AGILE - a system for multilingual generation of technical instructions
17150Authors
nan
Abstract
AbstractThis paper presents a multilingual Natural Language Generation system that produces technical instruction texts in Bulgarian, Czech and Russian. It generates several types of texts, common for software manuals, in two styles. We illustrate the system’s functionality with examples of its input and output behaviour. We discuss the criteria and procedures adopted for evaluating the system and summarise their results. The system embodies novel approaches to providing multilingual documentation, ranging from the re-use of a large-scale, broad coverage grammar of English in order to develop the lexico-grammatical resources necessary for the generation in the three target languages, through to the adoption of a ‘knowledge editing’ approach to specifying the desired content of the texts to be generated independently of the target languages in which those texts finally appear.
Keywords
Full Content
AGILE – A System for Multilingual Generation of Technical Instructions Anthony Hartley1, Donia Scott1, John Bateman2, Danail Dochev3 1Information Technology Research Institute – University of Brighton [donia.scott, tony.hartley]@itri.brighton.ac.uk 2Faculty of linguistics and literature (FB10)– University of Bremen bateman@uni-bremen.de 3Institute of Information Technologies – Bulgarian Academy of Sciences dochev@iinf.bas.bg Abstract This paper presents a multilingual Natural Language Generation system that produces technical instruction texts in Bulgarian, Czech and Russian. It generates several types of texts, common for software manuals, in two styles. We illustrate the system’s functionality with examples of its input and output behaviour. We discuss the criteria and procedures adopted for evaluating the system and summarise their results. The system embodies novel approaches to providing multilingual documentation, ranging from the re-use of a large-scale, broad coverage grammar of English in order to develop the lexico-grammatical resources necessary for the generation in the three target languages, through to the adoption of a ‘knowledge editing’ approach to specifying the desired content of the texts to be generated independently of the target languages in which those texts finally appear. Keywords Generation, multilinguality, styles, grammar re-use, evaluation Introduction The AGILE project (Automatic Generation of Instructions in Languages of Eastern Europe) was a three-year project (1998—2001) in which a prototype multilingual Natural Language Generation (NLG) system was developed for producing user manuals for CAD-CAM systems in Bulgarian, Czech and Russian. The project involved the Institute of Information Technologies—Bulgarian Academy of Sciences, Charles University in Prague, the Russian Research Institute for Artificial Intelligence, the University of the Saarland and the ITRI at the University of Brighton (coordinators). It built on the success of the previous DRAFTER system, developed by the ITRI with support from two commercial partners, Praetorius Ltd and Integral Solutions Ltd. (Scott & Evans, 1998). DRAFTER stands for “DRafting Assistant For TEchnical writers”, and enables the production of draft software manuals in English and in French. Within AGILE, this approach was investigated further, considering a broader range of languages and more sophisticated textual possibilities. The prototype system developed within AGILE allows users to specify the content of the instructions for carrying out tasks in the CAD-CAM domain. This content is then automatically expressed in each of the three target languages in parallel. The approach of multilingual NLG thus contrasts with the more conventional approach of (MT) in that the starting point is not a source text in one language, but a non- linguistic specification of the content to be expressed (Hartley and Paris, 1997). This specification may draw on one of the target languages, but need not: in our illustrations in the present paper, for example, the AGILE user-interface language was set to English in order to facilitate the presentation. One practical advantage of applying such a multilingual NLG system is therefore that end-users can directly ‘author’ draft first versions of texts in languages that they do not themselves speak. The AGILE project also represented the first attempt ever at a comprehensive computational account of Bulgarian, Czech and Russian for the purpose of …
Content truncated to 500 words
Labeled Text
AbstractThis paper presents a multilingual Natural Language Generation system that produces technical instruction texts in Bulgarian, Czech and Russian. It generates several types of texts, common for software manuals, in two styles. We illustrate the system’s functionality with examples of its input and output behaviour. We discuss the criteria and procedures adopted for evaluating the system and summarise their results. The system embodies novel approaches to providing multilingual documentation, ranging from the re-use of a large-scale, broad coverage grammar of English in order to develop the lexico-grammatical resources necessary for the generation in the three target languages, through to the adoption of a ‘knowledge editing’ approach to specifying the desired content of the texts to be generated independently of the target languages in which those texts finally appear.
Publication Details
- Paper ID:
- 17150
- Year:
- 2001
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan