Search

We describe a novel approach to crosslingual dialogue that supports highly accurate communication of semantically complex content between people who do not speak the same language. The approach is introduced through an implemented application that covers the same ground as the chapter of a conventional phrase book for food shopping. We position the approach with respect to dialogue systems and Machine Translation-based approaches to crosslingual dialogue. The current work is offered as a first step towards the innovative use of dialogue theories for the enhancement of human–human dialogue.

A conceptually aligned text is one in which spans are systematically linked to a logical encoding of their meanings. We describe the model of alignment used in WYSIWYM systems, which support knowledge editing through an automatically generated feedback text, and show that this model has a series of practical advantages through which it can support applications requiring semantic interac-tivity and inference, as envisaged by the Semantic Web community. Some results from an efficient recent implementation are presented, showing the benefits of having all levels of linguistic description available for interactive services.

This literature review forms a deliverable in the European Network of Excellence on Semantic Interoperability and Data Mining in Biomedicine. More specifically, it is part of a work package (wp27) which aims to develop and evaluate generic methods and tools for assisting patients to understand their health and healthcare by generating patient-friendly readable texts that paraphrase the content of their electronic health records. We have reviewed the literature in topics that we consider to be relevant to this work package. When appropriate, we cover variations in conditions in the four countries of the collaborating research groups (France, Germany, Sweden and the UK) and we cover corpora, tools and language technologies for the European languages of interest to these groups.First, we consider legal issues involved in patients gaining access to their medical records. Who can view the records? What data do they have the right to access? Are there any data that patients cannot access? Who can access records of dead patients?What about security and data protection? See chapter 2 for brief surveys of the current state of affairs in France, Sweden and the UK. Patient records are packed with jargon, acronyms and medical terms that clinical staff know and understand. Often there is a learning curve before patients become familiar with medical terms associated with their own particular illnesses and they may require more familiar words and phrases to describe medical concepts in an accessible form. The development of largescale medical term banks, thesauri and lexicons (e.g. ums specialist and Metathesaurus) enable Language Technology developers to generate reports for medical staff, but how can we communicate the same concepts to patients? We review the current literature on communicating technical medical terms in everyday language for patients and related issues. See chapter 3.Our survey on computational methodologies for generating patient-friendly texts included the fo

We describe a novel approach to crosslingual dialogue that supports highly accurate communication of semantically complex content between people who do not speak the same language. The approach is introduced through an implemented application that covers the same ground as the chapter of a conventional phrase book for food shopping. We position the approach with respect to dialogue systems and Machine Translation-based approaches to crosslingual dialogue. The current work is offered as a first step towards the innovative use of dialogue theories for the enhancement of human–human dialogue.