Search

285 p., Healthcare practice and clinical research produce vast amounts of digitised, unstructured data in multiple languages that are currently underexploited, despite their potential applications in improving healthcare experiences, supporting trainee education, or enabling biomedical research, for example. To automatically transform those contents into relevant, structured information, advanced Natural Language Processing (NLP) mechanisms are required. In NLP, this task is known as Information Extraction. Our work takes place within this growing field of clinical NLP for the Spanish language, as we tackle three distinct problems. First, we compare several supervised machine learning approaches to the problem of sensitive data detection and classification. Specifically, we study the different approaches and their transferability in two corpora, one synthetic and the other authentic. Second, we present and evaluate UMLSmapper, a knowledge-intensive system for biomedical term identification based on the UMLS Metathesaurus. This system recognises and codifies terms without relying on annotated data nor external Named Entity Recognition tools. Although technically naive, it performs on par with more evolved systems, and does not exhibit a considerable deviation from other approaches that rely on oracle terms. Finally, we present and exploit a new corpus of real health records manually annotated with negation and uncertainty information: NUBes. This corpus is the basis for two sets of experiments, one on cue andscope detection, and the other on assertion classification. Throughout the thesis, we apply and compare techniques of varying levels of sophistication and novelty, which reflects the rapid advancement of the field.

The influence of fake news in the perception of reality has become a mainstream topic in the last years due to the fast propagation of miss-leading information, which has been enhanced by social media. To contribute to the fight against misinformation, researchers have proposed to develop automated solutions. The task of automated claim verification consists in assessing the truthfulness of a claim by finding evidence about its veracity. Datasets with synthetic claims have been developed to train models that perform this task. However, naturally-occurring claims are usually semantically more complex than synthetic claims. In this work, we test if the use of explicit semantic structures can help with the task of claim verification. We integrate Semantic Role Labels and Open Information Extraction structures to a BERT model, showing some improvement on the performance of the task. Additionally, we perform some explainability tests which show that the semantically-enriched model is better at handling complex cases, such as sentences in passive form or with multiple propositions.

This paper describes the first approach to Grammatical Error Correction for Spanish health records. We present a series of experiments using neural networks and data augmentation, achieving 70.89 F0.5 score. Resources designed for this task are introduced, namely the IMEC corpus of corrected health records and the TMAE corpus of clinical texts augmented with errors., Este artículo presenta el primer trabajo sobre la corrección gramatical de textos clínicos en español. En este trabajo, presentamos un conjunto de experimentos basados en redes neuronales y aumentación de datos, en los cuales conseguimos una puntuación de 70,89 F0,5. Además, se presentan dos corpus creados para esta tarea: el corpus IMEC, un corpus médico corregido manualmente, y el corpus TMAE, un corpus de textos clínicos aumentado con errores.

Akats Gramatikalen Zuzenketa (GEC, ingelesetik, Grammatical Error Analysis) Hizkuntza Naturalaren Prozesamenduaren azpieremu bat da, ortogra a, puntuazio edo gramatika akatsak dituzten testuak automatikoki zuzentzea helburu duena. Orain arte, bigarren hizkuntzako ikasleek ekoitzitako testuetara bideratu da gehien bat, ingelesez idatzitako testuetara batez ere. Master-Tesi honetan gaztelaniaz idatzitako mediku-txostenetarako Akats Gramatikalen Zuzenketa lantzen da. Arlo espezi ko hau ez da asko esploratu orain arte, ez gaztelaniarako zentzu orokorrean, ezta domeinu klinikorako konkretuki ere. Hasteko, IMEC (gaztelaniatik, Informes Médicos en Español Corregidos) corpusa aurkezten da, eskuz zuzendutako mediku-txosten elektronikoen bilduma paralelo berria. Corpusa automatikoki etiketatu da zeregin honetarako egokitutako ERRANT tresna erabiliz. Horrez gain, hainbat esperimentu deskribatzen dira, zeintzuetan sare neuronaletan oinarritutako sistemak ataza honetarako diseinatutako baseline sistema batekin alderatzen diren., Grammatical Error Correction (GEC) is a sub field of Natural Language Processing that aims to automatically correct texts that include errors related to spelling, punctuation or grammar. So far, it has mainly focused on texts produced by second language learners, mostly in English. This Master's Thesis describes a first approach to Grammatical Error Correction for Spanish health records. This specific field has not been explored much until now, nor in Spanish in a general sense nor for the clinical domain specifically. For this purpose, the corpus IMEC (Informes Médicos en Español Corregidos) ---a manually-corrected parallel collection of Electronic Health Records--- is introduced. This corpus has been automatically annotated using the toolkit ERRANT, specialized in the automatic annotation of GEC parallel corpora, which was adapted to Spanish for this task. Furthermore, some experiments using neural networks and data augmentation are shown and compared with a baseline system also created specifically for this task.

170 p., Cada día se genera gran cantidad de texto en diferentes medios online. Gran parte de ese texto contiene opiniones acerca de multitud de entidades, productos, servicios, etc. Dada la creciente necesidad de disponer de medios automatizados para analizar, procesar y explotar esa información, las técnicas de análisis de sentimiento han recibido gran cantidad de atención por parte de la industria y la comunidad científica durante la última década y media. No obstante, muchas de las técnicas empleadas suelen requerir de entrenamiento supervisado utilizando para ello ejemplos anotados manualmente, u otros recursos lingüísticos relacionados con un idioma o dominio de aplicación específicos. Esto limita la aplicación de este tipo de técnicas, ya que dicho recursos y ejemplos anotados no son sencillos de obtener. En esta tesis se explora una serie de métodos para realizar diversos análisis automáticos de texto en el marco del análisis de sentimiento, incluyendo la obtención automática de términos de un dominio, palabras que expresan opinión, polaridad del sentimiento de dichas palabras (positivas o negativas), etc. Finalmente se propone y se evalúa un método que combina representación continua de palabras (continuous word embeddings) y topic-modelling inspirado en la técnica de Latent Dirichlet Allocation (LDA), para obtener un sistema de análisis de sentimiento basado en aspectos (ABSA), que sólo necesita unas pocas palabras semilla para procesar textos de un idioma o dominio determinados. De este modo, la adaptación a otro idioma o dominio se reduce a la traducción de las palabras semilla correspondientes.

Sentiment analysis is the area of Natural Language Processing that aims to determine the polarity (positive, negative, neutral) contained in an opinionated text. A usual resource employed in many of these approaches are the so-called polarity lexicons. A polarity lexicon acts as a dictionary that assigns a sentiment polarity value to words. In this work we explore the possibility of automatically generating domain adapted polarity lexicons employing continuous word representations, in particular the popular tool Word2Vec. First we show a qualitative evaluation of a small set of words, and then we show our results in the SemEval-2015 task 12 using the presented method., El análisis de sentimiento es un campo del procesamiento del lenguaje natural que se encarga de determinar la polaridad (positiva, negativa, neutral) en los textos en los que se vierten opiniones. Un recurso habitual en los sistemas de análisis de sentimiento son los lexicones de polaridad. Un lexicón de polaridad es un diccionario que asigna un valor predeterminado de polaridad a una palabra. En este trabajo exploramos la posibilidad de generar de manera automática lexicones de polaridad adaptados a un dominio usando representaciones continuas de palabras, en concreto la popular herramienta Word2Vec. Primero mostramos una evaluación cualitativa de la polaridad sobre un pequeño conjunto de palabras, y después mostramos los resultados de nuestra competición en la tarea 12 del SemEval-2015 usando este método.

The automatic analysis of opinions, which usually receives the name of opinion mining or sentiment analysis, has gained a great importance during the last decade. This is mainly due to the overgrown of online content in the Internet. The so-called aspect based opinion mining systems aim to detect the sentiment at “aspect” level (i.e. the precise feature being opinionated in a clause or sentence). In order to detect such aspects it is required some knowledge about the domain under analysis. The vocabulary in different domains may vary, and different words are interesting features in different domains. We aim to generate a list of domain related words and expressions from unlabeled domain texts, in a completely unsupervised way, as a first step to a more complex opinion mining system., El análisis automático de la opinión, que usualmente recibe el nombre minería de opinión o análisis del sentimiento, ha cobrado una gran importancia durante la última década. La minería de opinión basada en aspectos se centra en detectar el sentimiento con respecto a “aspectos” de la entidad examinada (i.e. características o partes concretas evaluadas en una sentencia). De cara a detectar dichos aspectos se requiere una cierta información sobre el dominio o temática del contenido analizado, ya que el vocabulario varía de un dominio a otro. El objetivo de este trabajo es generar de manera automática una lista de aspectos del dominio partiendo de un set de textos sin etiquetar, de manera completamente no supervisada, como primer paso para el desarrollo de un sistema más completo.

This paper presents a system to normalize Spanish tweets, which uses preprocessing rules, a domain-appropriate edit-distance model, and language models to select correction candidates based on context. The system is an improvement on the tool we submitted to the Tweet-Norm 2013 shared task, and results on the task’s test-corpus are above-average. Additionally, we provide a study of the impact for tweet normalization of the different components of the system: rule-based, edit-distance based and statistical., Este artículo presenta un sistema para la normalización de tweets en español, que usa reglas de preproceso, un modelo de distancias de edición adecuado al dominio y modelos de lenguaje para seleccionar candidatos de corrección según el contexto. Se trata de un sistema mejorado basado en el que presentamos en la tarea compartida Tweet-Norm 2013. El sistema obtiene resultados superiores a la media en el corpus de test de la tarea. Presentamos además un estudio del impacto en la normalización de los diferentes componentes del sistema: basados en reglas, en distancia de edición, y estadísticos.

Actualmente existe una gran cantidad de empresas ofreciendo servicios para el análisis de contenido y minería de datos de las redes sociales con el objetivo de realizar análisis de opiniones y gestión de la reputación. Un alto porcentaje de pequeñas y medianas empresas (pymes) ofrecen soluciones específicas a un sector o dominio industrial. Sin embargo, la adquisición de la necesaria tecnología básica para ofrecer tales servicios es demasiado compleja y constituye un sobrecoste demasiado alto para sus limitados recursos. El objetivo del proyecto europeo OpeNER es la reutilización y desarrollo de componentes y recursos para el procesamiento lingüístico que proporcione la tecnología necesaria para su uso industrial y/o académico., Currently there are a many companies offering Content Analytics and Social Internet Mining services for the purposes of Opinion Mining and Reputation Management. A high percentage of Small and Medium Enterprises (SMEs) are active offering niche solutions to specific segments of the market and/or domains. However, acquiring or developing the base qualifying technologies required to enter the market is an expensive undertaking that redirects the already limited resources of SMEs away from offering products and services that the market demands. The main goal of the OpeNER European project is the reuse and repurposing of existing language resources and data sets to provide a set of underlying technologies to the broader industrial and academic community.

Tesis doctoral en Informática realizada por Montse Cuadros y dirigida por Dr. Lluís Padró y Dr. German Rigau. La defensa de la tesis fue en la facultad de Informática de la Universitat Politècnica de Catalunya el día 22 de noviembre de 2011. El tribunal estuvo formado por Dr. Horacio Rodríguez (Universitat Politècnica de Catalunya), Prof. Dr. Piek Vossen (Vrije Universiteit Amsterdam), Dra. Arantza Díaz de Ilarraza (Universidad del País Vasco), Dra. Irene Castellón (Universitat de Barcelona) y Dr. Roberto Navigli (Sapienza University of Rome), que le otorgaron la nota de Sobresaliente Cum Laude., Ph. D. thesis in Computer Science written by Montse Cuadros under the supervision of Dr. Lluís Padró and Dr. German Rigau. The thesis defense was done on 22th November 2011 at the Computer Science Faculty of the Universitat Politècnica de Catalunya. The Doctoral Examination Committee was composed by Dr. Horacio Rodríguez (Universitat Politècnica de Catalunya), Prof. Dr. Piek Vossen (Vrije Universiteit Amsterdam), Dra. Arantza Díaz de Ilarraza (Universidad del País Vasco), Dra. Irene Castellón (Universitat de Barcelona) and Dr. Roberto Navigli (Sapienza University of Rome). The thesis was graded Cum Laude.

This paper presents deepKnowNet, a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method applies a knowledge-based Word Sense Disambiguation algorithm to assign the most appropriate WordNet sense to large sets of topically related words acquired from the web, named TSWEB. This Word Sense Disambiguation algorithm is the personalized PageRank algorithm implemented in UKB. This new method improves by automatic means the current content of WordNet by creating large volumes of new and accurate semantic relations between synsets. KnowNet was our first attempt towards the acquisition of large volumes of semantic relations. However, KnowNet had some limitations that have been overcomed with deepKnowNet. deepKnowNet disambiguates the first hundred words of all Topic Signatures from the web (TSWEB). In this case, the method highlights the most relevant word senses of each Topic Signature and filter out the ones that are not so related to the topic. In fact, the knowledge it contains outperforms any other resource when is empirically evaluated in a common framework based on a similarity task annotated with human judgements, Postprint (published version)

We present a methodology to link domain thesauri to general-domain lexica. This is applied in the framework of the KYOTO project to link the Species2000 thesaurus to the synsets of the English WordNet. Moreover, we study the formalisation of this thesaurus according to the ISO LMF standard and its dialect WordNet-LMF. This conversion will allow Species2000 to communicate with the other resources available in the KYOTO architecture., Peer Reviewed, Postprint (published version)

With the proliferation of applications sharing information represented in multiple ontologies, the development of automatic methods for robust and accurate ontology matching will be crucial to their success. Connecting and merging already existing semantic networks is perhaps one of the most challenging task related to knowledge engineering. This paper presents a new approach for aligning automatically a very large domain ontology of Species to WordNet in the framework of the KYOTO project. The approach relies on the use of knowledge-based Word Sense Disambiguation algorithm which accurately assigns WordNet synsets to the concepts represented in Species 2000., Peer Reviewed, Postprint (published version)

This article presents a new freely available trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia and has been automatically enriched with linguistic information. To our knowledge, this is the largest such corpus that is freely available to the community: In its present version, it contains over 750 million words. The corpora have been annotated with lemma and part of speech information using the open source library FreeLing. Also, they have been sense annotated with the state of the art Word Sense Disambiguation algorithm UKB. As UKB assignsWordNet senses, andWordNet has been aligned across languages via the InterLingual Index, this sort of annotation opens the way to massive explorations in lexical semantics that were not possible before. We present a first attempt at creating a trilingual lexical resource from the sense-tagged Wikipedia corpora, namely, WikiNet. Moreover, we present two by-products of the project that are of use for the NLP community: An open source Java-based parser for Wikipedia pages developed for the construction of the corpus, and the integration of the WSD algorithm UKB in FreeLing., Peer Reviewed, Postprint (published version)

In this paper, we present a brief snapshot of the state of affairs in computational processing of Catalan and the initiatives that are starting to take place in an effort to bring the field a step forward, by making a better and more efficient use of the already existing resources and tools, by bridging the gap between research and market, and by establishing periodical meeting points for the community. In particular, we present the results of the First Workshop on the Computational Processing of Catalan, which succeeded in putting together a fair representation of the research in the area, and received attention from both the industry and the administration. Aside from facilitating communication among researchers and between developers and users, the Workshop provided the organizers with valuable information about existing resources, tools, developers and providers. This information has allowed us to go a step further by setting up a “harvesting” procedure which will hopefully build the seed of a portal-catalogue-observatory of language resources and technologies in Catalan, Peer Reviewed, Postprint (published version)

El proyecto KNOW pretende añadir significado, conocimiento y razonamiento a las tecnologías actuales de Procesamiento del Lenguaje Natural., The KNOW project aims to add meaning, knowledge and reasoning to current Natural Language Processing technologies.

El processament computacional de la llengua abraça qualsevol activitat relacionada amb la creació, gestió i utilització de tecnologia i recursos lingüístics. En el pla científic, aquesta activitat és central en disciplines com ara la lingüística de corpus, l'enginyeria lingüística, o el processament del llenguatge natural escrit o parlat. En el pla quotidià, el processament s'inclou en un ampli ventall d'aplicacions cada cop més habituals: sistemes automàtics d'atenció telefònica, traducció automàtica, etc. La gran majoria d'aquestes aplicacions requereixen eines i recursos lingüístics específics per a cada llengua. Per a llengües amb un mercat ampli, com l'anglès o el castellà, l'oferta de productes i serveis basats en tecnologia lingüística és variada i habitual. Per al cas de llengües com el català, és més difícil trobar productes i serveis que s'ofereixin ja "de fàbrica" amb aquesta tecnologia. Per tal de reflectir l'estat actual de les tecnologies de la llengua aplicades al català, de posar en contacte els membres d'aquesta comunitat, i d'impulsar iniciatives que les potenciïn, el març del 2009 es va celebrar al Palau Robert de Barcelona la primera Jornada del Processament Computacional del Català (JPCC). La Jornada tenia l'objectiu d'esdevenir un punt de trobada i alhora un aparador per als grups de recerca de l'àrea, i encetar el debat sobre com articular la comunitat per tal de potenciar l'ús i el desenvolupament del català tant en la tecnologia lingüística com en els productes i serveis que en depenen. Aquest article presenta un resum del contingut i les conclusions de la Jornada., Peer Reviewed, Postprint (published version)

El processament computacional de la llengua abraça qualsevol activitat relacionada amb la creació, gestió i utilització de tecnologia i recursos lingüístics. En el pla científic, aquesta activitat és central en disciplines com ara la lingüística de corpus, l'enginyeria lingüística, o el processament del llenguatge natural escrit o parlat. En el pla quotidià, s'inclou en un ampli ventall d'aplicacions cada cop més habituals: sistemes automàtics d'atenció telefònica, traducció automàtica, etc. La gran majoria d'aquestes aplicacions requereixen eines i recursos lingüístics específics per a cada llengua. Per a llengües amb un mercat ampli, com l'anglès o el castellà, l'oferta de productes i serveis basats en tecnologia lingüística és variada i habitual. Per al cas de llengües com el català, és més difícil trobar productes i serveis que s'ofereixin ja “de fàbrica” amb aquesta tecnologia. Aquest article presenta una panoràmica de l'estat actual de les tecnologies de la llengua per al català, així com diversos aspectes que avui dia es debaten en el si de la comunitat científica dedicada al processament del llenguatge natural parlat i escrit., Peer Reviewed, Postprint (published version)

Presentamos las conclusiones de la primera Jornada del Processament Computacional del Català, celebrado en Barcelona en marzo del 2009. We present the conclusions of the first Jornada del Processament Computacional del Català, held in Barcelona on March 2009, Peer Reviewed, Postprint (published version)

El proyecto KNOW pretende añadir significado, conocimiento y razonamiento a las tecnologías actuales de Procesamiento del Lenguaje Natural., Postprint (published version)

Este artículo presenta un nuevo método totalmente automático de construcción de bases de conocimiento muy densas y precisas a partir de recursos semánticos preexistentes. Básicamente, el método usa un algoritmo de Interpretación Semántica de las palabras preciso y de amplia cobertura para asignar el sentido más apropiado a grandes conjuntos de palabras de un mismo tópico que han sido obtenidas de la web. KnowNet, la base de conocimiento resultante que conecta grandes conjuntos de conceptos semánticamente relacionados es un paso importante hacia la adquisición automática de conocimiento a partir de corpus. De hecho, KnowNet es varias veces más grande que cualquier otro recurso de conocimiento disponible que codifique relaciones entre sentidos, y el conocimiento que KnowNet contiene supera cualquier otro recurso cuando es empíricamente evaluado en un marco multilingüe común., This paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate knowledge-based Word Sense Disambiguation algorithm to assign the most appropriate senses to large sets of topically related words acquired from the web. KnowNet, the resulting knowledge-base which connects large sets of semantically-related concepts is a major step towards the autonomous acquisition of knowledge from raw corpora. In fact, KnowNet is several times larger than any available knowledge resource encoding relations between synsets, and the knowledge KnowNet contains outperform any other resource when is empirically evaluated in a common multilingual framework.

Este artículo presenta el resultado del estudio de un amplio conjunto de bases de conocimiento multilíngües actualmente disponibles que pueden ser de interés para un gran número de tareas de procesamiento semántico a gran escala. El estudio incluye una amplia gama de recursos derivados de forma manual y automática para el inglés y castellano. Con ello pretendemos mostrar una imagen clara de su estado actual. Para establecer una comparación justa y neutral, la calidad de cada recurso se ha evaluado indirectamente usando el mismo método en dos tareas de resolución de la ambigüedad semántica de las palabras (WSD, del inglés Word Sense Disambiguation). En concreto, las tareas de muestra léxica del inglés del Senseval-3., This report presents a wide survey of publicly available multilingual Knowledge Resources that could be of interest for wide–coverage semantic processing tasks. We also include an empirical evaluation in a multilingual scenario of the relative quality of some of these large-scale knowledge resources. The study includes a wide range of manually and automatically derived large-scale knowledge resources for English and Spanish. In order to establish a fair and neutral comparison, the quality of each knowledge resource is indirectly evaluated using the same method on a Word Sense Disambiguation task (Senseval-3 English Lexical Sample Task).

Este artículo presenta un nuevo método totalmente automático de construcción de bases de conocimiento muy densas y precisas a partir de recursos semánticos preexistentes. Básicamente, el método usa un algoritmo de Interpretación Semántica de las palabras preciso y de amplia cobertura para asignar el sentido mas apropiado a grandes conjuntos de palabras de un mismo tópico que han sido obtenidas de la web. KnowNet, la base de conocimiento resultante que conecta grandes conjuntos de conceptos semánticamente relacionados es un paso importante hacia la adquisición automática de conocimiento a partir de corpus. De hecho, KnowNet es varias veces mas grande que cualquier otro recurso de conocimiento disponible que codifique relaciones entre sentidos, y el conocimiento que KnowNet contiene supera cualquier otro recurso cuando es empíricamente evaluado en un marco multilingüe común. This paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate knowledge-based Word Sense Disambiguation Algorithm to assign the most appropriate senses to large sets of topically related words acquired from the web. KnowNet, the resulting knowledge-base which connects large sets of semantically-related concepts is a major step towards the autonomous acquisition of knowledge from raw corpora. In fact, KnowNet is several times larger than any available knowledge resource encoding relations between synsets, and the knowledge KnowNet contains outperform any other resource when is empirically evaluated in a common multilingual framework., Peer Reviewed, Postprint (published version)

This paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate knowledge-based Word Sense Disambiguation algorithm to assign the most appropriate senses to large sets of topically related words acquired from the web. KnowNet, the resulting knowledge-base which connects large sets of semantically related concepts is a major step towards the autonomous acquisition of knowledge from raw corpora. In fact, KnowNet is several times larger than any available knowledge resource encoding relations between synsets, and the knowledge KnowNet contains outperform any other resource when is empirically evaluated in a common framework., Peer Reviewed, Postprint (author's final draft)

This paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate nowledge-based Word Sense Disambiguation algorithm to assign the most appropriate senses to large sets of topically related words acquired from the web. KnowNet, the resulting knowledge-base which connects large sets of semantically-related concepts is a major step towards the autonomous acquisition of knowledge from raw corpora. In fact, KnowNet is several times larger than any available knowledge resource encoding relations between synsets, and the knowledge KnowNet contains outperform any other resource when is empirically evaluated in a common multilingual framework., Peer Reviewed, Preprint (author's version)

Este artículo presenta el resultado del estudio de un amplio conjunto de bases de conocimiento multilingües actualmente disponibles que pueden ser de interés para un gran número de tareas de procesamiento semántico a gran escala. El estudio incluye una amplia gama de recursos derivados de forma manual y automática para el inglés y castellano. Con ello pretendemos mostrar una imagen clara de su estado actual. Para establecer una comparación justa y neutral, la calidad de cada recurso se ha evaluado indirectamente usando el mismo método en dos tareas de resolución de la ambigüedad semántica de las palabras (WSD, del inglés Word Sense Disambiguation). En concreto, las tareas de muestra léxica del ingles del Senseval-3. --- This report presents a wide survey of publicly available multilingual Knowledge Resources that could be of interest for wide–coverage semantic processing tasks. We also include an empirical evaluation in a multilingual scenario of the relative quality of some of these large-scale knowledge resources. The study includes a wide range of manually and automatically derived large-scale knowledge resources for English and Spanish. In order to establish a fair and neutral comparison, the quality of each knowledge resource is indirectly evaluated using the same method on a Word Sense Disambiguation task (Senseval-3 English Lexical Sample Task)., Peer Reviewed, Postprint (published version)

This paper presents an empirical evaluation in a multilingual scenario of the semantic knowledge present on publicly available large-scale knowledge resources. The study covers a wide range of manually and automatically derived large-scale knowledge resources for English and Spanish. In order to establish a fair and neutral comparison, the knowledge resources are evaluated using the same method on two Word Sense Disambiguation tasks (Senseval-3 English and Spanish Lexical Sample Tasks). First, this study empirically demonstrates that the combination of the knowledge contained in these resources surpass the most frequent sense classi er for English. Second, we also show that this large-scale topical knowledge acquired from one language can be successfully ported to other languages., Peer Reviewed, Postprint (author’s final draft)

This task tries to establish the relative quality of available semantic resources (derived by manual or automatic means). The quality of each large-scale knowledge resource is indirectly evaluated on a Word Sense Disambiguation task. In particular, we use Senseval-3 and SemEval-2007 English Lexical Sample tasks as evaluation bechmarks to evaluate the relative quality of each resource. Furthermore, trying to be as neutral as possible with respect the knowledge bases studied, we apply systematically the same disambiguation method to all the resources. A completely different behaviour is observed on both lexical data sets (Senseval-3 and SemEval-2007)., Peer Reviewed, Postprint (author’s final draft)