Créditos
4.5
Tipos
- MDS: Optativa
- MAI: Optativa
Requisitos
Esta asignatura no tiene requisitos
, pero tiene capacidades previas
Departamento
CS;TSC
Profesorado
Responsable
- Anna Sallés Rius (anna.salles@upc.edu)
Horas semanales
Teoría
2
Problemas
1
Laboratorio
0
Aprendizaje dirigido
0
Aprendizaje autónomo
5.65
Competencias
Genéricas
Académicas
Profesionales
Trabajo en equipo
Uso solvente de los recursos de información
Razonamiento
Analisis y sintesis
Básicas
Objetivos
-
Learning the current trends of Human Language Engineering and further challenges.
Competencias relacionadas: CEA5, CEA7, CG1, CB9, CEA3, CT4, -
Learning knowledge and tools required to develop Human Language Engineering applications in the selected areas (Information Extraction, Machine Translation and Dialogue Systems), and comparison criteria.
Competencias relacionadas: CB8, CT4, CT6, CEA3, -
Development of criteria to identity problems to be solved using Human Language Engineering.
Competencias relacionadas: CT3, CT6, CT7, CEA7, CG1, CEP3, -
Application of the acquired knowledge to specific real problems.
Competencias relacionadas: CEA3, CT3, CT7, CB6, CEA5, CEA7, CG1, CEP3, CEP4, -
Understanding the potential applications of Human Language Engineering in the business environment.
Competencias relacionadas: CEA3, CEA7, CG1, CEA5,
Contenidos
-
Course Introduction
Presentation of the course: aims, plan and structure.
General overview of the range of applications associated with language engineering. Currents trends.
Review of the transformer architecture. -
Information Extraction
Entity and Relation extraction. Event and Time extraction. Sentiment and Affect extraction. Summarisation. -
Machine Translation
Classical MT. Statistical MT. Resources and models for MT. MT Evaluation. -
Dialogue Systems
Question Answering. Conversational Agents. Chatbots. Virtual Assistants.
Actividades
Actividad Acto evaluativo
Course Introduction
Presentation of the course: aims, plan and structure. General overview of the range of applications associated with language engineering. Currents trends.Objetivos: 1
Contenidos:
Teoría
2h
Problemas
1h
Laboratorio
0h
Aprendizaje dirigido
0h
Aprendizaje autónomo
5.7h
Information Extraction
Entity and Relation extraction. Event and Time extraction. Sentiment and Affect extraction. Summarisation. Considering open and restricted domains. Considering monolingual and crosslingual scenarios.Objetivos: 5 2 3
Contenidos:
Teoría
6h
Problemas
3h
Laboratorio
0h
Aprendizaje dirigido
0h
Aprendizaje autónomo
17h
Metodología docente
This course will build on different teaching methodology (TM) aspects, including:TM1: theoretical lecture sessions
TM2: practical sessions with invited speakers from the industry
TM3: laboratory session
TM4: oral presentations of the students
TM5: development of a final project
Método de evaluación
The evaluation of the subject is done through several activities:1. The students must choose a paper with a state-of-the-art technique related to the concepts seen in class and explain it in an oral presentation (15% of the final grade).
2. Laboratory assignment of an HLE application (15% of the final grade).
3. The students must deliver a report from an industrial session, where invited speakers from the industry explain actual applications of HLE (10% of the final grade).
4. For the other 60% of the mark, the students will develop a project that will consist of one of the following options:
a) Deep study of a specific HLE application or a comparative study of HLE applications
b) Development of a HLE application
c) Development of a proposal to solve a specific real challenge
In all cases, the students must prepare an oral presentation (10%) and write a report (50%).
Bibliografía
Básico
-
Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition
- Jurafsky, D.; Martin, J.H,
Prentice Hall,
2008.
ISBN: 9332518416
https://discovery.upc.edu/discovery/fulldisplay?docid=alma991003460299706711&context=L&vid=34CSUC_UPC:VU1&lang=ca -
Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition
- Jurafsky, D.; Martin, J.H,
2019.
http://cataleg.upc.edu/record=b1536816~S1*cat
Capacidades previas
- Introductory concepts and methods of Natural Language Processing.- Programming.