September 18 - 20, 2013

Facultad de Informática, Universidad Complutense de Madrid.

The 29th edition of the Annual Conference of the Spanish Society for Natural Language Processing (SEPLN) will take place in the Universidad Complutense de Madrid on September 18, 19 and 20, 2013. The aim of the conference is to provide a forum for discussion and communication where the latest research work and developments in the field of Natural Language Processing (NLP) can be presented by scientific and business communities. The conference also aims at exposing new possibilities of real applications and R&D projects in this field. Moreover, as in previous editions, there is the intention of identifying future guidelines or paths for basic research and foreseen software applications, in order to compare them against the market needs. Finally, the conference intends to be an appropriate forum in helping new professionals to become active members within the area.


Invited Speakers


Talk on Wednesday 18th September, 9:30 am. Dr. Jörg Tiedemann, Uppsala University, Sweden.

Linguistic Solidarity in Machine Translation - Statistical MT for Under-Resourced Languages and Domains Statistical Machine Translation (SMT) is by far the most dominant approach to automatic translation in current research and system development. The success of statistical methods is based on the availability of large bodies of parallel and monolingual texts. However, appropriate resources are non-existing or not accessible for most language pairs. Furthermore, current SMT models are very sensitive to domain shifts but domain-specific data is usually sparse or difficult to obtain even for "high-density" languages.
In my talk I will look at specific problems for selected language pairs and discuss possibilities for training machine translation systems with extremely sparse data sets. In particular, I will look at triangulation and pivot-based translation as a way to overcome the shortage of data. The main idea in this approach is to make use of intermediate languages to support poorly resourced languages. I will focus on closely related languages as pivot and emphasize the use of low-level translation techniques that take advantage of structural and lexical similarities between those languages.


Talk on Friday 20th September, 11:00am. Dr. Horacio Saggion, Universitat Pompeu Fabra

Text Simplification in Spanish: What for?
Automatic text simplification arises as a Natural Language Processing task with two clear objectives: on the one hand it aims at reducing the complexity of sentences in order to improve the performance of certain linguistic processors. On the other hand, it can be used to adapt textual content to make it more accessible to different types of users. In recent years, research in automatic text simplification has intensified with a number of interesting methods, solutions and simplification-related tools been proposed. In this talk I will introduce the text simplification problem, give an overview of techniques and discuss research carried out with a number of collaborators to address simplification in the Spanish language.


News

  • The deadline for reduced registration fees is July 8, 2013. At least one author must register for each accepted contribution.
  • Information of the accepted workshops announced.
  • Deadline extension. New deadline: 30th April.

Organizers