Automated question answering via natural language sentence similarity: Achievements for Brazilian e-commerce platforms
Resumo
Chatbots have become indispensable for quickly answering e-commerce customer queries, which is crucial for selling products online. However, in Brazilian e-commerce, finding scalable chatbot solutions can be challenging. This article proposes an automatic question-answering system by replying to incoming questions with Frequently Asked Questions from stores. Our solution builds a store-specific database populated with question-answer pairs by generating the embedding of questions. We define a retrieval process by ranking candidate questions with a neural network to reuse the questions' known answers. Our solution was deployed and evaluated with data in the Portuguese and Spanish languages for several stores in South America's biggest e-commerce platforms. The development approach achieved 97.75% of satisfaction with the given answers.
Palavras-chave:
NLP, semantic textual similarity, semantic retrieval, e-commerce
Referências
Cer, D., Yang, Y., yi Kong, S., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., Sung, Y.-H., Strope, B., and Kurzweil, R. (2018). Universal sentence encoder. https://doi.org/10.48550/arXiv.1803.11175
Chen, S., Li, C., Ji, F., Zhou, W., and Chen, H. (2019). Review-driven answer generation for product-related questions in e-commerce. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM ’19, page 411–419, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3289600.3290971
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
Finardi, P., Viegas, J. D., Ferreira, G. T., Mansano, A. F., and Caridá, V. F. (2021). Bertaú: Itaú bert for digital customer service. ArXiv, abs/2101.12015 https://doi.org/10.48550/arXiv.2101.12015
Fonseca, E. R., Borges dos Santos, L., Criscuolo, M., and Aluísio, S. M. (2016). Visão Geral da Avaliação de Similaridade Semântica e Inferência Textual. Linguamática, 8(2):3–13.
Gormley, C. and Tong, Z. (2015). Elasticsearch: The Definitive Guide. O’Reilly Media, Inc., 1st edition.
Gupta, M., Kulkarni, N., Chanda, R., Rayasam, A., and Lipton, Z. C. (2019). Amazonqa: A review-based question answering task. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 4996–5002. International Joint Conferences on Artificial Intelligence Organization https://doi.org/10.24963/ijcai.2019/694
Gupta, S. and Carvalho, V. R. (2019). Faq retrieval using attentive matching. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR’19, page 929–932, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3331184.3331294
Kulkarni, A., Mehta, K., Garg, S., Bansal, V., Rasiwasia, N., and Sengamedu, S. (2019). Productqna: Answering user questions on e-commerce product pages. In Companion Proceedings of The 2019 World Wide Web Conference, WWW ’19, page 354–360, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3308560.3316597
Mass, Y., Carmeli, B., Roitman, H., and Konopnicki, D. (2020). Unsupervised FAQ retrieval with question generation and BERT. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 807–812, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.74
Sakata, W., Shibata, T., Tanaka, R., and Kurohashi, S. (2019). Faq retrieval using query-question similarity and bert-based query-answer relevance. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR’19, page 1113–1116, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3331184.3331326
Shinzato, K., Shibata, T., Kawahara, D., Hashimoto, C., and Kurohashi, S. (2008). TSUBAKI: An open search engine infrastructure for developing new information access methodology. In Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. u., and Polosukhin, I. (2017). Attention is all you need. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. https://doi.org/10.48550/arXiv.1706.03762
Yang, Y., Cer, D., Ahmad, A., Guo, M., Law, J., Constant, N., Hernandez Abrego, G., Yuan, S., Tar, C., Sung, Y.-h., Strope, B., and Kurzweil, R. (2020). Multilingual universal sentence encoder for semantic retrieval. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 87–94, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-demos.12
Chen, S., Li, C., Ji, F., Zhou, W., and Chen, H. (2019). Review-driven answer generation for product-related questions in e-commerce. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM ’19, page 411–419, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3289600.3290971
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
Finardi, P., Viegas, J. D., Ferreira, G. T., Mansano, A. F., and Caridá, V. F. (2021). Bertaú: Itaú bert for digital customer service. ArXiv, abs/2101.12015 https://doi.org/10.48550/arXiv.2101.12015
Fonseca, E. R., Borges dos Santos, L., Criscuolo, M., and Aluísio, S. M. (2016). Visão Geral da Avaliação de Similaridade Semântica e Inferência Textual. Linguamática, 8(2):3–13.
Gormley, C. and Tong, Z. (2015). Elasticsearch: The Definitive Guide. O’Reilly Media, Inc., 1st edition.
Gupta, M., Kulkarni, N., Chanda, R., Rayasam, A., and Lipton, Z. C. (2019). Amazonqa: A review-based question answering task. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 4996–5002. International Joint Conferences on Artificial Intelligence Organization https://doi.org/10.24963/ijcai.2019/694
Gupta, S. and Carvalho, V. R. (2019). Faq retrieval using attentive matching. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR’19, page 929–932, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3331184.3331294
Kulkarni, A., Mehta, K., Garg, S., Bansal, V., Rasiwasia, N., and Sengamedu, S. (2019). Productqna: Answering user questions on e-commerce product pages. In Companion Proceedings of The 2019 World Wide Web Conference, WWW ’19, page 354–360, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3308560.3316597
Mass, Y., Carmeli, B., Roitman, H., and Konopnicki, D. (2020). Unsupervised FAQ retrieval with question generation and BERT. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 807–812, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.74
Sakata, W., Shibata, T., Tanaka, R., and Kurohashi, S. (2019). Faq retrieval using query-question similarity and bert-based query-answer relevance. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR’19, page 1113–1116, New York, NY, USA. Association for Computing Machinery. https://doi.org/10.1145/3331184.3331326
Shinzato, K., Shibata, T., Kawahara, D., Hashimoto, C., and Kurohashi, S. (2008). TSUBAKI: An open search engine infrastructure for developing new information access methodology. In Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. u., and Polosukhin, I. (2017). Attention is all you need. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. https://doi.org/10.48550/arXiv.1706.03762
Yang, Y., Cer, D., Ahmad, A., Guo, M., Law, J., Constant, N., Hernandez Abrego, G., Yuan, S., Tar, C., Sung, Y.-h., Strope, B., and Kurzweil, R. (2020). Multilingual universal sentence encoder for semantic retrieval. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 87–94, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-demos.12
Publicado
25/09/2023
Como Citar
CHICO, Víctor Jesús Sotelo; ZUCCHI, Luiz; FERRAGUT, Daniel; CAUS, Rodrigo; DE FREITAS, Victor Hochgreb; DOS REIS, Julio Cesar.
Automated question answering via natural language sentence similarity: Achievements for Brazilian e-commerce platforms. In: SIMPÓSIO BRASILEIRO DE TECNOLOGIA DA INFORMAÇÃO E DA LINGUAGEM HUMANA (STIL), 14. , 2023, Belo Horizonte/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 74-83.
DOI: https://doi.org/10.5753/stil.2023.233918.
