Exploring Semantic Textual Similarity

[EN]Measuring semantic similarity and relatedness between textual items (words, sentences, paragraphs or even documents) is a very important research area in Natural Language Processing (NLP). In fact, it has many practical applications in other NLP tasks. For instance, Word Sense Disambiguation, Textual Entailment, Paraphrase detection, Machine Translation, Summarization and other related tasks such as Information Retrieval or Question Answering. In this masther thesis we study di erent approaches to compute the semantic similarity between textual items. In the framework of the european PATHS project1, we also evaluate a knowledge-base method on a dataset of cultural item descriptions. Additionaly, we describe the work carried out for the Semantic Textual Similarity (STS) shared task of SemEval-2012. This work has involved supporting the creation of datasets for similarity tasks, as well as the organization of the task itself.

Koherentziazko diskurtso erlazioen detekzio automatikoa patroien bidez, XMLko erlazio-egiturak oinarri hartuta

[EU]Hizkuntzaren prozesamenduan testu koherenteetan kausa taldeko erlazioak (KAUSA, ONDORIOA eta HELBURUA) automatikoki hautematea eta bereiztea erabilgarria da galdera-erantzun automatikoko sistemak eraikitzerako orduan. Horretarako Egitura Erretorikoaren Teoria (Rhetorical Structure Theory, aurrerantzean RST) eta bere erlazioak erabiliko ditugu, corpus bezala RST Treebank -a (Iruskieta et al., 2013) hartuta, zientziako laburpen-testuz osatutako corpusa, hain zuzen ere. Corpus hori XML formatuan deskargatu eta hortik XPATH tresnaren bidez informazio garrantzitsuena eskuratzen dugu. Lan honek 3 helburu nagusi ditu: lehendabizi, kausa taldeko erlazioak elkarren artean bereiztea, bigarrenez, kausa taldeko erlazio hauek beste erlazio guztiekin bereiztea, eta azkenik, EBALUAZIOA eta INTERPRETAZIOA erlazioak bereiztea sentimendu analisian aplikatu ahal izateko. Ataza horiek egiteko, RhetDB tresnarekin eskuratu diren patroi ensaguratsuenak erabili eta bi aplikazio garatu ditugu. Alde batetik, bilatu nahi ditugun patroiak adierazi eta erlazio-egitura duen edonolako testuetan bilaketak egiten dituen bilatzailea, eta bestetik, patroi esanguratsuenak emanda erlazioak etiketatzen dituen etiketatzailea. Bi aplikazio hauek gainera, ahalik eta modu parametrizagarrienean erabiltzeko garatu ditugu, kodea aldatu gabe edonork erabili ahal izateko antzeko atazak egiteko. Etiketatzaileak ebaluatu ondoren, identifikatzeko erlaziorik errazena HELBURUA erlazioa dela ikusi dugu eta KAUSA eta ONDORIOA bereizteko arazo gehiago dauzkagula ere ondorioztatu dugu. Modu berean, EBALUAZIOA eta INTERPRETAZIOA ere elkarren artean bereiz dezakegula ikusi dugu.

Creación de neologismos en euskera: Análisis descriptivo de la terminología de la odontología en lengua vasca y propuestas para la formación de términos en los ámbitos de especialidad.

450 p.

A methodology for the semiautomatic annotation of EPEC-RolSem, a basque corpus labeled at predicative level following the PropBank-Verb Net model

In this article we describe the methodology developed for the semiautomatic annotation of EPEC-RolSem, a Basque corpus labeled at predicate level following the PropBank-VerbNet model. The methodology presented is the product of detailed theoretical study of the semantic nature of verbs in Basque and of their similarities and differences with verbs in other languages. As part of the proposed methodology, we are creating a Basque lexicon on the PropBank-VerbNet model that we have named the Basque Verb Index (BVI). Our work thus dovetails the general trend toward building lexicons from tagged corpora that is clear in work conducted for other languages. EPEC-RolSem and BVI are two important resources for the computational semantic processing of Basque; as far as the authors are aware, they are also the first resources of their kind developed for Basque. In addition, each entry in BVI is linked to the corresponding verb-entry in well-known resources like PropBank, VerbNet, WordNet, Levin’s Classification and FrameNet. We have also implemented several automatic processes to aid in creating and annotating the BVI, including processes designed to facilitate the task of manual annotation.

Pertsonaia protagonista femeninoen ezaugarriak eta bilakaera euskal narratiba garaikidean

361 p.

Assisting blog publication: annotation, model transformation, and crossblogging techniques

Although blogs exist from the beginning of the Internet, their use has considerablybeen increased in the last decade. Nowadays, they are ready for being used bya broad range of people. From teenagers to multinationals, everyone can have aglobal communication space.Companies know blogs are a valuable publicity tool to share information withthe participants, and the importance of creating consumer communities aroundthem: participants come together to exchange ideas, review and recommend newproducts, and even support each other. Also, companies can use blogs for differentpurposes, such as a content management system to manage the content of websites,a bulletin board to support communication and document sharing in teams,an instrument in marketing to communicate with Internet users, or a KnowledgeManagement Tool. However, an increasing number of blog content do not findtheir source in the personal experiences of the writer. Thus, the information cancurrently be kept in the user¿s desktop documents, in the companies¿ catalogues,or in another blogs. Although the gap between blog and data source can be manuallytraversed in a manual coding, this is a cumbersome task that defeats the blog¿seasiness principle. Moreover, depending on the quantity of information and itscharacterisation (i.e., structured content, unstructured content, etc.), an automaticapproach can be more effective.Based on these observations, the aim of this dissertation is to assist blog publicationthrough annotation, model transformation and crossblogging techniques.These techniques have been implemented to give rise to Blogouse, Catablog, andBlogUnion. These tools strive to improve the publication process considering theaforementioned data sources.

Open Personalization: Involving Third Parties in Improving the User Experience of Websites

Traditional software development captures the user needs during the requirement analysis. The Web makes this endeavour even harder due to the difficulty to determine who these users are. In an attempt to tackle the heterogeneity of the user base, Web Personalization techniques are proposed to guide the users’ experience. In addition, Open Innovation allows organisations to look beyond their internal resources to develop new products or improve existing processes. This thesis sits in between by introducing Open Personalization as a means to incorporate actors other than webmasters in the personalization of web applications. The aim is to provide the technological basis that builds up a trusty environment for webmasters and companion actors to collaborate, i.e. "an architecture of participation". Such architecture very much depends on these actors’ profile. This work tackles three profiles (i.e. software partners, hobby programmers and end users), and proposes three "architectures of participation" tuned for each profile. Each architecture rests on different technologies: a .NET annotation library based on Inversion of Control for software partners, a Modding Interface in JavaScript for hobby programmers, and finally, a domain specific language for end-users. Proof-of-concept implementations are available for the three cases while a quantitative evaluation is conducted for the domain specific language.

Criterios para la aplicación de coeficientes modificativos de la curva S-N de fatiga

[ES]Este Trabajo de Fin de Grado tiene como objeto crear un programa que sirva como herramienta para los cálculos en las propiedades a fatiga de una pieza. El conjunto del trabajo se centra en su creación mediante la herramienta Excel. El programa cuenta con tres diferentes pestañas: una para los datos que debe introducir el usuario, otra correspondiente a los cálculos y por último una en la que aparecen los resultados. El usuario debe conocer las propiedades de la probeta del material a ensayar, así como el rango de ciclos en el cual se va a trabajar (siempre en un rango de ciclos medio alto). A partir de estas informaciones de la probeta, y gracias a la curva de Basquin y la ecuación de Marin, el programa será capaz de obtener la curva de resistencia a fatiga correspondiente para la pieza. Se incluyen también casos especiales en los que se realicen tratamientos mecánicos de mejora, con una tensión límite del proceso. Para obtener la curva S-N de la pieza se pedirá información en la pestaña de interfaz con el usuario sobre distintas propiedades de la pieza, que permitan así calcular los valores de los coeficientes de Marín gracias a la base de datos que contiene el programa. El usuario tiene también la opción de introducir él mismo los valores de los coeficientes para así obtener una curva que se aproxime más a sus resultados experimentales. En resumen, la función del programa es la de ser una calculadora de la resistencia fatiga de la pieza a partir de los datos que se disponen de la probeta.