As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the dialog generation task mostly augment all cases in the training dataset without considering the intrinsic attributes between different cases. We argue that not all cases are beneficial for augmentation task, and the cases suitable for augmentation should obey the following two attributes: (1) low-quality (the dialog model cannot generate a high-quality response for the case), (2) representative (the case should represent the property of the whole dataset). Herein, we explore this idea by proposing a Selective Data Augmentation framework (SDA) for the response generation task. SDA employs a dual adversarial network to select the lowest quality and most representative data points for augmentation in one stage. Extensive experiments conducted on two publicly available datasets, i.e., DailyDialog and OpenSubtitles, show that our framework can improve the response generation performance with respect to various metrics

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and cons. Despite the natural idea of an ensemble model of the two, existing ensemble methods only focused on leveraging one approach to enhance another, we argue however that they can be further mutually enhanced with a proper training strategy. In this paper, we propose ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario. It consists of a language-model-like generator, a ranker generator, and one ranker discriminator. Aiming at generating responses that approximate the ground-truth and receive high ranking scores from the discriminator, the two generators learn to generate improved highly relevant responses and competitive unobserved candidates respectively, while the discriminative ranker is trained to identify true responses from adversarial ones, thus featuring the merits of both generator counterparts. The experimental results on a large short-text conversation data demonstrate the effectiveness of the ensembleGAN by the amelioration on both human and automatic evaluation metrics.

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and cons. Despite the natural idea of an ensemble model of the two, existing ensemble methods only focused on leveraging one approach to enhance another, we argue however that they can be further mutually enhanced with a proper training strategy. In this paper, we propose ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario. It consists of a language-model-like generator, a ranker generator, and one ranker discriminator. Aiming at generating responses that approximate the ground-truth and receive high ranking scores from the discriminator, the two generators learn to generate improved highly relevant responses and competitive unobserved candidates respectively, while the discriminative ranker is trained to identify true responses from adversarial ones, thus featuring the merits of both generator counterparts. The experimental results on a large short-text conversation data demonstrate the effectiveness of the ensembleGAN by the amelioration on both human and automatic evaluation metrics.

Social networking sites have been growing at an unprecedented rate in recent years. User profiling and personalized recommendation plays an important role in social networking, such as targeting advertisement and personalized news feed. For NLPCC Task 8, there are two subtasks. Subtask one is User Tags Prediction (UTP), which is to predict tags related to a user. We consider UTP as a Multi Label Classification (MLC) problem and proposed a CNN-RNN framework to explicitly exploit the label dependencies. The proposed framework employs CNN to get the user profile representation and the RNN module captures the dependencies among labels. Subtask two, User Following Recommendation (UFR), is to recommend friends to the users. There are mainly two approaches: Collaborative Filtering (CF) and Most Popular Friends (MPF), and we adopted a combination of both. Our experiments show that both of our methods yield clear improvements in F1@K compared to other algorithms and achieved first place in both subtasks.

Artificial Intelligence continues to grow in popularity on various industrial platforms, becoming especially prominent in Chatbot technology. A great deal of recent research was focused on social and assistive Chatbot, and its technology has been evolving over time. Following this direction, a Chatbot Framework is established in this paper, discussing about the relevant technologies. Firstly, the development of Artificial Intelligence is introduced. In particular, we present the Chatbot history of technology timeline. Following this, we describe the capabilities of the Chatbot and discuss about the technologies. The entire Chatbot framework will be presented afterwards, as well as the supporting set of modules. Our analysis of this framework shows that the framework that is based on some theoretical designs could be practically implemented to satisfy the required capabilities in the industry. Through our analysis, we show that the capabilities are also feasible.

Recommender systems have been proposed to exploit the potential of social network by filtering the information and offer recommendations to a user that he is predicted to like. Collaborative Filtering (CF) is believed to be a suitable underlying technique for recommender systems on social network, because CF gathers tastes of similar users; and social network provides such a collaborative social environment. One inherent challenge however for running CF on social network is quantitative estimation of trust between friends. Although many researchers investigated trust metrics and models in social network, none so far has efficiently integrated them in a CF algorithm. The contribution of this paper is a framework of collaborative filtering on social network, and a novel approach in measuring trust factors by data-mining over a survey dataset provided by The Facebook Project. The quantitatively estimated trust factors can be used as input parameters in the CF algorithm. Facebook is taken as a case study here to illustrate the concepts.