Angel Luis Garrido

An experience developing a semantic annotation system in a media group

Nowadays media companies have difficulties for managing large amounts of news from agencies and self-made articles. Journalists and documentalists must face categorization tasks every day. There is also an additional trouble due to the usual large size of the list of words in a thesaurus, the typical tool used to tag news in the media. In this paper, we present a new method to tackle the problem of information extraction over a set of texts where the annotation must be composed by thesaurus elements. The method consists of applying lemmatization, obtaining keywords, and finally using a combination of Support Vector Machines (SVM), ontologies and heuristics to deduce appropriate tags for the annotation. We have evaluated it with a real set of changing news and we compared our tagging with the annotation performed by a real documentation department, obtaining very good results.

NASS: News Annotation Semantic System

Today in media companies there is a serious problem for cataloging news due to the large number of articles received by the documentation departments. That manual labor is subject to many errors and omissions because of the different points of view and expertise level of each staff member. There is also an additional difficulty due to the large size of the list of words in a thesaurus. In this paper, we present a new method for solving the problem of text categorization over a corpus of newspaper articles where the annotation must be composed of thesaurus elements. The method consists of applying lemmatization, obtaining keywords and named entities, and finally using a combination of Support Vector Machines (SVM), ontologies and heuristics to infer appropriate tags for the annotation. We carried out a detailed evaluation of our method with real newspaper articles, and we compared out tagging with the annotation performed by a real documentation department, obtaining really promising results.

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.

SOLE-R: A Semantic and Linguistic Approach for Book Recommendations

Reading is a fundamental skill that each person needs to develop during early childhood and continue to enhance into adulthood. While children/teenagers depend on this skill to advance academically and become educated individuals, adults are expected to acquire a certain level of proficiency in reading so that they can engage in social/civic activities and successfully participate in the workforce. A step towards assisting individuals to become lifelong readers is to provide them adequate reading selections which can cultivate their intellectual and emotional growth. With that in mind, we have developed SOLE-R, a topic map-based tool that yields book recommendations. SOLE-R takes advantage of lexical and semantic resources to infer the likes/dislikes of a reader and thus is not restricted by the syntactic constraints imposed on existing recommenders. Furthermore, SOLE-R relies on publicly-accessible data on books to perform an in-depth analysis of the preferences of a reader that goes beyond book content or reading patterns explored by existing recommenders. We have verified the correctness of SOLE-R using a popular benchmark dataset. In addition, we have compared its performance with (state-of-the-art) recommendation strategies to further demonstrate the effectiveness of SOLE-R.

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.

Hypatia: An expert system proposal for documentation departments

Nowadays the vast amount of text-based information stored in organizations requires different approaches and new tools in order to manage it adequately. This paper presents Hypatia, a support expert system for documentation departments and regular users that exploits not only local information, but also external resources from the Web (e.g., Linked Data). The expert system uses different modules: Natural Language Processing (NLP) analysis, categorization, semantic disambiguation, Automatic Query Expansion (AQE), semantic search, summarization, knowledge extraction, and aggregation. Users can interact with the expert system in different ways, varying from giving very specific orders to writing a simple list of keywords. The latter method requires a previous interpretation before deciding the response of the system. The obtained results will benefit from semantic links referencing complementary data to improve both the information presentation and the data navigation.

TMR: A Semantic Recommender System Using Topic Maps on the Items’ Descriptions

Recommendation systems have become increasingly popular these days. Their utility has been proved to filter and to suggest items archived at web sites to the users. Even though recommendation systems have been developed for the past two decades, existing recommenders are still inadequate to achieve their objectives and must be enhanced to generate appealing personalized recommendations effectively. In this paper we present TMR, a context-independent tool based on topic maps that works with item’s descriptions and reviews to provide suitable recommendations to users. TMR takes advantage of lexical and semantic resources to infer users’ preferences and thus the recommender is not restricted by the syntactic constraints imposed on some existing recommenders. We have verified the correctness of TMR using a popular benchmark dataset.

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.