Speaking the users' languages

Abstract

S uppose you're on the Web and looking at the image in Figure 1. You might ask, "What in the digital world is that?" Information about such digital objects is easy to provide to users who, for example, click on the object in their browsers. But clicking does not automatically provide information that is tailored to the individual user's abilities, interests, or preferences, or that takes account of previous exchanges between the user and the system. For that to happen, the information must be stored in a different, nontextual fashion and turned into a spoken or written message in the user's language when needed. This generation process can take into account the context and the user's linguistic and personal preferences so that it looks to the user as if the object has been stored all along as a personalized information object.Usability expert Jakob Nielsen has long argued that computer systems should speak the user's language. By using personalized information objects, a system can indeed speak the user's language. Moreover, a multilingual system can speak all the users' languages. Such objects will find application in many different arenas. For instance, GPS-equipped alwayson mobile devices will offer location-based services, providing users with information about nearby objects and organizations. These include both commercial and cultural products and providers: sales offers, restaurants, historical artifacts, and tourist attractions. But the attractiveness and utility of location-based services could be greatly enhanced if they trade specifically in personalized information objects. Users expect customized information, and they will expect it to be delivered using whatever presentation method makes the most sense: graphics, text, speech, or all three.We don't need to wait for next-generation mobile devices to explore the possibilities of personalized information objects. The system we have been working on, within the M-PIRO project, has concentrated on virtual and other museum settings. A specific advantage is that museum communication professionals are well versed in the need to tailor an organization's preferred message to their visitors' expertise and information needs. The project has focused on developing language-engineering technology for personalized information objects, specifically on multilingual information delivery.Progress on the project has required working on multilingual natural language generation from a single source, improving speech synthesis for languages other than English, generating spoken and written messages from the same source, authoring the single source through symbolic authoring techniques, and working with adaptive user modeling for personalized information presentation. The result is a stateof-the-art system that speaks the users' languages and offers highly personalized information objects.

Enriching OWL Ontologies with Linguistic and User-Related Annotations: The ELEON System

“…M-PIRO project [1] developed the Exprimo NLG engine using the ILEX system [2] as a starting point. Exprimo generated personalized multilingual textual descriptions and supported three languages, English, Italian and Greek.…”

“…Recently, it has been enhanced to cooperate with NaturalOWL [3] while it can also collaborate with the Methodius NLG engine 3 , the enhanced version of Exprimo. In general, it can easily communicate with various NLG engines due to its wellspecified interface 1 ELEON generates texts from the ontology that encodes domain knowledge in the form of concepts, concepts' instances (entity types and entities respectively in ELEON's terminology), concepts' properties and relations between concepts. Entity types are organized in a taxonomy.…”

“…Natural Language Generation (NLG) systems have found many applications, from generating software manuals from a single, symbolic source, like DRAFTER [5] and AGILE [8], to generating drug descriptions [9], and museum exhibit descriptions [1,2]. All these systems can generate in multiple languages from a single, language-neutral symbolic source of information.…”

“…This issue has mainly been addressed so far by developing authoring tools that help in the creation of source information and domaindependent linguistic resources. Such tools were developed, for example, in GIST [7], DRAFTER [5], WYSIWYM [6], and M-PIRO [1]. M-PIRO's authoring environment allowed curators to fully define the domain ontology, create domain-dependent linguistic resources and link them to the ontology, and adjust parameters related to user modeling.…”

OntoVerbal: a Generic Tool and Practical Application to SNOMED CT

“…Several initiatives in the field of natural language generation (NLG) have addressed the problem of generating better, more coherent and easily processable texts derived from ontologies -for example, ILEX [6], M-PIRO [7], NaturalOWL [8] and Rabbit [9]. These systems make use of annotated data or users' interactions to construct sentences and paragraphs.…”