17/11/2017 - Audi Primadhanty PhD dissertation


Low-Rank Regularization for High-Dimensional Sparse Conjunctive Feature Spaces in Information Extraction



Audi Primadhanty



Sala Juntes, B6 Building


Fri Nov 17, 2017




Drs. Xavier Carrreras and Ariadna Quattoni



TALP Seminar on NLP with UIMA / DKPro

Title: UIMA / DKPro Core - With Reusable and Interoperable Components Towards Reproducible Experiments 
Date: Thursday, 9th of November
Time: From 10:00 to 14:00 
Room: Campus Nord UPC, Omega building, S210.
by:Jens Grivolla (UPF)
Abstract: Vast amounts of information are stored in unstructured formats such as audio, video, or plain text. The field of Natural Language Processing (NLP) addresses this by providing not only methods but also many ready made tools to analyze text and to structure it in many ways ranginge from simple segmentation to complex
semantic analysis. However, it is often difficult to incorporate these tools into new experimental setups because the complexities of installation, configuration, data transformation and interoperability in general are often  underestimated. This negatively affects the reproducibility of such experiments. This talk will give an introduction to doing NLP with DKPro Core and the DKPro eco-system with a focus on the approaches employed to promote and facilitate reproducible experiments and the development of NLP-based applications.
Taller de PLN con UIMA / DKPro
El taller de introducción al análisis automático de texto con UIMA y DKPro presentará la plataforma abierta de procesamiento de datos UIMA (Unstructured Information Management Architecture) en conjunto con DKPro, una amplia colección de componentes intercambiables de PLN (procesamiento de lenguaje natural).
El taller consistirá en tres partes principales:
1. introducción a UIMA y DKPro (presentación)
2. configuración, ejecución e integración de cadenas de procesamiento usando componentes existentes (sesión práctica)
3. desarrollo y adaptación de componentes compatibles con UIMA/DKPro (sesión práctica)
Para las sesiones prácticas se necesita un ordenador con Eclipse, Java, Git y Maven.
Jens Grivolla es un investigador postdoctoral en el grupo TALN de la Universidad Pompeu Fabra. Sus principales líneas de investigación son la extracción y recuperación de información y los sistemas de recomendación, en particular los sistemas híbridos y multimodales. Es el responsable de arquitectura e infraestructura de software del grupo y lidera las tareas de integración en varios proyectos H2020. Es un miembro activo de la comunidad de UIMA desde el 2009 y organizador del workshop OIAF4HLT (Open Infrastructures and Analysis Frameworks for HLT) en COLING 2014.


Open PhD position on Unsupervised evaluation for Machine Translation using deep learning

At the TALP Research Center from Universitat Politècnica de Catalunya (UPC, Barcelona) we are looking for a PhD student to work in automatic unsupervised evaluation for machine translation using deep learning techniques. The PhD position is a MINECO contract in the context of the CHISTERA Project: ALLIES: Autonomous Lifelong Learning IntelligEnt Systems. The ALLIES project will lay the foundation for development of autonomous intelligent systems sustaining their performance across time. 

The PhD position is funded including salary, tuition, travel and equipment for students of any nationality. We offer a 3-year contract (expected start date is December 2017/January 2018). The gross salary of a PhD student is 25,000 €/year aprox. The TALP research group provides excellent opportunities for professional and personal development, research stays at the most competitive international research labs, participation in top international conferences.




The applicants must have a MS degree in Electrical Engineering, Mathematics, Computer Science, or Computational Linguistic, or equivalent (300 ECTS including the BS degree).  We encourage candidates with strong computer science foundation, natural language processing and/or deep learning experience.

You should apply by sending a brief CV (2-pages) and an application letter to This email address is being protected from spambots. You need JavaScript enabled to view it. , by 20th November 2017. Subject of email should be **PhD Application**


  • Join us

    Job Offers and Research Positions

  • Awards

    Scientific awards Best: Publications, Thesis, Demos, ...

  • Seminars

    Framework to promote research related with Natural Language Processing or Speech Processing.

  • Thesis

    TALP PhD dissertation

  • Events

    Information about Courses, Conferences, workshops, talks, ...

  • Call For Papers

    Relevant Conference, workshops or special issues call for papers announcement

  • Relevant Publications
  • Members

    Professors, students and colaborators visiting TALP.

    New members incorporation and former members carreer.

  • Projects

    TALP research and innovation projects

  • Press

    Selected articles and reports about the TALP Research Center taken from the international press

  • Formation

Additional information