Program 2017-2018
IKASGAIA MODULE |
ECTS | HIZKUNTZA LANGUAGE |
Irakaslea en teacher en |
Irakaslea eu teacher eu |
1.LAUHILEKOA - SEMESTER1 | ||||
Hizkuntzaren tratamendu automatikorako hizkuntzalaritza (HAP2) Giza hizkuntzaren oinarrizko maila linguistikoen sarrera: fonologia, morfologia, sintaxia, semantika etapragmatika. Hizkuntzalaritza tradizionalaren ikuspegitik aztertuko da, baina Hizkuntzaren Teknologiaren testuinguruan. 1. gaia: GIZA HIZKUNTZA: HIZKUNTZAK VS HIZKUNTZA Linguistics for natural language processing (LAP2) The course presents an introduction to the fundamental sof language in phonology, morphology, syntax, semantics,and pragmatics. It addresses these Themes from the perspective of traditional linguistics but in the context of Language Technologies. Theme 1: Human language: The languages versus The Language. |
6 H | Euskara - English (LCT) |
Itziar San Martín | Maxux Aranzabe + |
Hizkuntza prozesatzeko programazio-teknikak (HAP5) Hizkuntzaren prozesamenduan erabiltzen direnoinarrizko software-tresnak ikasleak ondo ezagutzea daIkastaroaren helburua. Python programazio-lengoaiaren oinarrizko maila landuko da. Informazio linguistikoa adierazteko estandar erabilienak aztertuko dira. Etagainera, ikasleei prozesaketa banatuari buruz hainbatalde praktiko azalduko dira. 1. gaia: Programazioaren oinarrizko kontzeptuak Programming techniques for Natural Language processing (LAP5) The aim of the course is to familiarize students with basic software tools used in natural language processing.The course includes a brief introduction to the Python programming language, a review of the standard techniques of representing linguistic information, and an overview of practical issues regarding distributed processing. Theme 1: Basic programming concepts. |
6 H | Euskara - English (LCT) |
Kepa Sarasola + | Kepa Sarasola + |
Metodo estatistikoak eta Testu-corpusak (HAP1) Irakasgaia bi zatitan banatzen da: i) Hizkuntzaren prozesaketan beharrezkoak diren oinarri estatistikoen sarrera. Estatistika deskribatzailearen zein inferentzialaren inguruko hainbat alderdi landukodira bertan. 1. Gaia: Estatistikaren oinarriak. Statistical Methods and Corpus Linguistics (LAP1)
The course is divided into two parts: i) Introduction to fundamental statistics for natural language processing. Concepts of descriptive and inferential statistics.
ii) Survey of the field of Corpus-based Natural LanguageProcessing and Corpus Linguistics. Ways of representing linguistic information and exploitation. Annotation on different linguistic levels: morphology, syntax, semantic,etc. Main approaches to corpus-based analysis, including distributional and pattern-based techniques. As examples,this section will use leading projects for Basque,Catalan, Spanish and English. Theme 1:Fundamentals of statistics. |
6 D | Euskara - English (LCT) |
Aitor Soroa + | Aitor Soroa + |
Automata, Computability, and Complexity Theory (LAP6)
In this course students will study the theoretical foundations of computer science, i.e., the theory ofcomputation. The course has two parts:
i) Automata Theory. Abstract models called automata are at the core of all computers. This part of the course provides a close examination of automata, formal languages and grammars, and classifies them according to the Chomsky Hierarchy. Theme 1:Mathematical concepts and basic formal reasoning. Sets, relations, functions, character strings, and languages. Demonstrations. |
9H | English (LCT) | Maite Oronoz + | |
Hizkuntzalaritza konputazionala, morfologia eta sintaxia (HAP3) Ikastaroak bi helburu nagusi ditu: a) morfologiaren tratamendu konputazionalerako oinarrizko kontzeptuak eta ereduak aurkeztea (adierazpen erregularrak, automatafinituak, morfologia konputazionala). Ikastaroan zehar,ikasleak Foma, egoera finituko tresna aske eta irekia)erabiltzeko aukera izango du. Morfologia aberatseko hizkuntzak landuko dira bereziki. b) Sintaxiaren tratamendurako formalismo konputazionalen aurkezpena.Horien artean testuingururik gabeko gramatikak, egoera finituko sintaxia, eta eredu sintaktiko probabilistikoak. Lexical Functional Grammar (LFG), Head-driven Phrase Structure Grammar (HPSG) eta Constraint Grammar bezalako formalismoak azalduko dira. Tagging, Chunking eta Parsing (analisi sintaktikoa) prozesuenikuspegi orokorra emango da. 1. gaia: Morfologia Konputazionalerako formalismoak Computational Linguistics, Morphology and Syntax (LAP3) The course has a twofold goal: i) To present the basic concepts and computational models for the treatment of morphology (regular expressions, finite automata, computational morphology). During the course the student will have the opportunity to practice with foma, a free and open sourcefinite-state toolkit. ii) To present the computational formalisms for the treatment of syntax: N-grams, basic context-free grammars, probabilistic context-free grammars, and dependency syntax. The course will also examine the implementation of formal grammars providingan overview of frameworks, such as Categorical Grammars(CG), Lexical Functional Grammars (LFG), and Head-driven Phrase Structure Grammar (HPSG). The Constraint Grammar Formalism will be presented in detail and leading projects for Basque and Finnish will be used for illustration. In addition, the course will overviewtagging, chunking and parsing processes. Specialattention will be paid to the treatment of Basque, giventhat it is a morphologically rich language. Theme 1:Dependency Grammars |
9 D | Euskara - English (LCT) |
Koldo Gojenola + | Koldo Gojenola + |
Terminologia eta testu espezializatuak (HAP16) Testu espezializatuen azterketak lotura zuzena duhizkuntzaren azterketa eta prozesamendu automatikoarekin, lan automatikoaren helburua oso maiztestu espezializatuak baitira: errazago formalizatzen dira zenbait testu orokor mota baino eta profesionalenedo adituen arteko komunikazioa dagoen guztietan ekoizten dira. Egun informazioaren gizartean bizi garela esan ohi da eta jakintza espezializatuarekin lotutako espezializazio maila desberdinetako testuek garrantzi handia hartu dute gizartean. Hortaz, hizkuntzare ntratamendu automatikoan aditua izan nahi duenak maiz lanegin beharko du testu espezializatuen gainean eta, beraz, ezagutu beharko ditu testu horien bereizgarriak. 1. gaia: Komunikazio orokorra eta komunikazioespezializatua: testu berezituak eta terminologia hizkuntza naturalean |
4.5H | Euskara | Xabier Artola + | |
Artificial Intelligence and Advanced User Interaction (LAP13)
The birth of Computer Science occurred in an interdisciplinary historical context, closely related to the idea of whether machines could be considered intelligent: Cognitive Science and Artificial Intelligence irrupted at the intersection of linguistics, psychology and theoretical computerscience. This course aims at providing students with the tools required to identify the origins of the current research in Natural Language Processing and Computational Linguistics. As an application of the knowledge acquired in Artificial intelligence, user-model-based adaptive interfaces will be studied. In addition, the methodologies and development environments for building intelligent user-adapted systems will beaddressed. 1: Introduction to Artificial Intelligence |
4.5H | English (LCT) | Mikel Larrañaga + | |
2.LAUHILEKOA - SEMESTER 2 | ||||
Hizkuntz ingeniaritzaren arloko aplikazioak (HAP9) Kurtsoak hiru zati desberdinez osatuta egongo da: i)Itzulpen automatikoa: kurtsoan itzulpen automatikorako paradigma desberdinak zehaztasunez aztertuko dira, etaparadigmen konbinazioen beharra eta konbinazio horienmota desberdinak ikusiko dira. Horretaz gain, ikasleek kasu praktikoak eta erabilgarri dagoen ingeles-euskarabenetako sistema bat aztertzeko aukera izango dute; ii)Hezkuntza eta Hizkuntzaren Prozesamendua (HP):kurtsoaren bigarren zatian HP tresnak eta baliabideenerabilera bigarren hizkuntzaren ikaskuntzan aztertukodira, baita hauen erabilera gai orokorrenikasketa-prozesuan ere; iii) Web-bilaketa eta Testu-Meatzaritza: zati honetan web-bilaketaz eta informazio berreskurapenaz gain, informazio erauzketarako bestelako testu-meatzaritzarako metodoak ere aztertuko dira; baita testu askea analizatu eta prozesatzeko metodoak eta hauen erabilera zenbait aplikazio zientifiko zein komertzialetan ere.Informazioaren berreskurapenaren oinarrizko kontzeptuekin hasiko gara, testuetan oinarritutako berreskurapen sistemen oinarrizko algoritmoak azalduz,ikerkuntzaren mugetaraino iritsi arte. 1. gaia: Hizkuntzen ikaskuntza, HP eta tutore adimendunak Aplications on Language Technologies (LAP9) The course contains three parts: i) Machine translation: Existing MT paradigms will bepresented in detail. The student will have the opportunity of studying real cases for a SMT system from English to Basque and for doing practice projects. In addition, the course will overview the need for and practical ways of combining classical paradigms. Theme 1: Language learning, NLP and intelligent tutors. Study of thetechnologies of instruction and learning; intelligent computerized learning environments. |
9 H | Euskara - English (LCT) |
Gorka Labaka + | Montse Maritxalar + |
Logika,semantika eta pragmatika konputazionala (HAP4) ..........
Computational Logic,Semantics and Pragmatics (LAP4) The course coversthe following topics: i) Computational semantics. The goal of this part ofthe course is to present the basic concepts insemantics, covering the issues related tosyntax-semantics interface: formal representation of the meaning of a sentence, computational approaches forformal semantics, essential resources needed for the computational treatment of semantics, and fundamental statistical approaches to word sense disambiguation. ii)Computational pragmatics and Discourse covering. This part covers subjects like: a) the study of theories that formalize the rhetorical structure of a text (e.g. RST),b) the problem of coreference and the identification of coreferential chains, and c) constructing models of speech acts in dialogue. Theme 1:Automated reasoning in propositional, first-order,temporal and description logic. |
9 H | Euskara - English (LCT) |
Arantza Diaz de Ilarraza + | Arantza Diaz de Ilarraza + |
Corpusetan oinarritutako semantika konputazionala(HAP10) Ikastaro honek ondoko helburuak dauzka: i) Analisi semantikoan erabiltzen diren baliabide nagusien azterketa. Baliabide horien artean ezagutza base lexikosemantiko orokorrak daude (adibidez, WordNet, Multilingual Central Repository, VerbNet, FrameNet,Ontonotes edo DBpedia), baina baita domeinu espezifikoetakoak ere (adibidez medikuntzako UMLS). Baliabide horietako informazioarekin etiketatutako corpusak ere aztertuko dira. Hainbat hizkuntzakobaliabideak ikusiko dira, ingelesa eta euskara barne.ii) Hitzen esanahiarekin lan egiteko teknika aurreratuaklanduko dira, antzekotasuna eta desanbiguazioa barne.Alde batetik desanbiguaziorako algoritmo nagusiak sakonean ikusiko dira, bai edukidun hitzei dagozkionak (Hitzen Adiera Desanbiguazioa), baita entitateei dagozkionak ere (Izendun Entitateen Desanbiguazioa). Bestetik hitzen eta testuen arteko antzekotasun semantikoa (Testu-Antzekotasun Semantikoa). 1. gaia: Baliabide semantikoak Corpus-based computational semantics (LAP10)
This course has the following objectives:
i) To review the main resources used in semantic analysis. The resources include general lexical repositories like WordNet, Multilingual Central Repository, VerbNet, FrameNet, Ontonotes and DbPedia, and also somedomain-specific repositories. The course also reviews related corpora annotated (manually and automatically) with semantic information. We will cover resources in English, Basque and other languages. Theme 1: Semantic resources. |
9 H | Euskara - English (LCT) |
Eneko Agirre + | Eneko Agirre + |
Advanced methods for corpus analysis (LAP11)
The main objective of this course is to analyze the fundamental methods and techniques for the advanced treatment of large volumes of textual data (e.g. text onthe Internet). We will review three main approaches: statistical methods, machine learning methods, andknowledge-based methods.
Theme 1:Introduction to corpus analysis. |
4.5H | English (LCT) | German Rigau + | |
Speech Processing and speech technologies (LAP12) The course presents the fundamentals of speech processing techniques,as well as introducing students to state-of-the-artmethodologies, software toolkits, and resources used in speech technology. The course also reviews the differentfields of speech processing, including speech synthesisand speech and speaker recognition. Theme 1: Basic concepts about signal. |
9 H | English (LCT) | Eva Navas + | |
Lengoaia naturalaren ikerkuntza eta prozesamendua: dokumentazioa eta komunikazioa (HAP15) Hizkuntza-teknologien arloko ikerketa zientifiko bati buruzko dokumentazioari aurre egiteko behar diren oinarri metodologikoak lantzen dira. Oinarri metodologiko horiek bereziki jarduera praktikoen bidez jorratuko dira. 1. gaia: Sarrera Hizkuntzen Teknologiari: aplikazioak eta berauen garapenerako estrategia. |
3 H | Euskara - English (LCT) | Olatz Arregi + | |
This course focuses on a range of techniques inspired by artificial intelligence and classical statistics. In the last decade, these fields have experienced a boom, particularly with regard to problems related to largevolumes of data for which the mathematical, statistical,or classical operations research have been unable to offer effective or efficient solutions. The applications of machine learning cover fields as diverse as bioinformatics, finance, and natural language. The studentwill study the most common major techniques for data mining, as well as acquire skills in the use of free software packages that implement these techniques. This will be linked to the study and demonstration of real applications of these techniques.
|
4.5H | English (LCT) | Basilio Sierra + | |
Hizkuntza-teknologien mintegia. Deep learning. (HAP18) Deep Learning neural network models have been successfully applied to natural language processing. These models are able to infer a continuous representation for words and sentences, instead of using hand-engineered features as in other machine learning approaches. The seminar will introduce the main deep learning models used in natural language processing, allowing the students to gain hands-on understanding and implementation of understanding and implementation of them in Tensorflow. Topics
Prerequisite. Basic programming experience, a university-level course in computer science and experience in Python. Basic math skills (algebra or pre-calculus) are also needed.
Seminar on Language Technologies. Deep learning. (LAP18) Deep Learning neural network models have been successfully applied to natural language processing. These models are able to infer a continuous representation for words and sentences, instead of using hand-engineered features as in other machine learning approaches. The seminar will introduce the main deep learning models used in natural language processing, allowing the students to gain hands-on understanding and implementation of them in Tensorflow . Topics
Prerequisite. Basic programming experience, a university-level course in computer science and experience in Python. Basic math skills (algebra or pre-calculus) are also needed.
|
4.5 H | English (LCT) | Eneko Agirre + | Eneko Agirre + |
Master-tesia / Master's Thesis |
30 |
D : Derrigorrezkoak / Compulsory H : Hautazkoak / Elective