Técnicas

Própias

Multilingüalidad

Alternativas a traducción automática en MT

  • Exploiting Wikipedia and EuroWordNet to Solve Cross–Lingual Question Answering. This is a new advance in solving Cross-Lingual Question Answering (CL–QA) tasks. It is built on three main pillars: (i) the use of several multilingual knowledge resources to reference words between languages (the Inter Lingual Index (ILI) module of EuroWordNet and the multilingual knowledge encoded in Wikipedia); (ii) the consideration of more than only one translation per word in order to search candidate answers; and (iii) the analysis of the question in the original language without any translation process. This novel approach overcomes the errors caused by the common use of Machine Translation (MT) services by CL–QA systems. Experimental results in bilingual scenarios show that our approach performs better than an MT based CL–QA approach achieving an average improvement of 36.7%. Publicación (Universidad de Alicante)

Evaluación y refinamiento de traductores

  • heurísticas para la combinación de traductores
  • selección de la mejor traducción por frecuencias web

Alineación automática de términos entre lenguas

  • Harnessing parallel corpora for extending the TERSEO temporal model to other languages. This technique uses automatic corpora annotation in the target side of parallel corpora. The main idea is focused on annotating the Spanish side of a parallel corpora, projecting the analysis to the second language, and then obtaining new TERSEO patterns (1) and new annotated corpus (2). The set of new patterns will be used to improve the current TERSEO language independent modules. Whereas the new annotated corpus will be used to train a ML system. This system will annotate new temporal expressions in the new language.

Interactividad

Detección del contexto: aprovechamiento del histórico interactivo

  • FlickLing consists of two interfaces which allow to perform monolingual and multilingual image retrieval over the Flickr database, retrieving results with images annotated in different languages. From a given query entered by the user, FlickLing performs automatic term-by-term translation into up to six languages, and provides assistance for interactive query refinement and translation. Since it has been design with the goal of collecting a large search log, it works as an online competitive game, where users have to find as many images as possible to obtain the highest individual and team scores. Publicación 1 Publicación 2 (Universidad Nacional de Educación a Distancia)

Enriquecimiento del diálogo: aprendizaje del estado emocional del usuario

  • Flexible Dialogue System, this is a mixed-initiative Dialogue System designed to guide the user when accessing the web. It has been designed to access different types of web services and information. The main goal in the system design have been its adaptability to the different types of web contents and different types of users and different languages. The Dialogue System consists of four main modules: the Natural Language Analyzer, the Dialogue Manager, the Language Generator and the Services' Access. The Dialogue System is focused in the development of a platform for accessing Web Services. The communication channel can be either textual or by voice, using natural language. The aim of our Dialogue System is to facilitate the integration of new applications into the platform. Then, the development of application specific resources should be easy and able to do by non skilleds. http://www.lsi.upc.es/~nlp/disi (Universidad Politécnica de Cataluña)

Multimodalidad

Técnicas de procesamiento de imágenes y combinación multimodal

  • MMLCA y MMRR TF-IDF Dos técnicas de RI basada en fusión multimodal que han demostrado buenos resultados en diferentes competiciones combinando sistemas de RI basados en las notas al pie de las imágenes y sistemas de RI basados en las características visuales de la imagen. Publicación (Universidad de Alicante)

Técnicas de procesamiento de transcripciones

  • Aplicación: RI/QA sobre audio transcrito
  • Aproximaciones: ganancia de información

Recopilación de Terceros

Recuperación de Información Visual

tecnicas.txt · Última modificación: 2009/09/25 13:26 por admin
CC Attribution-Noncommercial-Share Alike 3.0 Unported www.chimeric.de Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0