A frequent pattern in customer care conversations is the agents responding with appropriate webpage URLs that address users' needs. We study the task of predicting the documents that customer care agents can use to facilitate users' needs. We also introduce a new public dataset which supports the aforementioned problem. Using this dataset and two others, we investigate state-of-the art deep learning (DL) and information retrieval (IR) models for the task. Additionally, we analyze the practicality of such systems in terms of inference time complexity. Our show that an hybrid IR+DL approach provides the best of both worlds.
@article{arxiv.2010.02305,
title = {Conversational Document Prediction to Assist Customer Care Agents},
author = {Jatin Ganhotra and Haggai Roitman and Doron Cohen and Nathaniel Mills and Chulaka Gunasekara and Yosi Mass and Sachindra Joshi and Luis Lastras and David Konopnicki},
journal= {arXiv preprint arXiv:2010.02305},
year = {2020}
}
Comments
EMNLP 2020. The released Twitter dataset is available at: https://github.com/IBM/twitter-customer-care-document-prediction