Abstract
Human language constantly evolves due to the changing world and the need for easier forms of expression and communication. Our knowledge of language evolution is however still fragmentary despite significant interest of both researchers as well as wider public in the evolution of language. In this paper, we present an interactive framework that permits users study the evolution of words and concepts. The system we propose offers a rich online interface allowing arbitrary queries and complex analytics over large scale historical textual data, letting users investigate changes in meaning, context and word relationships across time.

Abstract
Building upon the success of the first edition, we organize the second edition of the Text2Story Workshop on Narrative Extraction from Texts in conjunction with the 41 st European Conference on Information Retrieval (ECIR 2019) on April 14, 2019. Our objective is to further consolidate the efforts of the community and reflect upon the progress made since the last edition. Although the understanding of natural language has improved over the last couple of years – with research works emerging on the grounds of information extraction and text mining – the problem of constructing consistent narrative structures is yet to be solved. It is expected that the state-of-the-art has been advancing in pursuit of methods that automatically identify, interpret and relate the different elements of narratives which are often spread among different sources. In the second edition of the workshop, we foster the discussion of recent advances in the link between Information Retrieval (IR) and formal narrative representations from text. © Springer Nature Switzerland AG 2019.

Abstract
In this demo, we present a tool that allows to automatically generate temporal summarization of news collections. Conta-me Histórias (Tell me stories) is a friendly user interface that enables users to explore and revisit events in the past. To select relevant stories and temporal periods, we rely on a key-phrase extraction algorithm developed by our research team, and event detection methods made available by the research community. Additionally, we offer the engine as an open source package that can be extended to support different datasets or languages. The work described here stems from our participation at the Arquivo.pt 2018 competition, where we have been awarded the first prize. © Springer Nature Switzerland AG 2019.

Abstract

Abstract

Abstract
As video games arc developing fast, many users issue queries related to video games in a daily fashion. While there Were a few attempts to understand their behavior, little is known on how the video game-related searches are done. Digesting and analyzing this search behavior may thus be faced as an important contribution for search engines to provide better results and search services for their users. To overcome this lack of knowledge and to gain more insight into how video game searches are done, we analyze in this paper, a number of game search queries submitted to a general search engine named Parsijoo. The analysis conducted was performed on top of 372,508 game search records extracted from the query logs within 253,516 different search sessions. Different aspects of video game searches are studied, including, their temporal distribution, game version specification. popular game categories, popular game platforms, game search sessions and clicked pages. Overall, the experimental analysis on video game searches shows that the current retrieval methods used by traditional search engines cannot be applied for game searches, thus, different retrieval and search services should be considered for these searches in the future.