{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-automated-customer-support","title":"Towards Automated Customer Support","arxiv_id":"1809.00303","date":"2018-09-02","proceeding":null,"authors":["Momchil Hardalov","Ivan Koychev","Preslav Nakov"],"abstract":"Recent years have seen growing interest in conversational agents, such as\nchatbots, which are a very good fit for automated customer support because the\ndomain in which they need to operate is narrow. This interest was in part\ninspired by recent advances in neural machine translation, esp. the rise of\nsequence-to-sequence (seq2seq) and attention-based models such as the\nTransformer, which have been applied to various other tasks and have opened new\nresearch directions in question answering, chatbots, and conversational\nsystems. Still, in many cases, it might be feasible and even preferable to use\nsimple information retrieval techniques. Thus, here we compare three different\nmodels:(i) a retrieval model, (ii) a sequence-to-sequence model with attention,\nand (iii) Transformer. Our experiments with the Twitter Customer Support\nDataset, which contains over two million posts from customer support services\nof twenty major brands, show that the seq2seq model outperforms the other two\nin terms of semantics and word overlap.","url_abs":"http://arxiv.org/abs/1809.00303v1","url_pdf":"http://arxiv.org/pdf/1809.00303v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-automated-customer-support","repo_url":"https://github.com/mhardalov/customer-support-chatbot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00303","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}