Detecting Inappropriate Use of Free Online Machine Translation by Language Students. A Special Case of Plagiarism Detection

Detecting Inappropriate Use of Free Online Machine Translation by Language Students – A Special Case of Plagiarism Detection Harold Somers Federico Gaspari Ana Niño School of Informatics University of Manchester PO Box 88 Manchester M60 1QD, UK School of Informatics University of Manchester PO Box 88 Manchester M60 1QD, UK School of Education University of Manchester Oxford Road Manchester M13 9PL, UK Harold.Somers@manchester.ac.uk, {F.Gaspari,A.Nino}@postgrad.manchester.ac.uk Abstract. The ready availability of free online machine translation (MT) systems has given rise to a problem in the world of language teaching in that students – especially weaker ones – use free online MT to do their translation homework. Apart from the pedagogic implications, one question of interest is whether we can devise any techniques for automatically detecting such use. This paper reports an experiment which aims to address this particular problem, using methods from the broader world of computational stylometry, plagiarism detection, text reuse, and MT evaluation. A pilot experiment comparing ‘honest’ and ‘derived’ translations produced by 25 intermediate learners of Spanish, Italian and German is reported. 1. Introduction One of the most important developments in the history of Machine Translation (MT) has been the availability, since about 1994, of free MT online: while initially perhaps a marketing ploy, this has had a profound effect on the perceptions of the general public, as well as shaping the development of the technology. It was CompuServe who first entered into an agreement with Systran to make MT available free online (Flanagan, 1996), though AltaVista’s subsequent development of the Babelfish website is much better known. Some ten years on, numerous sites offer MT between vast numbers of language pairs, although some of them are little more than on-line dictionaries, sometimes of dubious quality. There have been a number of studies of the use of free online MT (FOMT) systems, both from the developers’ and users’ perspectives (Bennett, 1996; Miyazawa et al., 1999; Yang and Lange 1998, 2003). This paper concerns one small group of such users, namely language learners. 1.1 MT in the classroom There is a growing literature on the impact of MT in general on the language classroom (see Somers (2001) for an overview), including a series of Workshops at various conferences.1 Much of the focus is on what trainee translators (or language learners as potential professional translators) should learn about MT, and how MT can be taught to computational linguists. There are also contributions suggesting how MT can be used as a kind of computer-assisted language learning tool. Of interest are approaches which seek to exploit the weaknesses of MT to illustrate the differences between languages, or to heighten learners’ appreciation of matters of grammar and style in both languages 1 See “MT in the classroom” bibliography at http://www.co.umist.ac.uk/~harold/teachMTbibl.html. Dedicated conferences are the MT Summit VIII Workshop on Teaching Machine Translation, Santiago de Compostela (2001), 6th EAMT Workshop Teaching Machine Transla- tion, Manchester (2002), and MT Summit IX Workshop on Teaching Translation Technologies and Tools (T4) (Third Workshop on Teaching Machine Translation), New Or- …

Content truncated to 500 words