Hervé Blanchon

Multilingual Dialogue-Based MT for Monolingual Authors: the LIDIA Project and a First Mockup

Dialogue-Based Machine Translation (DBMT) is a new paradigm for translation situations where other approaches such as the Linguistic-Based (LBMT) and the Knowledge-Based (KBMT) approaches, are not adequate. In DBMT, although the linguistic knowledge sources are still crucial, and extralinguistic knowledge might be used if available, emphasis is on indirect pre-editing through a negotiation and a clarification dialogue with the author in order to get high quality translations without revision. Authors are distinguished from “spontaneous” writers or speakers by the fact that they want to produce a “clean” final message and may be willing to enter into such dialogues. After having described the main situational, linguistic and ergonomic issues in DBMT for monolingual authors, we describe ongoing work on the LIDIA project. The typical translational situation considered is the production of multilingual technical documentation in the form of HyperCard stacks. Notable points in the linguistic design include multilevel transfer with interlingual acceptions, properties and relations, the “guided language” approach (typed textual fragments and lexical peferences), and a TEI-inspired representation of texts and structures. The current mockup, LIDIA-1.0, demonstrates the majority of these ideas on a HyperCard stack, to be translated from French into German, Russian and English. Some of its aspects are discussed in detail, in particular the user interface, the object-oriented implementation, and the production of disambiguation dialogues.

Perspectives of DBMT for monolingual authors on the basis of LIDIA-1, an implemented mock-up

DBMT is researched here in the context of future systems for the general public, where a monolingual author wants to translate into several languages. We have produced a complete mock-up, LIDIA-1, which demonstrates how a French HyperCard™ stack could be translated into German, Russian and English. We present the computational, linguistic and ergonomic aspects of the mock-up, and discuss them in the perspective of building an operational prototype in the future.

Annotating documents by their intended meaning to make them self explaining: an essential progress for the semantic web

A Self-Explaining Document (SED) is a document enriched with annotations keeping track of all possible interpretations with respect to a given grammar and dictionary, as well as disambiguating choices. If disambiguation is complete and has been done by the author himself, a SED conveys “the authors intention”. The availability of SEDs might considerably reduce misunderstanding between authors and readers, and perhaps lead to the assignment of a “meaning certification level” to any part of a document. We present ways to integrate these annotations into an arbitrary XML document (SED-XML), and to make them visible and usable to readers for accessing the “true content” of a document. We also show that, under several constraints, a SED, once translated into a target language L, might be transformed into an SED in L with no human interaction. Hence, the SED structure might be used in multilingual as well as in monolingual contexts, without addition of human work.