Investigação sobre a Leitura de Documentos de Modelos de Perguntas e Respostas no Domínio Esportivo
Resumo
Neste artigo são investigados modelos de leitor de documentos em sistemas de perguntas e respostas. Esses modelos analisam documentos pré-selecionados usando técnicas avançadas de processamento de linguagem natural para entender o contexto e a semântica do texto, produzindo respostas relevantes. São comparados os modelos BERT, DistilBERT, MiniLM, RoBERTa e ELECTRA, considerando a capacidade desses em responder perguntas referentes ao domínio esportivo. Os resultados obtidos demonstraram que o modelo RoBERTa proveu melhor desempenho para as métricas Exact Match e F-Score, e o modelo DistilBERT proveu melhor tempo de execução.
Palavras-chave:
Mineração e análise de dados, Aplicações/pipelines de ciência de dados, Experimentos e análises
Referências
Aurpa, T. T., Rifat, R. K., Ahmed, M. S., Anwar, M. M., and Ali, A. B. M. S. (2022). Reading comprehension based question answering system in Bangla language with transformer-based learning. Heliyon, 8(10):e11052.
Chebbi, I., Boulila, W., and Farah, I. R. (2015). Big data: Concepts, challenges and applications. In Computational Collective Intelligence. Lecture Notes in Computer Science, volume 9330, pages 638–647.
Chen, D., Fisch, A., Weston, J., and Bordes, A. (2017). Reading Wikipedia to answer open-domain questions. CoRR, abs/1704.00051.
Clark, K., Luong, M., Le, Q. V., and Manning, C. D. (2020). ELECTRA: pre-training text encoders as discriminators rather than generators. CoRR, abs/2003.10555.
Devlin, J., Chang, M., Lee, K., and Toutanova, K. (2018). BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805.
Hirschman, L. and Gaizauskas, R. (2001). Natural language question answering: the view from here. Natural Language Engineering, 7(4):275–300.
Jardim, P. C., Moraes, L. M. P., and Aguiar, C. D. (2023). QASports: A question answering dataset about sports. In Proceedings of the Brazilian Symposium on Databases: Dataset Showcase Workshop, pages 1–12.
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692.
Mishra, A. and Jain, S. K. (2016). A survey on question answering systems with classification. Journal of King Saud University - Computer and Information Sciences, 28(3):345–361.
Moraes, L. M. P., Jardim, P., and Aguiar, C. D. (2023). Design principles and a software reference architecture for big data question answering systems. In Proc. of the 25th International Conference on Enterprise Information Systems, pages 57–67.
Rajpurkar, P., Zhang, J., Lopyrev, K., and Liang, P. (2016). Squad: 100,000+ questions for machine comprehension of text. CoRR, abs/1606.05250.
Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR, abs/1910.01108.
Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., and Zhou, M. (2020). Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In Advances in Neural Information Processing Systems, volume 33, pages 5776–5788.
Chebbi, I., Boulila, W., and Farah, I. R. (2015). Big data: Concepts, challenges and applications. In Computational Collective Intelligence. Lecture Notes in Computer Science, volume 9330, pages 638–647.
Chen, D., Fisch, A., Weston, J., and Bordes, A. (2017). Reading Wikipedia to answer open-domain questions. CoRR, abs/1704.00051.
Clark, K., Luong, M., Le, Q. V., and Manning, C. D. (2020). ELECTRA: pre-training text encoders as discriminators rather than generators. CoRR, abs/2003.10555.
Devlin, J., Chang, M., Lee, K., and Toutanova, K. (2018). BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805.
Hirschman, L. and Gaizauskas, R. (2001). Natural language question answering: the view from here. Natural Language Engineering, 7(4):275–300.
Jardim, P. C., Moraes, L. M. P., and Aguiar, C. D. (2023). QASports: A question answering dataset about sports. In Proceedings of the Brazilian Symposium on Databases: Dataset Showcase Workshop, pages 1–12.
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692.
Mishra, A. and Jain, S. K. (2016). A survey on question answering systems with classification. Journal of King Saud University - Computer and Information Sciences, 28(3):345–361.
Moraes, L. M. P., Jardim, P., and Aguiar, C. D. (2023). Design principles and a software reference architecture for big data question answering systems. In Proc. of the 25th International Conference on Enterprise Information Systems, pages 57–67.
Rajpurkar, P., Zhang, J., Lopyrev, K., and Liang, P. (2016). Squad: 100,000+ questions for machine comprehension of text. CoRR, abs/1606.05250.
Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR, abs/1910.01108.
Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., and Zhou, M. (2020). Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In Advances in Neural Information Processing Systems, volume 33, pages 5776–5788.
Publicado
14/10/2024
Como Citar
CAMARGOS, Laura Fernandes; MORAES, Leonardo Mauro Pereira; AGUIAR, Cristina Dutra.
Investigação sobre a Leitura de Documentos de Modelos de Perguntas e Respostas no Domínio Esportivo. In: WORKSHOP DE TRABALHOS DE ALUNOS DA GRADUAÇÃO (WTAG) - SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 39. , 2024, Florianópolis/SC.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 8-14.
DOI: https://doi.org/10.5753/sbbd_estendido.2024.243679.
