En  este documento se presenta la investigación que está siendo llevada a cabo en el Grupo de Procesamiento de Lenguaje Natural (GPLN) de la Universidad Politécnica de Cataluña (UPC). En concreto, hemos articulado la presentación de las diferentes lineas de trabajo tomando como referencia su aplicación en un asistente virtual. Creemos que su uso y implantación irá en aumento en los próximos diez años, de ahí la importancia del estado de las tecnologías del lenguaje natural y, aún más, de los nuevos retos que este tipo de aplicaciones nos plantean.

[Download full paper / Descargar artículo completo]

Internet growth has provoked that information search had come to have one of the most relevant roles in the industry and to be one of the most current topics in research environments. Internet is the largest information container in history and its facility to generate new information leads to new challenges when talking about retrieving information and discern which one is more relevant than the rest.

Parallel to the information growth in quantity, the way information is provided has also changed. One of these changes that has provoked more information traffic has been the emergence of social networks. We have seen how social networks can provoke more traffic than search engines themselves. We can draw conclusions that allow us to take a new approach to the information retrieval problem. Public trusts the most information coming from known contacts.

In this document we will explore a possible change in classic search engines to bring them closer to the social side and adquire those social advantages.

[Download full paper / Descargar artículo completo]

In this work, a novel approach is introduced in which NLP systems cooperate together with users in the processing and satisfactory achievement of a given task.

[Download full paper / Descargar artículo completo]

In this paper we present SIC + Health 3.0, a personalized information system that tries to cover the main information needs from the two main actors in the health ecosystem: patients and physicians. SIC + Health 3.0 integrates some basis health functionalities such as Electronic records managements, and several other Technologies that have been successfully tested in other application environments, such as GIS and recommender Systems.

[Download full paper / Descargar artículo completo]

In this article it is introduced FuMaS (Fuzzy Matching System), a system that allows efficient recovery of addresses through noisy queries. The fuzzy retrieval of this information has countless applications, from finding / clean duplicates in databases (voter registration, find nests of mail fraud, etc.) to correct the input from users on systems such as street directories or any type of form where an address has to be filled. The results of these experiments show that FuMaS is a very useful tool for addresses retrieval in noisy queries, being able to resolve about 85% of the addresses with errors which were introduced into the system; a 15% higher efficiency than any other similar system tested.

[Download full paper / Descargar artículo completo]

In this paper we present the advantages of applying trust in recommender systems for social networks like Wipley, a vertical social network of videogames, where users can access information related to games and interact with other users and their opinions. This kind or recommendations are based on the social graph of the user, and using it in sites like Wipley is aimed to offer relevant and confident content to the user. This will increase user’s satisfaction with the site and other users and, at the same time, will benefit the social network with an increase of information demand and purchase of related products.

[Download full paper / Descargar artículo completo]

Mobile phones have become one of the most widely used devices throughout the world. The mobile device industry has become one of the greatest technological advance of human history in the last decade and a perfect way for people to interact with information systems. This article analyzes the situation and describes a new way for using systems based on content based information retrieval.

[Download full paper / Descargar artículo completo]

The Web 2.0 has been successful thank to the possibility for the user to interact dynamically, not only in collaborative environments, but also in forums and adding/sharing resources to the Web.

Two of the most important examples that apply for this paradigm are Flickr and YouTube. The first one host the majority of videos that are played on the Web, and the latter has built the biggest photographers community all over the Internet. Both services work in the same way, letting the user to upload resources with information attached to it, which help to explain or classify it. As they are international communities, the resources added by the users will be in different languages, so the query to search multimedia resources on these sites is dependable on the query language.

The purpose of this paper is to introduce Babxel, a multilingual and multimedia information retrieval system, born due to a Computer Engineering final degree project, as an upgrade and extension of FlickrBabel. Babxel takes advantages of the automatic multilingual translation to generate more results related to the users’ queries, results obtained from the platforms previously mentioned.

[Download full paper / Descargar artículo completo]

More and more people have access to Internet and the content they produce keeps growing. The need to know what people are writing in blogs, forums and social media in general about specific brands and products has become strategically important for large corporations all around the globe. We will present the demo of an application, NaturalOpinions, which follows a rule-based NLP approach to parsing user-generated content both in English and Spanish. The application is able to detect the topic and extract the sentiment, either positive or negative, about particular product features or brand names. Social media intelligence solutions can thus be implemented rapidly with Bitext’s language technologies.

[Download full paper / Descargar artículo completo]

The rise of social media networks has entirely transformed the searching and analysis techniques used until today. Many companies aim at analyzing the opinions found on the Internet therefore shaping the future of Sentiment Analysis Tools.

[Download full paper / Descargar artículo completo]