Despite the growing importance of multilingual aspect of web search, no appropriate offline metrics to evaluate its quality are proposed so far. At the same time, personal language preferences can be regarded as intents of a query. This approach translates the multilingual search problem into a particular task of search diversification. Furthermore, the standard intent-aware approach could be a...

This study introduces large-scale field experiments of VoiceTra, which is the world’s first speech-to-speech multilingual translation application for smart phones. In the study, approximately 10 million input utterances were collected since the experiments commenced. The usage of collected data was analyzed and discussed. The study has several important contributions. First, it explains system ...

In this paper we will briefly describe the approaches taken by the Cheshire (Berkeley) Group for the CLEF CHiC Adhoc tasks (Monolingual, Bilingual and Multilingual retrieval for English, French and German). We used multiple translations of the topics for searching each of the CHiC Europeana English, French and German subcollections, employing Google Translate as our translation system. In addit...

Ontology development is mostly directed at the representation of domain knowledge and much less at the representation of textual or image-based symbols for this knowledge, i.e., the multilingual and multimedia lexicon. To allow for automatic multilingual and multimedia knowledge markup, a richer representation of text and image features is needed. At present, such information is mostly missing ...

This paper deals with various methods for multilingual document categorization and informs about the results of experiments in which EuroWordNet (EWN) plays the central role and serves as a fundamental problem solving tool. We describe both the algorithmic principles and the methodologies used in our classification system and consequently prove their functionality by experimental results. The a...

Within the context of the European research project ”Monnet”, which implements among other activities ontology-based multilingual information extraction, we tackle the the issue of recognizing variants of concept labels in business reports that guide the information extraction process. In this short paper, we describe two related experiments in finding variants of multilingual taxonomy labels u...

A multilingual disaster information system (MLDI) has been developed to overcome the language barrier during times of natural disaster. MLDI is a web-based system that includes templates in nine languages so that translated texts can be made available immediately. Mobile phone e-mail with graphic text is a useful tool for delivering multilingual disaster information. The visibility of graphic t...

This paper presents a new approach to computer assisted production of parallel instructions in multiple languages: multilingual generation. At the IT Research Institute at the University of Brighton, we are working on two major projects on multilingual generation of instructions, funded by the CEC and SERC/DTI and involving collaboration with groups of professional technical authors and transla...

This paper reports the first results on extracting a meaningful representation for words from multilingual parallel corpora. Independent component analysis is used to extract a number of components from statistics calculated for words in contexts. Individual components are meaningful and multilingual and words are represented as a bag of concepts model. The component space created by the extrac...

In this paper, we discuss the possibility of enriching user profiles with multilingual information. Nowadays, the English language is the de facto standard language of commerce and science, however users can speak and interact also in other languages. This brings up the need of enriching the user profiles with multilingual information. Therefore, we propose to combine ontology-based user modeli...