A recent ''third wave'' of neural network (NN) approaches now delivers state-ofthe-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, work in this area is often referred to as deep learning. Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created. In this paper,

No abstract

Abstract. Being one of the most popular microblogging platforms, Twitter handles more than two billion queries per day. Given the users' desire for fresh and novel content but their reluctance to submit long and descriptive queries, there is an inevitable need for generating diversified search results to cover different aspects of a query topic. In this paper, we address diversification of results in tweet search by adopting several methods from the text summarization and web search domains. We provide an exhaustive evaluation of all the methods using a standard dataset specifically tailored for this purpose. Our findings reveal that implicit diversification methods are more promising in the current setup, whereas explicit methods need to be augmented with a better representation of query sub-topics.

With millions of users worldwide, crowd-sourced social media data provide a valuable data source for events happening around the world. More specifically, microblogs, which are social networks that enforce short text messages, have a high popularity due to their availability as a mobile application and the practicality of short messages. Estimating the location of the events detected by following posts in microblogs have been the motivation of numerous recent studies. Extracting the location information and estimating the event location is a challenging task to maintain satisfactory situation awareness, especially for emergency cases such as fire or traffic accidents. Today, Twitter is among the most popular microblogging platforms, and there are recent research efforts aimed at detection of novel events online by following the Tweets. In order to analyze events, researchers generally focus on spatio-temporal features of the posts. Temporal features denote the time and ordering of posts, whereas spatial features are useful for location extraction or estimation. In this work, we present an overview on the process for toponym recognition and location estimation from microblogs.196 European Handbook of Crowdsourced Geographic Information