SISTEM ZA ODGOVORE NA PITANJA U DOMENU FITNESA ZASNOVAN NA MAŠINSKOM UČENJU
Ključne reči:
Odgovori na pitanja, Jezički modeli, NLP, QA, BERT
Apstrakt
U ovom radu predstavljen je sistem za odgovore na pitanja u oblasti fitnesa i nutricionizma, koji dovoljno dobro generalizuje i za opšti domen. Kao ulaz model prima pitanje u obliku niza karaktera, a potom traži najbolje kandidate dokumente u bazi znanja, koji imaju odgovor na pitanje koje je na ulazu u sistem postavljeno.
Reference
[1] Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.
[2] Lewis, P., Denoyer, L., Riedel, S. (2019). Unsupervised Question Answering by Cloze Translation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
[3] Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, Ming Zhou. (2020). MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers.
[4] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, & Veselin Stoyanov. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach
[5] Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih. (2020). Dense Passage Retrieval for Open-Domain Question Answering.
[6] Yang, Zhilin, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. "Xlnet: Generalized autoregressive pretraining for language understanding." arXiv preprint arXiv:1906.08237 (2019).
[7] Victor Sanh, Lysandre Debut, Julien Chaumond, & Thomas Wolf. (2020). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.
[8] Sina J. Semnani, & Manish Pandey. (2020). Revisiting the Open-Domain Question Answering Pipeline.
[2] Lewis, P., Denoyer, L., Riedel, S. (2019). Unsupervised Question Answering by Cloze Translation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
[3] Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, Ming Zhou. (2020). MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers.
[4] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, & Veselin Stoyanov. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach
[5] Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih. (2020). Dense Passage Retrieval for Open-Domain Question Answering.
[6] Yang, Zhilin, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. "Xlnet: Generalized autoregressive pretraining for language understanding." arXiv preprint arXiv:1906.08237 (2019).
[7] Victor Sanh, Lysandre Debut, Julien Chaumond, & Thomas Wolf. (2020). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.
[8] Sina J. Semnani, & Manish Pandey. (2020). Revisiting the Open-Domain Question Answering Pipeline.
Objavljeno
2022-01-26
Sekcija
Elektrotehničko i računarsko inženjerstvo
