Subject
Applications (I): Understanding NLP
General details of the subject
- Mode
- Face-to-face degree course
- Language
- English
Description and contextualization of the subject
El objetivo del curso es introducir el Procesamiento del Lenguaje Natural (PLN) a partir de aplicaciones ampliamente extendidas tanto en investigación como en la industria. El contenido constará de técnicas básicas de PLN: clasificación de documentos, técnicas que etiquetado secuencial para extraer opiniones, uso de representaciones vectoriales de palabras (word embeddings), normalización y pre-procesamiento de textos. Además, se analizará el papel de la traducción automática en el ámbito profesional y no profesional, atendiendo en particular al proceso de posedición. El curso tendrá un enfoque práctico basado en ejercicios mediante herramientas de software para el aprendizaje automático profundo (deep learning) utilizadas habitualmente en PLN.Teaching staff
Name | Institution | Category | Doctor | Teaching profile | Area | |
---|---|---|---|---|---|---|
AGERRI GASCON, RODRIGO | University of the Basque Country | Investigador Ramón Y Cajal | Doctor | Not bilingual | ** n o c o n s t a e l a r e a * ó " á r e a p r o v i s i o n a l" | rodrigo.agerri@ehu.eus |
ARANBERRI MONASTERIO, NORA | University of the Basque Country | Profesorado Agregado | Doctor | Bilingual | Translation and Interpretation | nora.aranberri@ehu.eus |
Competencies
Name | Weight |
---|---|
Ability to apply existing NLP multilingual tools (morphological, syntactic and semantic taggers). | 33.0 % |
Ability to understand the main characteristics of human language which made NLP processing such a challenging endeavor. | 33.0 % |
Ability to use existing applications in human language technology. | 33.0 % |
Study types
Type | Face-to-face hours | Non face-to-face hours | Total hours |
---|---|---|---|
Lecture-based | 10 | 15 | 25 |
Applied laboratory-based groups | 20 | 30 | 50 |
Training activities
Name | Hours | Percentage of classroom teaching |
---|---|---|
Computer work practice, laboratory, site visits, field trips, external visits | 50.0 | 40 % |
Lectures | 25.0 | 40 % |
Assessment systems
Name | Minimum weighting | Maximum weighting |
---|---|---|
Portfolio | 20.0 % | 20.0 % |
Practical tasks | 40.0 % | 40.0 % |
Presentations | 20.0 % | 20.0 % |
Written examination | 20.0 % | 20.0 % |
Learning outcomes of the subject
Being able to use, design and do research on NLP applications based on document classification and sequence labeling, from a multilingual and multi-domain (news, social networks) point of view.To identify the required linguistic resources in order to adapt NLP applications for our own needs.
Learning to use various tools and APIs for NLP and Machine Translation.
Being able to understand the role of post-edition when applying technology based on Machine Translation.
Autonomy in order to solve practical problems by applying NLP technology.
Temary
1. Introducción al PLN a través de casos de uso prácticos y aplicaciones (Traducción Automática, Análisis de Opiniones).2. Clasificación de documentos multilingüe: Detección de sentimiento y noticias falsas (fake news) en noticias y redes sociales.
3. Etiquetado Secuencial para análisis de opiniones y de sentimientos.
4. La post-edición la evaluación de sistemas de Traducción Automática.
Bibliography
Compulsory materials
Bing Liu. Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012. https://www.cs.uic.edu/~liub/FBS/SentimentAnalysis-and-OpinionMining.htmlNatural Language Processing in Python (http://www.nltk.org/book)
O¿Brien, S., Balling, L. W., Carl, M., Simar, M. and Specia, L. 2014. Post-editing of Machine Translation. Cambridge Scholars Publishing.