Search

Comunicació presentada a: LREC 2016, Tenth International Conference on Language Resources and Evaluation, celebrada del 23 al 28 de maig de 2016 a Portorož, Eslovènia. In most of the research studies on Author Profiling, large quantities of correctly labeled data are used to train the models. However, this does not reflect the reality in forensic scenarios: in practical linguistic forensic investigations, the resources that are available to profile the author of a text are usually scarce. To pay tribute to this fact, we implemented a Semi-Supervised Learning variant of the k nearest neighbors algorithm that uses small sets of labeled data and a larger amount of unlabeled data to classify the authors of texts by gender (man vs woman). We describe the enriched KNN algorithm and show that the use of unlabeled instances improves the accuracy of our gender identification model. We also present a feature set that facilitates the use of a very small number of instances, reaching accuracies higher than 70% with only 113 instances to train the model. It is also shown that the algorithm performs equally well using publicly available data. The presentation of this work was partially supported by the ICT PhD program of Universitat Pompeu Fabra through a travel grant.

International audience

Part 6: Third Intelligent Systems for Quality of Life Information Services Workshop (ISQL 2012); International audience; Environmental and meteorological conditions are of utmost importance for the population, as they are strongly related to the quality of life. Citizens are increasingly aware of this importance. This awareness results in an increasing demand for environmental information tailored to their specific needs and background. We present an environmental information platform that supports submission of user queries related to environmental conditions and orchestrates results from complementary services to generate personalized suggestions. From the technical viewpoint, the system discovers and processes reliable data in the web in order to convert them into knowledge. At run time, this information is transferred into an ontology-structured knowledge base, from which then information relevant to the specific user is deduced and communicated in the language of their preference. The platform is demonstrated with real world use cases in the south area of Finland showing the impact it can have on the quality of everyday life.

In this article, we present ongoing work on an advanced patent processing service PATExpert. The central assumption underlying PATExpert is that in order to meet the needs of the users of patent processing services, recourse must be made to the content of patent material. We introduce a content representation schema for patent documentation and sketch the design of techniques that facilitate the integration of this schema into the patent processing cycle. Two types of techniques are discussed. Techniques of the first type facilitate the access to the content of patent documentation provided in a textual format - be it by the human reader or by the machine - in that they rephrase and summarize the documentation and map it onto a formal semantic representation. Techniques of the second type operate on the content representation. At this stage, PATExpert is explored in two technology areas - optical recording devices and machine tools. The work is being carried out in the framework of an R&D-project partially funded by the European Commission.

Los grafos de coocurrencia léxica han sido utilizados en lingüística computacional en experimentos de desambiguación de sentidos pero hasta ahora no para la extracción de relaciones de hiperonimia, donde la metodología más usual ha sido la aplicación de patrones léxico-sintácticos. En este artículo mostramos que es posible extraer relaciones de hiperonimia entre términos utilizando estadísticas de coocurrencia. La clave del método reside en que las relaciones de coocurrencia no suelen ser simétricas en el caso de las relaciones de hiperonimia y, en consecuencia, es posible generar grafos dirigidos de coocurrencia que guardan una apariencia similar a la de una taxonomía. En el presente artículo presentamos experimentos con textos de la Wikipedia en castellano ordenados aleatoriamente, pero los resultados sugieren que la coocurrencia asimétrica entre términos es una propiedad intrínseca y macroscópica del discurso argumentativo en general. Word co-occurrence graphs have been used in computational linguistics mainly for word sense disambiguation and induction, but until very recently, not for the extraction of hypernymy relations, where the methodology most often applied is the use of lexico-syntactic patterns. In this paper, we show that it is possible to use word co-occurrence statistics to extract IS-A relations between entities in scientific and technical corpora. We exploit the fact that word co-occurrence often has a direction, that is, a term might co-occur with another, but this is very often not true the other way round. This means that one can represent co-occurrence as a directed graph and this graph resembles a taxonomy. In this paper we present an experiment with texts randomly extracted from the Spanish Wikipedia, but our findings suggest that this co-occurrence behavior is a macroscopic and intrinsic property of argumentative discourse in general. This research was funded by project APLE (Spanish Ministry of Science and Education: Ref. FFI2009-12188-C05-01/FILO) lead by Dr. M. Teresa Cabré.