Multilingual Authoring Using Feedback Texts

There are obvious reasons for trying to automate the product ion of multilingual documentation, especially for routine subject-matter in restricted domains (e.g. technical instructions). Two approaches have been adopted: Machine ~lh'anslation (MT) of a source text, and Multilingual Natural Language Generation (M-NLG) from a knowledge base. For MT, information extraction is a major difficulty, since the meaning must be derived by analysis of the source text; M~NLG avoids this difficulty but seems at first sight to require an expensive phase of knowledge engineering in order to encode the meaning. Wc introduce here a new technique which employs M-NLG during the phase of knowledge editing. A 'feedback text', generated from a possibly incomplete knowledge base, describes in natural language the knowledge encoded so far, and the options for extending it. This method allows anyone speaking one of the supported languages to produce texts in all of them, requiring from the author only expertise in the subject-matter, not expertise in knowlo edge engineering. 1 I n t r o d u c t i o n The product ion of multilingual documentat ion has an obvious practical importance. Companies seeking global markets for their products must provide instructions or other reference materials in a variety of languages. Large political organizations like the European Union are under pressure to provide multilingual versions of official documents, especially when communicating with the public. This need is met mostly by human translation: an author produces a source document which is passed to a number of other people for translation into other languages. Human translation has several well-known disadvantages. It is not only costly but timeconsuming, often delaying the release of the product in some markets; also the quality is uneven and hard to control (Hartley and Paris, 1997). For all these reasons, the product ion of multilingual documentat ion is an obvious candidate for automation, at least for some classes of document. Nobody expects that automat ion will be applied in the foreseeable future for literary texts ranging over wide domains (e.g. novels). tIowever, therc is a mass of non-literary material in restricted domains for which automation is already a realistic aim: instructions for using equipment are a good example. The most direct a t tempt to automize multilingual document production is to replace the human translator by a machine. The source is still a natural language document written by a human author; a program takes this source as input, and produces an equivalent text in another language as output . Machine translation has proved useful as a way of conveying roughly the information expressed by the source, trot the output texts are typically poor and over-literal. The basic problem lies in the analysis phase: the program cannot extract from the source all the information that it needs in order to produce a good output text. This may happen either because the source is itself poor (e.g. ambiguous or incomplete), or because the source uses constructions and concepts that lie outside the program's range. Such problems can be alleviated to some extent by constraining the source doeument, e.g. through use of a 'Controlled Language' such as AECMA (1995). An alternative approach to translation is that of generating the multilingual documents fl'om a non-l inguis t ic source. In the case of automatic Multilingual Natural Language Generation (M-