The development of deep neural networks and the emergence of pre-trained language models such as BERT allow to increase performance on many NLP tasks. However, these models do not meet the same popularity for tweet stream summarization, which is probably because their computation limitation requires to drastically truncate the textual input. Our contribution in this article is threefold. First, we propose a neural model to automatically and incrementally summarize huge tweet streams. This extractive model combines in an original way pre-trained language models and vocabulary frequency based representations to predict tweet salience. An additional advantage of the model is that it automatically adapts the size of the output summary according to the input tweet stream. Second, we detail an original methodology to construct tweet stream summarization datasets requiring little human effort. Third, we release the TES 2012-2016 dataset constructed using the aforementioned methodology. Baselines, oracle summaries, gold standard, and qualitative assessments are made publicly available. To evaluate our approach, we conducted extensive quantitative experiments using three different tweet collections as well as an additional qualitative evaluation. Results show that our method outperforms state-of-the-art ones. We believe that this work opens avenues of research for incremental summarization, which has not received much attention yet.

To fulfill their information needs, users submit sets of related queries to available search engines. Query logs record users' activities along with timestamps and additional search-related information. The analysis of those chronological query logs enables the modeling of search tasks from user interactions. Previous research works rely on clicked URLs and surrounding queries to determine if adjacent queries are part of the same search tasks to segment the query logs properly. However, waiting for clicked URLs or future adjacent queries could render the use of these methods unfeasible in user supporting applications that require model results on the fly. Therefore, we propose a model for sequential search log segmentation. The proposed model uses only query pairs and their time span, generating results suited for on the fly user supporting applications, with improved accuracy over existing search segmentation approaches. We also show the advantages of fine-tuning the proposed model for adjusting the architecture to a small annotated collection.

Users convert their information needs to search queries, which are then run on available search engines. Query logs registered by search engines enable the automatic identification of the search tasks that users perform to fulfill their information needs. Search engine logs contain queries in multiple languages, but most existing methods for search task identification are not multilingual. Some methods rely on search context training of custom embeddings or external indexed collections that support a single language, making it challenging to support the multiple languages of queries run in search engines. Other methods depend on supervised components and user identifiers to model search tasks. The supervised components require labeled collections, which are difficult and costly to get in multiple languages. Also, the need for user identifiers renders these methods unfeasible in user agnostic scenarios. Hence, we propose an unsupervised multilingual approach for search task identification. The proposed approach is user agnostic, enabling its use in both user-independent and personalized scenarios. Furthermore, the multilingual query representation enables us to address the existing trade-off when mapping new queries to the identified search tasks.

Many papers have appeared recently assessing the effects of using tables and graphs in scientific publications. In this brief communication, we assess some of the methodological difficulties that have arisen in this context. These difficulties encompass issues of data availability, suitability of indicators, nature and purpose of tables and graphs, and the role of supplementary information.

The number of authors collaborating to write scientific articles has been increasing steadily, and with this collaboration, other factors have also changed, such as the length of articles and the number of citations. However, little is known about potential discrepancies in the use of tables and graphs between single and collaborating authors. In this article, we ask whether multiauthor articles contain more tables and graphs than single‐author articles, and we studied 5,180 recent articles published in six science and social sciences journals. We found that pairs and multiple authors used significantly more tables and graphs than single authors. Such findings indicate that there is a greater emphasis on the role of tables and graphs in collaborative writing, and we discuss some of the possible causes and implications of these findings.

Abstract This article describes an information retrieval approach according to the two different search modes that exist: browsing an ontology (via categories) or defining a query in free language (via keywords). Various proposals offer approaches adapted to one of these two modes. We present a proposal leading to a system allowing the integration of both modes using the same search engine. This engine is adapted according to each possible search mode.