nireEHU Subject
Applications (I): Understanding NLP
General details of the subject
- Mode
- Face-to-face degree course
- Language
- English
Description and contextualization of the subject
This course will introduce the most commonly used techniques to build applications based on NLP. Thus, the attendees will learn how to apply techniques such as document classification, sequence labeling, as well as vector-based word representations (embeddings) and pretrained language models for core applications such as Opinion Mining, Named Entity Recognition or Fake News Detection.The course will have a practical focus (laboratories and practical tasks) learning to use readily available NLP toolkits (Spacy, Flair, Transformers, etc.) based on machine and deep learning in a multilingual and multi-domain setting. The aim is to acquire the required autonomy to solve practical problems by applying and developing technology based on Natural Language Processing.
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 |
Competencies
| Name | Weight |
|---|---|
| Capacidad de aplicar las herramientas existentes para el procesamiento de diferentes lenguas (analizadores morfológicos, sintácticos, semánticos). | 20.0 % |
| Capacidad de comprensión de las características del lenguaje humano que hacen difícil su tratamiento automático. | 20.0 % |
| Capacidad de utilizar las aplicaciones existentes en el área de la tecnología de la lengua. | 20.0 % |
| Capacidad de investigar en el diseño de sistemas de procesamiento de lenguaje. | 20.0 % |
| Capacidad de relacionar los métodos empíricos más relevantes para la investigación en las tecnologías de la lengua | 20.0 % |
Study types
| Type | Face-to-face hours | Non face-to-face hours | Total hours |
|---|---|---|---|
| Lecture-based | 10 | 15 | 25 |
| Applied computer-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 (problems) | 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.
Autonomy in order to solve practical problems by applying NLP technology.
Ability to understand the main characteristics of human language which made NLP processing such a
challenging endeavor.
Ordinary call: orientations and renunciation
This course follows continuous evaluation and the activities required are the ones listed above. Any student wishing to change the module shall speak to the master director.Extraordinary call: orientations and renunciation
For extraordinary evaluation a written exam (80%) and a final project covering the syllabus of the module (20%) will be required.Temary
1. Introduction to NLP: Practical Applications.2. Multilingual Text Classification: Sentiment Analysis, Fake News, Stance and Propaganda detection in news and social networks.
3. Sequence Labeling: Named Entity Recognition, Contextual Lemmatization, Aspect Based Sentiment Analysis (ABSA).
4. Reformulating Sequence Labelling tasks.
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.
Basic bibliography
D. Jurafsky and J.H. Martin. Speech and Language Processing, 3rd edition. https://web.stanford.edu/~jurafsky/slp3/ed3book_dec302020.pdfBing Liu. Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012. https://www.cs.uic.edu/~liub/FBS/SentimentAnalysis-and-OpinionMining.html
Flair: A state of the art NLP framework (https://github.com/flairNLP/flair)
Spacy: Industrial Strength Natural Language Processing (https://spacy.io/)
Huggingface Transformers (https://huggingface.co/transformers/)
Natural Language Processing in Python (http://www.nltk.org/book)
It was not possible to load the content, please try again later. In case the problem persists contact CAU (Phone: 916014400 / E-mail: cau@ehu.eus / Website: https://lagun.ehu.eus).