Today's extraction of temporal information for events heavily depends on annotated temporal links. These so called TLINKs capture the relation between pairs of event mentions and time expressions. One problem is that the number of possible TLINKs grows quadratic with the number of event mentions, therefore most annotation studies concentrate on links for mentions in the same or in adjacent sentences. However, as our annotation study shows, this restriction results for 58% of the event mentions in a less precise information when the event took place. This paper proposes a new annotation scheme to anchor events in time. Not only is the annotation effort much lower as it scales linear with the number of events, it also gives a more precise anchoring when the events have happened as the complete document can be taken into account. Using this scheme, we annotated a subset of the TimeBank Corpus and compare our results to other annotation schemes. Additionally, we present some baseline experiments to automatically anchor events in time. Our annotation scheme, the automated system and the annotated corpus are publicly available. 1

Extracting the information from text when an event happened is challenging. Documents do not only report on current events, but also on past events as well as on future events. Often, the relevant time information for an event is scattered across the document. In this paper we present a novel method to automatically anchor events in time. To our knowledge it is the first approach that takes temporal information from the complete document into account. We created a decision tree that applies neural network based classifiers at its nodes. We use this tree to incrementally infer, in a stepwise manner, at which time frame an event happened. We evaluate the approach on the TimeBank-EventTime Corpus (Reimers et al., 2016) achieving an accuracy of 42.0% compared to an inter-annotator agreement (IAA) of 56.7%. For events that span over a single day we observe an accuracy improvement of 33.1 points compared to the state-of-the-art CAEVO system (Chambers et al., 2014). Without retraining, we apply this model to the SemEval-2015 Task 4 on automatic timeline generation and achieve an improvement of 4.01 points F1-score compared to the state-of-the-art. Our code is publically available.

Wireless sensor networks (WSNs) are usually missioned to gather critical information in hostile and adversarial environments, which make them susceptible to compromise and revelation. Therefore, establishing secure communication in such networks is of great importance necessitating utilization of efficient key distribution schemes. In order to address such methods, several works using probabilistic, deterministic and hybrid approaches have been introduced in past few years. In this paper, we study the connectivity of key-distribution mechanisms in secured topologies of wireless sensor networks. We explore the effect of the radio range on the connectivity of the network and provide a lower bound on the radio range under which the cover time of the underlying topology decreases significantly. We also deduce that any broadcasting algorithm in such a network is performing only by a factor O(n β ), where β ∈ (0, 1), worse than broadcasting algorithms in unsecured topologies. Our numerical results and simulation experiments validates the correctness and efficiency of our analysis.

Twitter is a popular microblogging service that has become a great medium for exploring emerging events and breaking news. Unfortunately, the explosive rate of information entering Twitter makes the users experience information overload. Since a great deal of tweets revolve around news events, summarising the storyline of these events can be advantageous to users, allowing them to conveniently access relevant and key information scattered over numerous tweets and, consequently, draw concise conclusions. A storyline shows the evolution of a story through time and sketches the correlations among its significant events. In this article, we propose a novel framework for generating a storyline of news events from a social point of view. Utilising powerful concepts from graph theory, we identify the significant events, summarise them and generate a coherent storyline of their evolution with reasonable computational cost for large datasets. Our approach models a storyline as a directed tree of socially salient events evolving over time in which nodes represent main events and edges capture the semantic relations between related events. We evaluate our proposed method against human-generated storylines, as well as the previous state-of-the-art storyline generation algorithm, on two large-scale datasets, one consisting of English tweets and the other one consisting of Persian tweets. We find that the results of our method are superior to the previous best algorithm and can be comparable with human-generated storylines.

No abstract