Papers by Arturo Trujillo
Except for W.J.Hutchins books, no other book gives such a wide overview of the major concepts of ... more Except for W.J.Hutchins books, no other book gives such a wide overview of the major concepts of machine translation (MT) and machine-aided translation (MAT). Indeed this volume of 300 pages presents (almost all) the major translation approaches argued with linguistic and technical implications for each kind of application. Moreover neighbouring concepts that are spontaneously involved in MT/MAT are introduced such as multilingual text processing, formal language theory and artificial intelligence. The audience is well defined by the author in the preface. This book is useful for anyone who is interested in translation. Linguists, computer specialists and professional translators can find useful resources in this book for their research, development, studies and other activities. Moreover the author's writing style is quite fluent making the key concepts accessible to non-specialist readers. Note that the author does not present a new approach to MT/MAT in this book, his own approach is mainly descriptive and less suggestive. Four parts containing ten chapters are intelligently arranged allowing the reader to go through them progressively. A conclusion and a list of complementary references end each one of the ten chapters.
IEEE Transactions on Medical Imaging
In this paper, we present an algorithm for the automatic extraction of translation patterns betwe... more In this paper, we present an algorithm for the automatic extraction of translation patterns between two (Indo-)European languages. These consist of possibly discontiguous text fragments, with the bilingual relationship between the text fragments and the discontinuities between them made explicit. The patterns are extracted from a bilingual parallel corpus aligned at the sentence level, without the need for linguistic analysis, and are used to build a translation memory database which is intended for use in a machine aided human translation (MAHT) setting, such as a translator's workbench (TWB). The patterns extracted could also form the basis for example-based machine translation (EBMT) without the need for complex linguistic or statistical processing. Given a TM database made up of our concept of translation patterns and a SL input string, relevant translation patterns combine to form TL translations as suggestions to the translator. We evaluate the accuracy of the translation patterns extracted along with the quality of translations produced.
Applying Machine Translation Techniques to the Evaluation of Grammar Texts
This paper describes a methodology for the eva- luation of translation and usage rules of the typ... more This paper describes a methodology for the eva- luation of translation and usage rules of the type usually found in pedagogical grammar texts; the methodology is applied to two types of such rules written from different perspectives, and the con- clusions drawn from this exercise are presented. The work is of relevance to teachers and compilers of learner grammars, since
Machine Translation with the ACQUILEX LKB
this paper transferinvolves mapping a list of SL lexical signs into a bag of target language (TL)... more this paper transferinvolves mapping a list of SL lexical signs into a bag of target language (TL) lexicalsigns. Bag generation consists of ordering the TL bag into a grammatical sentence; this isdone through a modified chart parser which effectively attempts every permutation of theTL bag. Much effort in lexicalist translation is needed to tackle the inefficiencies of thisgeneration process, and
Traditional Translation Memory systems that find the best match between a SL input sentence and S... more Traditional Translation Memory systems that find the best match between a SL input sentence and SL sentences in a database of previously translated sentences are not ideal. Studies in the cognitive processes underlying human translation reveal that translators very rarely process SL text at the level of the sentence. The units with which translators work are usually much smaller i.e. word, syntactic unit, clause or group of meaningful words. A building blocks approach (a term borrowed from the theoretical framework discussed in Lange et al ), is advantageous in that it extracts fragments of text, from a traditional TM database, that more closely represent those with which a human translator works. The text fragments are combined with the intention of producing TL translations that are more accurate, thus requiring less postediting on the part of the translator.
Uploads
Papers by Arturo Trujillo