María Granados Buey

TM-Gen: A Topic Map Generator from Text Documents

The vast amount of text documents stored in digital format is growing at a frantic rhythm each day. Therefore, tools able to find accurate information searching in natural language information repositories are gaining great interest in recent years. In this context, there are especially interesting tools capable of dealing with large amounts of text information and deriving human-readable summaries. However, one step further is to be able not only to summarize, but to extract the knowledge stored in those texts, and even represent it graphically. In this paper we present an architecture to generate automatically a conceptual representation of knowledge stored in a set of text-based documents. For this purpose we have used the topic maps standard and we have developed a method that combines text mining, statistics, linguistic tools, and semantics to obtain a graphical representation of the information contained therein, which can be coded using a knowledge representation language such as RDF or OWL. The procedure is language-independent, fully automatic, self-adjusting, and it does not need manual configuration by the user. Although the validation of a graphic knowledge representation system is very subjective, we have been able to take advantage of an intermediate product of the process to make a experimental validation of our proposals.

GEO-NASS: A Semantic Tagging Experience from Geographical Data on the Media

From a documentary point of view, an important aspect when we are conducting a rigorous labeling is to consider the geographic locations related to each document. Although there exist tools and geographic databases, it is not easy to find an automated labeling system for multilingual texts specialized in this type of recognition and further adapted to a particular context. This paper proposes a method that combines geographic location techniques with Natural Language Processing and statistical and semantic disambiguation tools to perform an appropriate labeling in a general way. The method can be configured and fine-tuned for a given context in order to optimize the results. The paper also details an experience of using the proposed method over a content management system in a real organization a major Spanish newspaper. The experimental results obtained show an overall accuracy of around 80%, which shows the potential of the proposal.

SQX-Lib: Developing a Semantic Query Expansion System in a Media Group

Recently, there has been an exponential growth in the amount of digital data stored in repositories. Therefore, the efficient and effective retrieval of information from them has become a key issue. Organizations use traditional architectures and methodologies based on classical relational databases, but these approaches do not consider the semantics of the data or they perform complex ETL processes from relational repositories to triple repositories. Most companies do not carry out this type of migration due to lack of time, money or knowledge. In this paper we present a system that performs a semantic query expansion to improve information retrieval from traditional relational databases repositories. We have also linked it to an actual system and we have carried out a set of tests in a real Media Group organization. Results are very promising and show the interest of the proposal.

The AIS Project: Boosting Information Extraction from Legal Documents by using Ontologies

In the legal field, it is a fact that a large number of documents are processed every day by management companies with the purpose of extracting data that they consider most relevant in order to be stored in their own databases. Despite technological advances, in many organizations, the task of examining these usually-extensive documents for extracting just a few essential data is still performed manually by people, which is expensive, time-consuming, and subject to human errors. Moreover, legal documents usually follow several conventions in both structure and use of language, which, while not completely formal, can be exploited to boost information extraction. In this work, we present an approach to obtain relevant information out from these legal documents based on the use of ontologies to capture and take advantage of such structure and language conventions. We have implemented our approach in a framework that allows to address different types of documents with minimal effort. Within this framework, we have also regarded one frequent problem that is found in this kind of documentation: the presence of overlapping elements, such as stamps or signatures, which greatly hinders the extraction work over scanned documents. Experimental results show promising results, showing the feasibility of our approach.

Information Extraction on Weather Forecasts with Semantic Technologies

In this paper, we describe a natural language application which extracts information from worded weather forecasts with the aim of quantifying the accuracy of weather forecasts. Our system obtains the desired information from the weather predictions taking advantage of the structure and language conventions with the help of a specific ontology. This automatic system is used in verification tasks, it increases productivity and avoids the typical human errors and probable biases in what people may incur when performing this task manually. The proposed implementation uses a framework that allows to address different types of forecasts and meteorological variables with minimal effort. Experimental results with real data are very good, and more important, it is viable to being used in a real environment.

KGNR: A knowledge-based geographical news recommender

Online news reading services, such as Google News and Yahoo! News, have become very popular since the Internet provides fast access to news articles from various sources around the world. A key issue of these services is to help users to find interesting articles that match their preferences as much as possible. This is the problem of personalized news recommendation. Recently, personalized news recommendation has become a promising research direction and a variety of techniques have been proposed to tackle it, including content-based systems, collaborative filtering systems and hybrid versions of these two. In addition, the widespread use of mobile phones today and the different features that these phones offer users allow the possibility to keep users up to date with the latest news that have taken place in their environment, anywhere and at any time. This paper presents KGNR (Knowledge-based Geographical News Recommender), a new approach to develop a personalized news recommendation system as an application for mobile phones that takes into account the geolocation of the user and uses learned user profiles to generate personalized news recommendations. For this purpose, a content-based recommendation mechanism have been combined with topic-maps and geolocation for modeling the recommendation system.

An Approach for Automatic Query Expansion Based on NLP and Semantics

Nowadays, there is a huge amount of digital data stored in repositories that are queried by search systems that rely on keyword-based interfaces. Therefore, the retrieval of information from repositories has become an important issue. Organizations usually implement architectures based on relational databases that do not consider the syntax and semantics of the data. To solve this problem, they perform complex Extract, Transform and Load (ETL) processes from relational repositories to triple stores. However, most organizations do not carry out this migration due to lack of time, money and knowledge.

Knowledge Obtention Combining Information Extraction Techniques with Linked Data

Today, we can find a vast amount of textual information stored in proprietary data stores. The experience of searching information in these systems could be improved in a remarkable manner if we combine these private data stores with the information supplied by the Internet, merging both data sources to get new knowledge. In this paper, we propose an architecture with the goal of automatically obtaining knowledge about entities (e.g., persons, places, organizations, etc.) from a set of natural text documents, building smart data from raw data. We have tested the system in the context of the news archive of a real Media Group.

Automatic Legal Document Analysis: Improving the Results of Information Extraction Processes Using an Ontology

Information Extraction (IE) is a pervasive task in the industry that allows to obtain automatically structured data from documents in natural language. Current software systems focused on this activity are able to extract a large percentage of the required information, but they do not usually focus on the quality of the extracted data. In this paper we present an approach focused on validating and improving the quality of the results of an IE system. Our proposal is based on the use of ontologies which store domain knowledge, and which we leverage to detect and solve consistency errors in the extracted data. We have implemented our approach to run against the output of the AIS system, an IE system specialized in analyzing legal documents and we have tested it using a real dataset. Preliminary results confirm the interest of our approach.

AEMIX: Semantic Verification of Weather Forecasts on the Web

The main objectives of a meteorological service are the development, implementation and delivery of weather forecasts. Weather predictions are broadcasted to society through different channels, i.e. newspaper, television, radio, etc. Today, the use of the Web through personal computers and mobile devices stands out. The forecasts, which can be presented in numerical format, in charts, or in written natural language, have a certain margin of error. Providing automatic tools able to assess the precision of predictions allows to improve these forecasts, quantify the degree of success depending on certain variables (geographic areas, weather conditions, time of year, etc.), and focus future work on areas for improvement that increase such accuracy. Despite technological advances, the task of verifying forecasts written in natural language is still performed manually by people in many cases, which is expensive, time-consuming, and subjected to human errors. On the other hand, weather forecasts usually follow several conventions in both structure and use of language, which, while not completely formal, can be exploited to increase the quality of the verification. In this paper, we describe a methodology to quantify the accuracy of weather forecasts posted on the Web and based on natural language. This work obtains relevant information from weather forecasts by using ontologies to capture and take advantage of the structure and language conventions. This approach is implemented in a framework that allows to address different types of predictions with minimal effort. Experimental results with real data are promising, and most importantly, they allow direct use in a real meteorological service.