Augmenting Customer Support with an NLP-based Receptionist
Resumo
In this paper, we show how a Portuguese BERT model can be combined with structured data in order to deploy a chatbot based on a finite state machine to create a conversational AI system that helps a real-estate company to predict its client's contact motivation. The model achieves human level results in a dataset that containts 235 unbalanced labels. Then, we also show its benefits considering the business impact comparing it against classical NLP methods.
Referências
Azevedo, R. F. d., Rodrigues Pereira de Araujo, R., Guimarães Araújo, R., Moreira Bittencourt, R., Ferreira Alves da Silva, R., de Melo Vaz Nogueira, G., Marques Franca, T., Otharan Nunes, J., Ralff da Silva, K., and Regiane Cunha de Oliveira, E. (2020). In Quaresma, Screening of email box in portuguese with svm at banco do brasil. P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 153–163, Cham. Springer International Publishing.
Biewald, L. (2020). Experiment tracking with weights and biases. Software available from wandb.com.
Bonifacio, L. H., Vilela, P. A., Lobato, G. R., and Fernandes, E. R. (2020). A study on the impact of intradomain finetuning of deep language models for legal named entity recognition in portuguese. In Cerri, R. and Prati, R. C., editors, Intelligent Systems, pages 648–662, Cham. Springer International Publishing.
Carvalho, C. S., Pinheiro, V. C., and Freire, L. (2020). A deep learning model of common sense knowledge for augmenting natural language processing tasks in portuguese language. In Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 303–312, Cham. Springer International Publishing.
Dai, Y., Yu, H., Jiang, Y., Tang, C., Li, Y., and Sun, J. (2020). A survey on dialog management: Recent advances and challenges.
Dal Pont, T. R., Sabo, I. C., Hübner, J. F., and Rover, A. J. (2020). Impact of text specificity and size on word embeddings performance: An empirical evaluation in brazilian legal domain. In Cerri, R. and Prati, R. C., editors, Intelligent Systems, pages 521–535, Cham. Springer International Publishing.
DeLucia, A. and Moore, E. (2020). Analyzing hpc support tickets: Experience and recommendations. ArXiv, abs/2010.04321.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding.
Finardi, P., Viegas, J. D., Ferreira, G. T., Mansano, A. F., and Caridá, V. F. (2021). Bertaú: Itaú bert for digital customer service.
Fotso, S., Spanoudes, P., Ponedel, B. C., Reynoso, B., and Ko, J. (2018). Attention fusion networks: Combining behavior and e-mail content to improve customer support. ArXiv, abs/1811.03169.
Hermann, J. and Balso, M. D. (2017). Meet michelangelo: Uber’s machine learning platform.
Jurafsky, D. and Martin, J. H. (2021). Speech and Language Processing (3rd Edition). Prentice-Hall, Inc., USA.
Liu, C., Jiang, J., Xiong, C., Yang, Y., and Ye, J. (2020). Towards building an intelligent chatbot for customer service: Learning to respond at the appropriate time. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 20, page 3377–3385, New York, NY, USA. Association for Computing Machinery.
Marques, A. (2020). Butterfree: A spark-based framework for feature store building.
Melo, G. and Coheur, L. (2020). Towards a conversational agent with “character”. In Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 420–424, Cham. Springer International Publishing.
Molino, P., Zheng, H., and Wang, Y.-C. (2018). COTA: Improving the speed and accuracy of customer support through ranking and deep networks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 18, page 586–595, New York, NY, USA. Association for Computing Machinery.
Santos, J., Alves, A., and Gonçalo Oliveira, H. (2020). Leveraging on semantic textual similarity for developing a portuguese dialogue system. In Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 131–142, Cham. Springer International Publishing.
Souza, F., Nogueira, R., and Lotufo, R. (2020). BERTimbau: pretrained BERT models for Brazilian Portuguese. In 9th Brazilian Conference on Intelligent Systems, BRACIS, Rio Grande do Sul, Brazil, October 20-23.
Wan, M. and Chen, X. (2018). Beyond ”how may i help you?”: Assisting customer service agents with proactive responses.
Zhang, Z., Takanobu, R., Zhu, Q., Huang, M., and Zhu, X. (2020). Recent advances and challenges in task-oriented dialog system.
Zhu, C., Byrd, R., Nocedal, J., and Morales, J. L. (2011). L-BFGS-B — software for large-scale bound-constrained optimization.
Biewald, L. (2020). Experiment tracking with weights and biases. Software available from wandb.com.
Bonifacio, L. H., Vilela, P. A., Lobato, G. R., and Fernandes, E. R. (2020). A study on the impact of intradomain finetuning of deep language models for legal named entity recognition in portuguese. In Cerri, R. and Prati, R. C., editors, Intelligent Systems, pages 648–662, Cham. Springer International Publishing.
Carvalho, C. S., Pinheiro, V. C., and Freire, L. (2020). A deep learning model of common sense knowledge for augmenting natural language processing tasks in portuguese language. In Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 303–312, Cham. Springer International Publishing.
Dai, Y., Yu, H., Jiang, Y., Tang, C., Li, Y., and Sun, J. (2020). A survey on dialog management: Recent advances and challenges.
Dal Pont, T. R., Sabo, I. C., Hübner, J. F., and Rover, A. J. (2020). Impact of text specificity and size on word embeddings performance: An empirical evaluation in brazilian legal domain. In Cerri, R. and Prati, R. C., editors, Intelligent Systems, pages 521–535, Cham. Springer International Publishing.
DeLucia, A. and Moore, E. (2020). Analyzing hpc support tickets: Experience and recommendations. ArXiv, abs/2010.04321.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding.
Finardi, P., Viegas, J. D., Ferreira, G. T., Mansano, A. F., and Caridá, V. F. (2021). Bertaú: Itaú bert for digital customer service.
Fotso, S., Spanoudes, P., Ponedel, B. C., Reynoso, B., and Ko, J. (2018). Attention fusion networks: Combining behavior and e-mail content to improve customer support. ArXiv, abs/1811.03169.
Hermann, J. and Balso, M. D. (2017). Meet michelangelo: Uber’s machine learning platform.
Jurafsky, D. and Martin, J. H. (2021). Speech and Language Processing (3rd Edition). Prentice-Hall, Inc., USA.
Liu, C., Jiang, J., Xiong, C., Yang, Y., and Ye, J. (2020). Towards building an intelligent chatbot for customer service: Learning to respond at the appropriate time. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 20, page 3377–3385, New York, NY, USA. Association for Computing Machinery.
Marques, A. (2020). Butterfree: A spark-based framework for feature store building.
Melo, G. and Coheur, L. (2020). Towards a conversational agent with “character”. In Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 420–424, Cham. Springer International Publishing.
Molino, P., Zheng, H., and Wang, Y.-C. (2018). COTA: Improving the speed and accuracy of customer support through ranking and deep networks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 18, page 586–595, New York, NY, USA. Association for Computing Machinery.
Santos, J., Alves, A., and Gonçalo Oliveira, H. (2020). Leveraging on semantic textual similarity for developing a portuguese dialogue system. In Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., and Gonçalves, T., editors, Computational Processing of the Portuguese Language, pages 131–142, Cham. Springer International Publishing.
Souza, F., Nogueira, R., and Lotufo, R. (2020). BERTimbau: pretrained BERT models for Brazilian Portuguese. In 9th Brazilian Conference on Intelligent Systems, BRACIS, Rio Grande do Sul, Brazil, October 20-23.
Wan, M. and Chen, X. (2018). Beyond ”how may i help you?”: Assisting customer service agents with proactive responses.
Zhang, Z., Takanobu, R., Zhu, Q., Huang, M., and Zhu, X. (2020). Recent advances and challenges in task-oriented dialog system.
Zhu, C., Byrd, R., Nocedal, J., and Morales, J. L. (2011). L-BFGS-B — software for large-scale bound-constrained optimization.
Publicado
29/11/2021
Como Citar
BARBOSA, André; GODOY, Alan.
Augmenting Customer Support with an NLP-based Receptionist. In: SIMPÓSIO BRASILEIRO DE TECNOLOGIA DA INFORMAÇÃO E DA LINGUAGEM HUMANA (STIL), 13. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 133-142.
DOI: https://doi.org/10.5753/stil.2021.17792.
