Social networks play a fundamental role in the diffusion of information. However, there are two different ways of how information reaches a person in a network. Information reaches us through connections in our social networks, as well as through the influence external out-of-network sources, like the mainstream media. While most present models of information adoption in networks assume information only passes from a node to node via the edges of the underlying network, the recent availability of massive online social media data allows us to study this process in more detail.We present a model in which information can reach a node via the links of the social network or through the influence of external sources. We then develop an efficient model parameter fitting technique and apply the model to the emergence of URL mentions in the Twitter network. Using a complete one month trace of Twitter we study how information reaches the nodes of the network. We quantify the external influences over time and describe how these influences affect the information adoption. We discover that the information tends to "jump" across the network, which can only be explained as an effect of an unobservable external influence on the network. We find that only about 71% of the information volume in Twitter can be attributed to network diffusion, and the remaining 29% is due to external events and factors outside the network.

As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications.To this end, we present FEWSHOTWOZ, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develop the SC-GPT 1 model. It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains. Experiments on FEWSHOTWOZ and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods, measured by various automatic metrics and human evaluations.

With the abundance of automatic meeting transcripts, meeting summarization is of great interest to both participants and other parties. Traditional methods of summarizing meetings depend on complex multi-step pipelines that make joint optimization intractable. Meanwhile, there are a handful of deep neural models for text summarization and dialogue systems. However, the semantic structure and styles of meeting transcripts are quite different from articles and conversations. In this paper, we propose a novel abstractive summary network that adapts to the meeting scenario. We design a hierarchical structure to accommodate long meeting transcripts and a role vector to depict the difference among speakers. Furthermore, due to the inadequacy of meeting summary data, we pretrain the model on largescale news summary data. Empirical results show that our model outperforms previous approaches in both automatic metrics and human evaluation. For example, on ICSI dataset, the ROUGE-1 score increases from 34.66% to 46.28%.

Conversational question answering (CQA) is a novel QA task that requires understanding of dialogue context. Different from traditional single-turn machine reading comprehension (MRC) tasks, CQA includes passage comprehension, coreference resolution, and contextual understanding. In this paper, we propose an innovated contextualized attention-based deep neural network, SDNet, to fuse context into traditional MRC models. Our model leverages both inter-attention and self-attention to comprehend conversation context and extract relevant information from passage. Furthermore, we demonstrated a novel method to integrate the latest BERT contextual model. Empirical results show the effectiveness of our model, which sets the new state of the art result in CoQA leaderboard, outperforming the previous best model by 1.6% F 1 . Our ensemble model further improves the result by 2.7% F 1 .

Recent advances in click model have positioned it as an attractive method for representing user preferences in web search and online advertising. Yet, most of the existing works focus on training the click model for individual queries, and cannot accurately model the tail queries due to the lack of training data. Simultaneously, most of the existing works consider the query, url and position, neglecting some other important attributes in click log data, such as the local time. Obviously, the click through rate is different between daytime and midnight. In this paper, we propose a novel click model based on Bayesian network, which is capable of modeling the tail queries because it builds the click model on attribute values, with those values being shared across queries. We called our work General Click Model (GCM) as we found that most of the existing works can be special cases of GCM by assigning different parameters. Experimental results on a largescale commercial advertisement dataset show that GCM can significantly and consistently lead to better results as compared to the state-of-the-art works.