05/02/2015 SKATER 2nd Workshop at Barcelona

SKATER General meeting to present the research carried out in the framework of the national project:

http://nlp.lsi.upc.edu/skater/

 

Place A6203 (Aulario 6, Campus Nord, UPC)

 

AGENDA:

 

February 5th

10 – 10:30 Horacio Presentación de las jornadas

10:30 – 10:50 Luís Taxonomizing flat terminologies

10:50 – 11:10 Marta Utilización de modelos de usuario para generar preguntas y respuestas personalizadas en inglés, español y catalán

11:10 – 11:30 German Cross-lingual Event Detection

11:30 – 11:50 café

11:50 – 12:10 Zagros Semanticizing temporal expressions from Unstructured Contents

12:10 – 12:30 Eli Automatic Machine Translation Evaluation: a Qualitative Approach

12:30 – 12:50 Francesco Barbieri Figurative Language (SemEval)

12:50 – 13:10 Jordi DIP: Anonimizador de documentos clínicos bilíngües cas/cat

13:10 – 13:30 Canan Semiautomatic construction of a domain ontology from standard ISA88

13:30 – 15:00 comida

15:00 – 15:20 Lluís TextServer: Cloud-based language processing.

15:20 – 15:40 Jorge Scaling-up term acquisition

15:40 – 16:00 Egoitz Laparra Implicit SRL

16:00 – 16:20 Zuhaitz Big Data and NLP

16:20 – 16:40 Marina Lloberas PARTES: Test Suite for Parsing Evaluation

16:40 – 17:00 Xavier Arregui Ber2Tek demos

17:00 – 17:20 café

 

17:20 – 17:40 Xavier Adquisición de conocimiento terminológico en corpus a través de las relaciones de WordNet

17:40 – 18:00 Rodrigo Agerri Semi-supervised Domain adaptation

18:00 – 18:20 Daniel Ferrès Georeferencing Formal and Informal Documents with Knowledge Bases and Language Models

18:20 - 18:40 Montse Marimon demo + descripcion del simplificador definition extraction o taxonomy learing sentiment analysis

 

21:30 Cena

http://www.restaurantcalboter.com/


February 6th
9:30 – 11:30 Planificación del trabajo a realizar en el 2015 (por WP)
11:30 – 11:50 café
11:50 – 14:00 Discusión sobre la continuidad del proyecto en la siguiente convocatoria

Asistentes
UB
- Elisabeth Comellas
- Marina Lloberes
- Marta Coll-Florit
- Lara Gil
- Salvador Climent
- Antoni Oliver
- Irene Castellón

UPC
- Jordi Turmo
- Lluís Padró
- Marta Gatius
- Carme Martín
- Zagros Ardalan
- Javi Farreras
- Alicia
- Maria Fuentes
- Horacio Rodríguez

- Canan Dombayc

- Antonio Espuña
- Moisès Graells

UPF – IULA
- Jorge Vivaldi
- Núria Bel

EHU
- Zuhaitz Beloki
- Egoitz Laparra
- Xavier Arregi
- German Rigau

- Rodrigo Agerri

Uvigo
- Xavier Gómez

UPF – TALN
- Luis Espinosa
- Daniel Ferres
- Montserrat Marimon
- Francesco Barbieri
- Horacio Saggion

 

Workshop on Adaptive Natural Language Processing at IJCAI 2015

SKATER members organized the Workshop on Adaptive Natural Language Processing

in conjunction with IJCAI 2015

in Buenos Aires, Argentina, July 25-27 2015

 

Motivation and Aims

Natural Language Processing is becoming more and more ubiquitous as technologies become omnipresent in our daily life. This involves a huge effort to develop language-based interfaces, text analytics, search engines, writing assitants among other systems and their related tools and resources. Adaptation has been key to facilitate rapid development of language-based systems, with reuse of existing resources as alternatives to creating tools and resources from scratch. These approaches have benefited from the recent surge of complex Machine Learning approaches as applied to NLP tasks. This is the case for Semi-supervised and Unsupervised Learning, Active Learning, Domain Adaptation, and even Representation Learning and Deep Learning, which have had a very positive impact on NLP tasks and applications.

This workshop aims to provide a meeting point for researchers working on the portability of language resources and methodologies across languages and domains, with a special focus on exploiting available knowledge as a base to facilitate and enhance new developments. We understand that there is a common factor between tasks like porting a parser between related languages, adapting a dialogue system for a different domain, using rules inferred from an annotated corpus together with an unannotated corpus to port an information extraction system to another domain, or simplifying texts for different kinds of readers, among others. We believe that sharing insights on such approaches will be enriching and will contribute to a better understanding of the problems and solutions.

We expect that themes like Representation Learning, Deep Learning and Active Learning, and their successful applications to various areas of NLP, will raise interesting, intellectually challenging discussions.


Workshop Topics

Contributions may present results from completed as well as ongoing research, with an emphasis on novel approaches, methods, ideas, and perspectives.

The topics of the workshop include, but are not limited to:

Semi-supervised learning, Deep Learning, Active learning and Representation learning for domain adaptation, language portability and task portability
Adaptation and reuse of tools and resources for closely related languages
Adaptation of highly valuable resources, like treebanks, to languages not closely related
Linguistic issues in language portability: false friends, asymmetric discretization of semantic continuum
Learning from multiple domains
Development of multi-domain datasets
Evaluation paradigms for complex learning
Domain adaptation for specific applications: parsing, machine translation, information extraction, document classification, sentiment analysis and author attribution and profiling

Format of submissions

Submissions are invited for papers presenting high quality, previously unpublished research. Selection criteria include originality of ideas, correctness, clarity and significance of results and quality of presentation.

We welcome two types of contributions:

Long papers (10 pages), presenting substantial, original and completed research work. Accepted long papers will be presented orally.
Short papers (6 pages), with a small, focused contribution, work in progress, a negative result or an opinion piece. Accepted short papers will be presented either orally or as a poster.

Short papers can be combined with a system demonstration.

The only accepted format for submitting papers is Adobe PDF. Papers should follow IJCAI-15 formatting Guidelines.

As the review process will be double-blind, your submission must not include the author(s) name(s) and affiliation(s). Furthermore, self-references that reveal the author's identity, e.g., "We previously showed (Pérez, 2003) ...", must be avoided. Instead, citations such as "Pérez (2003) previously showed ...", must be used.

Submissions will be electronic, the submission site will be made available soon.


Important Dates

Submission deadline: April 27 2015
Acceptance/rejection notification: May 20 2015
Camera-ready deadline: May 30, 2015
Workshop: July 25-27 2015 at IJCAI 2015


Programme Committee

Luciana Benotti (UNC, Argentina)
Xavier Carreras (XEROX-XRCE, France)
Helena Caseli (UFSCar, Brazil)
José Castaño (UBA, Argentina)
Carlos Iván Chesñevar (UNS, Argentina)
Martín Domínguez (UNC, Argentina)
Pablo Duboue (Les Laboratoires Foulab, Canada)
Marcelo Errecalde (UNSL, Argentina)
Hugo Jair Escalante (INAOE, Mexico)
Paula Estrella (UNC, Argentina)
Mikel Forcada (UA, Spain)
Maria Fuentes Fort (UPC, Spain)
Xavier Gómez Guinovart (UVigo, Spain)
Agustín Gravano (UBA, Argentina)
Franco Luque (UNC, Argentina)
Rada Mihalcea (UNT, USA)
Maria das Graças Volpe Nunes (USP, Brazil)
Lluís Padró (UPC, Spain)
Muntsa Padró (Nuance, Canada)
Martí Quixal (UTübingen, Germany)
Thiago Pardo (USP, Brazil)
Ted Pedersen (UMN, USA)
German Rigau (UPV, Spain)
Aiala Rosá (UdelaR, Uruguay)
Paolo Rosso (UV, Spain)
Horacio Saggion (UPF, Spain)
Thamar Solorio (UH, USA)
Juan-Manuel Torres-Moreno (LIA/UAPV, France)
Cristina Vertan (UH, Germany)
Dina Wonsever (UdelaR, Uruguay)

Organizing Committee

Laura Alonso i Alemany (UNC, Argentina)
Núria Bel (UPF, Spain)
Irene Castellón (UB, Spain)
Manuel Montes y Gómez (INAOE, Mexico)

 

The Massive Open On-line Course on Machine Translation that will start on October 23

The course entitled: "Approaches to Machine Translation: rule-based, statistical and hybrid" is an opportunity to learn about the theory behind MT algorithms; how major on-line MT systems work; and how to manage open-source software to reproduce prototypes of such systems under a do-it-yourself basis.

The MOOC is offered by the UPC under the CANVAS platform. Students that successfully pass tests and assignments will be granted a certificate by the same University.

Subcategories

  • 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