首页|Researchers at Nottingham Trent University Target Robotics (Customer Service Cha tbot Enhancement With Attention-based Transfer Learning)
Researchers at Nottingham Trent University Target Robotics (Customer Service Cha tbot Enhancement With Attention-based Transfer Learning)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on Robotics are presented i n a new report. According to news reporting out of Nottingham, United Kingdom, b y NewsRx editors, research stated, “Customer service is an important and expensi ve aspect of business, often being the largest department in most companies. Wit h growing societal acceptance and increasing cost efficiency due to mass product ion, service robots are beginning to cross from the industrial domain to the soc ial domain.” Our news journalists obtained a quote from the research from Nottingham Trent Un iversity, “Currently, customer service robots tend to be digital and emulate soc ial interactions through on-screen text, but state-of-the-art research points to wards physical robots soon providing customer service in person. This article ex plores the feasibility of Transfer Learning different customer service domains t o improve chatbot models. In our proposed approach, transfer learning-based chat bot models are initially assigned to learn one domain from an initial random wei ght distribution. Each model is then tasked with learning another domain by tran sferring knowledge from the previous domains. To evaluate our approach, a range of 19 companies from domains such as e-Commerce, telecommunications, and technol ogy are selected through social interaction with X (formerly Twitter) customer s upport accounts. The results show that the majority of models are improved when transferring knowledge from at least one other domain, particularly those more d ata-scarce than others. General language transfer learning is observed, as well as higher-level transfer of similar domain knowledge. For each of the 19 domains , the Wilcoxon signed-rank test suggests that 16 have statistically significant distributions between transfer and non-transfer learning.”
NottinghamUnited KingdomEuropeEmer ging TechnologiesMachine LearningNano-robotRobotRoboticsNottingham Tre nt University