oʻrganish) kabi tabiiy tillarni qayta ishlashning bir muncha kuchli variantlari keyinchalik qoʻllanila boshlandi, vaqtlar oʻtgani sari mavjud qurilmalar takomillashib bordi va bu odddiy qoidalarga asoslangan tizimlarga nisbatan ancha muvaffaqiyatli boʻldi^[7].

Misol

Agar Tom oladigan mijozlar soni u olib boradigan reklamalar sonining 20% kvadratidan ikki baravar boʻlsa va reklamalar soni 45 ta boʻlsa, Tom qancha mijozlar oladi?

(Norvigdan olingan^[1])

Manbalar

↑ ^1,0 ^1,1 Norvig, Peter. Paradigms of artificial intelligence programming:case studies in Common Lisp. San Francisco, California: Morgan Kaufmann, 1992 — 109–149 bet. ISBN 1-55860-191-0.
↑ Bobrow, Daniel G (1964). Natural language input for a computer problem solving system (PhD). Massachusetts Institute of Technology.
↑ Raphael, Bertram (1964). SIR: A computer program for semantic information retrieval (PhD). Massachusetts Institute of Technology.
↑ |Shuming Shi and Yuehui Wang and Chin-Yew Lin and Xiaojiang Liu and Yong Rui (2015). "Automatically Solving Number Word Problems by Semantic Parsing and Reasoning". Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. doi:10.18653/v1/d15-1135.
↑ Kenneth D. Forbus (2010). "AI and Cognitive Science: The Past and Next 30 Years". Topics in Cognitive Science (Wiley) 2 (3): 345–356. doi:10.1111/j.1756-8765.2010.01083.x. PMID 25163864.
↑ Lin, Yi-Chung and Liang, Chao-Chun and Hsu, Kuang-Yi and Huang, Chien-Tsung and Miao, Shen-Yun and Ma, Wei-Yun and Ku, Lun-Wei and Liau, Churn-Jung and Su, Keh-Yih (2015). "Designing a tag-based statistical math word problem solver with reasoning and explanation". International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015-Special Issue on Selected Papers from ROCLING XXVII.
↑ Dongxiang Zhang and Lei Wang and Luming Zhang and Bing Tian Dai and Heng Tao Shen (2019). "The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers". IEEE Transactions on Pattern Analysis and Machine Intelligence (Institute of Electrical and Electronics Engineers (IEEE)) 42 (9): 2287–2305. doi:10.1109/tpami.2019.2914054. PMID 31056490.

[norvig-1] 1,0 ^1,1 Norvig, Peter. Paradigms of artificial intelligence programming:case studies in Common Lisp. San Francisco, California: Morgan Kaufmann, 1992 — 109–149 bet. ISBN 1-55860-191-0.

[2] Bobrow, Daniel G (1964). Natural language input for a computer problem solving system (PhD). Massachusetts Institute of Technology.

[3] Raphael, Bertram (1964). SIR: A computer program for semantic information retrieval (PhD). Massachusetts Institute of Technology.

[4] |Shuming Shi and Yuehui Wang and Chin-Yew Lin and Xiaojiang Liu and Yong Rui (2015). "Automatically Solving Number Word Problems by Semantic Parsing and Reasoning". Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. doi:10.18653/v1/d15-1135.

[5] Kenneth D. Forbus (2010). "AI and Cognitive Science: The Past and Next 30 Years". Topics in Cognitive Science (Wiley) 2 (3): 345–356. doi:10.1111/j.1756-8765.2010.01083.x. PMID 25163864.

[6] Lin, Yi-Chung and Liang, Chao-Chun and Hsu, Kuang-Yi and Huang, Chien-Tsung and Miao, Shen-Yun and Ma, Wei-Yun and Ku, Lun-Wei and Liau, Churn-Jung and Su, Keh-Yih (2015). "Designing a tag-based statistical math word problem solver with reasoning and explanation". International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015-Special Issue on Selected Papers from ROCLING XXVII.

[7] Dongxiang Zhang and Lei Wang and Luming Zhang and Bing Tian Dai and Heng Tao Shen (2019). "The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers". IEEE Transactions on Pattern Analysis and Machine Intelligence (Institute of Electrical and Electronics Engineers (IEEE)) 42 (9): 2287–2305. doi:10.1109/tpami.2019.2914054. PMID 31056490.

[1]

[2]

[3]

[4]

[5]

[6]

[7]