Collaborative Response Content Recommendation for Customer Service Agents.

The rapid development of artificial intelligence (AI) has motivated extensive research on dialog system. Using dialog system to automatize customer service is a common practice in many business fields. In this paper, we investigate a novel task to recommend response for customer service agents of each shop. A major challenge is the problem of data insufficiency for each shop. Meanwhile, we want to keep the personalized information for shops with very different commodities. To deal with such problems, we propose a LSTM (Long Short-Term Memory) Neuron Tensor Network architecture to encode the common features of all shops' data and model the personalized features of each shop. Extensive experiments demonstrate that our method outperforms four baseline methods evaluated by recall metric.