In this paper, we introduce a state-of-the-art pseudo-labeling technique for few-shot intent detection.We devise a folding/unfolding hierarchical clustering algorithm which assigns weighted pseudo-labels to unlabeled user utterances.We show that our two-step method yields significant improvement over existing solutions.This performance is achieved on multiple intent detection datasets, even in more challenging situations where the number of classes is large or when the dataset is highly imbalanced.Moreover, we confirm these results on the more general text classification task.We also demonstrate that our approach nicely complements existing solutions, thereby providing an even stronger state-of-the-art ensemble method.We make our code publicly available 1 for future research.

Navigating large knowledge bases made of billions of triples is very challenging. In this demonstration, we showcase Fouilla, a topical Knowledge Base browser that offers a seamless navigational experience of DBpedia. We propose an original approach that leverages both structural and semantic contents of Wikipedia to enable a topic-oriented filter on DBpedia entities. We devise an approach to drastically reduce the query time and to ensure a seamless browsing experience to the end user. We demonstrate how our system offers a novel and meaningful experience of DBpedia browsing by challenging the user to search for relevant information within the Knowledge Base in different use cases.

International audience

Automatic generation of questions has recently received attention, as an indirect consequence of the renewed interest in Question Answering systems. Yet, most Automatic Question Generation systems focused on tasks like question selection, verbalization, distractor generation and difficulty assessment. In this paper, we come up with a novel task for Question Generation systems: thematic question generation. Inspired by a famous trivia board game, we aim at solving the problem of generating meaningful questions and their distractors for common knowledge topics. In this paper, we develop an end-to-end system that tackles these issues. We use the Wikipedia structure and content to determine the topics and their boundaries. We developed a template based approach to generate questions, allowing complex questions generation from binary and n-ary statements. To automatically generate templates, we developed an approach that reverts templates used for questions answering, allowing us to import more than 2000 templates. Our experimental campaign reports a success in topic assignment of 0.69 and very high scores (>0.9) for questions and distractors quality along with high inter-rater agreements.

Docker is the most popular open-source software for managing software containers. Docker is widely used in the industry and is becoming the de-facto standard. In this paper, we tackle the issue of bringing Docker into the Linked Open Data Cloud to enhance docker images descriptions and search. We first present the construction of the ontology that describes Docker images. This ontology is interconnected with DBPedia and reuses SIOC and prov vocabularies. We then describe the automated process that automatically extracts data from the Docker Hub Registry to populate the aforementioned ontology. We also present a Web platform that provides a SPARQL endpoint as well as analytical insights into the dataset.

Top-k queries over data streams is a well studied problem. There exists numerous systems allowing to process continuous queries over sliding windows. At the opposite, non-append only streams call for ad-hoc solutions, e.g. tailor-made solutions implemented in a mainstream programming language. In the meantime, the Stream API and lambda expressions have been added in Java 8, thus gaining powerful operations for data stream processing. However, the Java Collections Framework does not provide data structures to safely and conveniently support sorted collections of evolving data. In this paper, we demonstrate Upsortable, an annotation-based approach that allows to use existing sorted collections from the standard Java API for dynamic data management. Our approach relies on a combination of pre-compilation abstract syntax tree modifications and runtime analysis of bytecode. Upsortable offers the developer a safe and time-efficient solution for developing top-k queries on data streams while keeping a full compatibility with standard Java.

The advent of semantic data on the Web requires efficient reasoning systems to infer RDF and OWL data. The linked nature and the huge volume of data entail efficiency and scalability challenges when designing productive inference systems. This paper presents Inferray, an implementation of RDFS, ρdf, and RDFS-Plus inference with improved performance over existing solutions. The main features of Inferray are 1) a storage layout based on vertical partitioning that guarantees sequential access and efficient sort-merge join inference; 2) efficient sorting of pairs of 64-bit integers using ad-hoc optimizations on MSD radix and a custom counting sort; 3) a dedicated temporary storage to perform efficient graph closure computation. Our measurements on synthetic and real-world datasets show improvements over competitors on RDFS-Plus, and up to several orders of magnitude for transitivity closure.

Real-time recommendation of Twitter users based on the content of their profiles is a very challenging task. Traditional IR methods such as TF-IDF fail to handle efficiently large datasets. In this paper we present a scalable approach that allows real time recommendation of users based on their tweets. Our model builds a graph of terms, driven by the fact that users sharing similar interests will share similar terms. We show how this model can be encoded as a compact binary footprint, that allows very fast comparison and ranking, taking full advantage of modern CPU architectures. We validate our approach through an empirical evaluation against the Apache Lucene’s implementation of TF-IDF. We show that our approach is in average two hundred times faster than standard optimized implementation of TF-IDF with a precision of 58%.

The Semantic Web has gained substantial momentum over the last decade. It contributes to the manifestation of knowledge from data, and leverages implicit knowledge through reasoning algorithms. The main drawbacks of current reasoning methods over ontologies are two-fold: first they struggle to provide scalability for large datasets, and second, the batch processing reasoners who provide the best scalability so far are unable to infer knowledge from evolving data. We contribute to solving these problems by introducing Slider, an efficient incremental reasoner. Slider goes a significant step beyond existing system, including i) performance, by more than a 70% improvement in average compared to the fastest reasoner available to the best of our knowledge, and ii) inferences on streams of semantic data, by using intrinsic features that are themselves streams-oriented. Slider is fragment agnostic and conceived to handle expanding data with a growing background knowledge base. It natively supports pdf and RDFS, and its architecture allows to extend it to more complex fragments with a minimal effort. In this demo a web-based interface allows the users to visualize the internal behaviour of Slider during the inference, to better understand its design and principles.

Microblogging websites such as Twitter produce tremendous amount of data each second. Consequently, real-time recommendation systems require very efficient algorithm to quickly proceed this massive amount of data. In this paper we propose a scalable and extensible way of building content-based user profiles. Scalability refers to the relative complexity of algorithms involved in building the users profiles with respect to state-of-the-art solutions. Extensibility consider avoiding to recompute the model for newcomers. We present a tractable algorithm to build user profiles out of their tweets. Our model is a graph of terms cooccurency, driven by the fact that user sharing similar interests will share similar terms. We then present how this model can be encoded as a binary footprint, hence boosting comparison of users. We provide an empirical study to measure how the distance between users in the hash space differs from distance between users using standard Information Retrieval techniques. This experiment is based on a Twitter dataset we crawled, and represents 25K users and 1 million tweets. Our approach is driven by real-time analysis requirements and is thus oriented on a trade-off between expressivity and efficiency. Experimental results shows that our approach outperforms vector space model by three orders of magnitude, with a precision of 58%.

In this paper we present a Friend Recommender System for micro-blogging. Traditional batch processing of massive amounts of data makes it difficult to provide a near-real time friend recommender system or even a system that can properly scale to millions of users. In order to overcome these issues, we have designed a solution that represents user-generated micro posts as a set of pseudo-cliques. These graphs are assigned a hash value using an original Concept-Sensitive Hash function, a new sub-kind of Locally-Sensitive Hash functions. Finally, since the user profiles are represented as a binary footprint, the pairwise comparison of footprints using the Hamming distance provides scalability to the recommender system. The paper goes with an online application relying on a large Twitter dataset, so that the reader can freely experiment the system.

Over the last decade, two new facets of the Web emerged. On one hand, the Semantic Web provides data structures in order to break meanings barriers between distributed and heterogeneous data sources presents on the Web. On the other hand, the Social Web helps in clustering Web users into communities, and let them be prosumers of their Web experience. Both visions encompass many online applications, including Education. On the question of what is really the next stage of Web developments for Education, authors usually focus on a single of these two facets of the Web. As few studies have tried to combine them for an educational purpose this paper aims at giving an insight on the pioneers' works and the opportunities raised by mixing the Social and the Semantic Web for education.

The focus of existing virtual communities is centered on a particular product or social interaction and the role of mobile devices is restricted to exchange a limited amount of contents. Herewith we envisage that the upcoming virtual communities will exploit the potential of social interaction and context information to offer personalized services to its members and mobile devices will play a significant role in this process. As a step towards this direction, in this paper we propose a business model for the mobile virtual communities in which the mobile device takes on the role of a content producer and content consumer. Though there are a number of research issues which need to be addressed to realize such virtual communities, in this paper we focus on the service requirements, architecture and open source software implementation of a technical platform for the content producer and consumer mobile devices.