A major part of the job offers and candidates profiles are now available online. Leveraging this public data, Multiposting, a subsidiary of SAP, aims at providing in real-time an exhaustive job market analysis through the SmartSearch project. One big issue in this project, and more generally in the e-recruitment and the human resources management, is to extract the skills from the raw texts in order to associate a job or a candidate to its corresponding skills. This paper proposes to generate a multilingual base of skills in a novel bottom-up approach that finds its roots from the terminology used by candidates in professional social networks. The knowledge base is built by leveraging the Linked Open Data project DBpedia, as well as the tags of a Q&A website, StackOverflow. The large-scale experiments on real-world job offers show that the coverage and precision of the skills extraction are higher using this base than existing bases. The system has been implemented in industrial context and is used daily to extract the skills from thousands of documents, leading to advanced statistics as illustrated at the end this paper.

Many systems rank outcomes before suggesting them to a user, such as Recommender Systems or Information Retrieval Algo- rithms. These systems require manual validation, which is time consuming and costly in industrial context. As it is the case in our industrial applications, we assume that the user's needs can be fulfilled by only one relevant outcome. We thus consider an algorithm that systematically selects the top ranked outcome. This approach requires to compute a correctness, estimating the confidence of the automatic decision, or equivalently how likely the first outcome of the ranking system is to be correct. Based on this estimation, we can apply a threshold on the correctness, above which no manual action is required; the system avoids human validation in many cases. This paper proposes a novel method to estimate this correctness based on a supervised classification approach using the manual validations available in the base coupled with a representation of the system's scores. We conducted experiments on Multiposting real-world datasets generated by algorithms used in the industry; the first algorithm categorizes a job offer, the second recommends semantic equivalents for a given expression in a nomenclature. Our approach has thereby been evaluated and compared, and showed good results on our datasets, even with a limited training base. Moreover, in our experiments, for a given threshold, the better is the correctness estimation, the more performant is the semi-automatic system, showing that the correctness estimation leads thus to a crucial efficiency gain.

Case-Based Reasoning (CBR) is a problem solving methodology that reuses the knowledge of past experiences to solve new problems. It's a knowledge-based technique that has been introduced to the recommendation field to allow reasoning on domain knowledge and to generate more accurate recommendations. If CBR helps suggesting items that meet the users' search criteria, it has the disadvantage of being domain-dependent (all the reasoning process is generally based on hard-coded domain knowledge) and generating less personalized recommendations. In this paper, we propose an approach for a generic and personalized CBR-based recommender system. First, we use a generic ontology to formalize all the knowledge required during the reasoning process. The ontology represents an intermediate layer between the recommender engine and the application domain to ensure the domain-independence criteria. Second, we propose a hybridization strategy that combines CBR and collaborative filtering to alleviate the limitations of CBR and improve the personalized character of the recommendations. Finally, preliminary validation is performed using a publicly available data set of restaurants.

Nowadays, in the Web 2.0 reality, one of the most challenging task for companies that aim to manage and recommend job offers is to convey this enormous amount of information in a succinct and intelligent manner such to increase the performances of matching operations against users profiles/curricula and optimize the time/space complexity of these processes. With this goal, this paper presents a novel method to formalize the textual content of job offers that aims at identifying the most relevant information and fields expressed by them and leverage this compact formalization for job recommendation and profile matching in social network environments. This method has been then developed and tested in the industrial environment represented by Multiposting and Work4, world leaders in digital solutions of e-recruitment problems. In this study three classes of documents are considered: job offers, job categories and social network user profiles (as potential job candidates); each class contains several fields with textual information. The proposed representation method permits to dynamically identify those text fields, for each class, that could help a cross-matching strategy in order to preserve, from one hand, the matching/recommendation performances and, on the other hand, reduce the cost of these operations (due to a straightforward dimensionality reduction mechanism). We then evaluated and compared the presented approach showing significant improvements on both categorization and recommendation tasks by also drastically reducing their computational costs.

Helen Hastie, Marie-Aude Aufaure, Panos Alexopoulos, Hugues Bouchard, Catherine Breslin, Heriberto Cuayáhuitl, Nina Dethlefs, Milica Gašić, James Henderson, Oliver Lemon, Xingkun Liu, Peter Mika, Nesrine Ben Mustapha, Tim Potter, Verena Rieser, Blaise Thomson, Pirros Tsiakoulis, Yves Vanrompay, Boris Villazon-Terrazas, Majid Yazdani, Steve Young, Yanchao Yu. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014.

Question Answering (Q&A) from structured data is a technique that may revolutionize enterprise search. A very promising use-case for such technology is Business Intelligence (BI). In order to make BI more accessible to end-users, some efforts have been made in the field of search for existing reports. However, the problem of converting an end-user's natural language input to a valid structured query in an ad-hoc fashion hasn't been sufficiently solved yet. In this paper we present a framework for Q&A systems that operate on structured data. The main innovation is that the framework allows defining a mapping between recognized semantics of a user's questions to a structured query model that can be executed on arbitrary data sources. It bases on popular standards like RDF and SparQL and is therefore very easy to adapt to other domains or use-cases. We will describe the application of this framework at hand of a BI question answering use-case, which also includes the personalization of generated queries, demonstrating the realworld applicability of our approach. In our experiments, we demonstrate that with our approach one can easily achieve a similar answering quality as one of the most popular Q&A systems on the Web.

In this work, we demonstrate a web application, available at http://d-index.di.unito.it, that permits to analyze the scientific profiles of all the researchers indexed by DBLP by focusing on the collaborations that contributed to define their curricula. The presented application allows the user to analyze the profile of a researcher, her dependence degrees on all the co-authors (along her entire scientific publication history) and to make comparisons among them in terms of dependence patterns. In particular, it is possible to estimate and visualize how much a researcher has benefited from collaboration with another researcher as well as the communities in which she has been involved. Moreover, the application permits to compare, in a single chart, each researcher with all the scientists indexed in DBLP by focusing on their dependences with respect to many other parameters like the total number of papers, the number of collaborations and the length of the scientific careers.

Traditional software in Formal Concept Analysis makes little use of visualization techniques, producing poorly readable concept lattice representations when the number of concepts exceeds a few dozens. This is problematic as the number of concepts in such lattices grows significantly with the size of the data and the number of its dimensions. In this work we propose several methods to enhance the readability of concept lattices firstly though colouring and distortion techniques, and secondly by extracting and visualizing trees derived from concept lattice structures. These contributions represent an important step in the visual analysis of conceptual structures, as domain experts may visually explore larger datasets that traditional visualizations of concept lattice cannot represent effectively.

Many works have been proposed in order to improve the recommendation accuracy. Algorithms aiming to improve recommendation accuracy have been developed and evaluated. These algorithms usually work with training data sets which are learned and used to make predictions on users' tastes. The training data set choice is a difficult task not only due to the technical nature of the algorithm used, but also because of the user issues associated with the acquisition of their opinions, since the training data consist of users' opinions. In this work we show the importance of understanding which predictions are impacted when a rating is acquired by developing a naive active learning criterion based on the number of impacted predictions. To do that, a Rating Impact Analysis method for the user-based collaborative filtering is proposed and applied to the active learning issue.

Numerous data mining methods have been designed to help extract relevant and significant information from large datasets. Computing concept lattices allows clustering data according to their common features and making all relationships between them explicit. However, the size of such lattices increases exponentially with the volume of data and its number of dimensions. This paper proposes to use spatial pixel-oriented and tree-based visualisations of these conceptual structures in order to optimally exploit their expressivity.

In this paper, we present an approach for building medical domain ontology as a foundation for knowledge-centric decision support. The knowledge acquisition phase is based on heterogeneous data sources including textual corpora, practice guidelines, databases, terminological sources as well as existing ontologies and medical Standards. Beyond a knowledge modelization process, we propose a meta-conceptualization and a formalization phase constituting a Medical Core-Ontology established at a high-level of abstraction and guiding the operationalization and exploitation phase. The operationalization process instantiates a referential medical domain ontology and integrates it into a knowledge-based system allowing knowledge reasoning and inference and thus, preparing the basis for a medical decision support.

Ontologies provide a common layer which plays a major role in supporting information exchange and sharing. In this paper, we focus on the ontological concept extraction process from HTML documents. In order to improve this process, we propose an unsupervised hierarchical clustering algorithm namely "contextual ontological concept extraction" (COCE) which is an incremental use of the partitioning algorithm Kmeans and is guided by a structural context. Our context exploits the HTML structure and the location of words to select the semantically closer cooccurrents for each word and to improve the words weighting. Guided by this context definition, we perform an incremental clustering that refines the context of each word clusters to obtain semantically extracted concepts. The COCE algorithm offers the choice between either an automatic execution or a user's interaction. We experiment our algorithm on HTML documents related to the tourism domain. Our results show how the execution of our context-based algorithm which implements an incremental process and a successive refinement of clusters improves their conceptual quality and the relevance of the extracted ontological concepts

This paper presents Lvis, a visual query language for Geographic Information Systems (GIS) and for spatio-temporal databases. Visual queries are specified by means of a combination of icons. These icons are used to represent both object types and operators. Geometric shapes are used to represent spatial objects and relations among them; Balloons and temporal axis are used to represent temporal criteria. A visual approach has been chosen because it offers numerous advantages for the representation of spatio-temporal queries. Visual representations are in fact well-suited since they easily permit to express the spatial nature of a query. Several research works dealing with this issue have been proposed in the last ten years. Besides, visual querying is a friendly and simple querying mode. It is the reason why it is well-adapted to novice users. The paper introduces the spatio-temporal model of the language. It gives some examples of queries to explain how geometric shapes, icons and temporal axis are combined. Finally, it discusses the main issues tied to the visual, psycho-cognitive and spatio-temporal considerations.