Search

La traduzione automatica (TA) ha subìto diversi mutamenti dal 1940 ad oggi. Come in molti altri campi dell’informatica e dell’intelligenza artificiale, si è passati da risorse sviluppate ad hoc manualmente ad approcci basati sempre di più su dati preesistenti. Il presente contributo si propone di offrire una panoramica delle diverse architetture di TA e dei dati da esse richiesti, partendo dagli approcci rule-based e arrivando alle architetture statistiche, examplebased e neurali. Ognuno di questi cambiamenti ha influito sulla tipologia di dati richiesti per la costruzione di motori di TA. Se i primi approcci non richiedevano l’utilizzo di frasi allineate, con la TA statistica è diventato imprescindibile poter fare affidamento su una grande quantità di dati paralleli. Oggi, grazie all’utilizzo delle reti neurali, è possibile ottenere una traduzione di buona qualità persino per combinazioni per cui non sono disponibili dati in entrambe le lingue.

This contribution presents the volume "Research Methods and Themes in Translation, Interpreting and Intercultural Studies", and provides a brief overview of the history of translatology and the relationships it has established with related disciplines. The volume aims to provide an overview of the methods and areas of research that have occupied centre stage in in Translation, Interpreting and Intercultural Studies in recent years, and is aimed both at young researchers who are taking their first steps in the discipline, and at more experienced scholars who wish to broaden their research perspective.

In this paper we present a pipeline developed at Acolad to test a Machine Translation (MT) engine and compute the discount to be applied when its output is used in production. Our pipeline includes three main steps where quality and productivity are measured through automatic metrics, manual evaluation, and by keeping track of editing and temporal effort during a post-editing task. Thanks to this approach, it is possible to evaluate the output quality and compute an engine-specific discount. Our test pipeline tackles the complexity of transforming productivity measurements into discounts by comparing the outcome of each of the above-mentioned steps to an estimate of the average productivity of translation from scratch. The discount is obtained by subtracting the resulting coefficient from the per-word rate. After a description of the pipeline, the paper presents its application on four engines, discussing its results and showing that our method to estimate post-editing effort through manual evaluation seems to capture the actual productivity. The pipeline relies heavily on the work of professional post-editors, with the aim of creating a mutually beneficial cooperation between users and developers.

The present work is a feasibility study on the application of Machine Translation (MT) to institutional academic texts, specifically course catalogues, for Italian-English and German-English. The first research question of this work focuses on the feasibility of profitably applying MT to such texts. Since the benefits of a good quality MT might be counteracted by preconceptions of translators towards the output, the second research question examines translator trainees' trust towards an MT output as compared to a human translation (HT). Training and test sets are created for both language combinations in the institutional academic domain. MT systems used are ModernMT and Google Translate. Overall evaluations of the output quality are carried out using automatic metrics. Results show that applying neural MT to institutional academic texts can be beneficial even when bilingual data are not available. When small amounts of sentence pairs become available, MT quality improves. Then, a gold standard data set with manual annotations of terminology (MAGMATic) is created and used for an evaluation of the output focused on terminology translation. The gold standard was publicly released to stimulate research on terminology assessment. The assessment proves that domain-adaptation improves the quality of term translation. To conclude, a method to measure trust in a post-editing task is proposed and results regarding translator trainees trust towards MT are outlined. All participants are asked to work on the same text. Half of them is told that it is an MT output to be post-edited, and the other half that it is a HT needing revision. Results prove that there is no statistically significant difference between post-editing and HT revision in terms of number of edits and temporal effort. Results thus suggest that a new generation of translators that received training on MT and post-editing is not influenced by preconceptions against MT.

La collana pubblica gli atti del convegno annuale di Linguistica Computazionale (CLiC-it), che ha lo scopo di costituire un luogo di discussione di riferimento nel campo delle ricerce sulla linguistica computazionale. Gli atti includono interventi sul trattamento automatico della lingua, comprendenti le riflessioni teoriche e metodologiche sul tema, e forniscono un contributo importante per questo campo di ricerca. Le altre tematiche principali sono: la linguistica computazionale, la linguistica, le scienze cognitive, l'apprendimento automatico, l'informatica, la rappresentazione della conoscenza, l'information retrieval e l'umanistica digitale. L'organizzazione del convegno è il risultato dello sforzo dell'Associazione Italiana di Linguistica Computazionale (AILC http://www.ai-lc.it/), rappresentata ogni anno da alcuni dei membri organizzatori, che sono affiliati anche ad altre organizzazioni che operano nell'ambito della linguistica computazionale. This book presents the proceedings of the annual Conference of Computational Linguistics (CLiC-it), which aims to provide a forum for discussion in the field of computational linguistics. The proceedings include interventions on the automatic treatment of language, with theoretical and methodological reflections on the subject, and provide an important contribution to this field of research. The other main topics are: computational linguistics, linguistics, cognitive sciences, automatic learning, computer science, knowledge representation, information retrieval and digital humanities. The organization of the conference is the result of the effort of the Italian Association of Computational Linguistics (AILC http://www.ai-lc.it/), represented every year by some of the organizing members, who are also affiliated to other organizations operating in the field of computational linguistics.

This paper describes an approach to translating course unit descriptions from Italian and German into English, using a phrase-based machine translation (MT) system. The genre is very prominent among those requiring translation by universities in European countries in which English is a non-native language. For each language combination, an in-domain bilingual corpus including course unit and degree program descriptions is used to train an MT engine, whose output is then compared to a baseline engine trained on the Europarl corpus. In a subsequent experiment, a bilingual terminology database is added to the training sets in both engines and its impact on the output quality is evaluated based on BLEU and post-editing score. Results suggest that the use of domain-specific corpora boosts the engines quality for both language combinations, especially for German-English, whereas adding terminological resources does not seem to bring notable benefits.