AMTA 2016 | Accepted Workshops

This workshop is intended for translators who are curious about machine translation but have never seriously experimented with it or tried their hand at post-editing. The workshop will invite a limited number of CAT tool vendors whose systems incorporate machine translation and allow each forty minutes to demonstrate their system’s MT features, particularly those designed for post-editing. We will select vendors whose systems cover a range of different options, in terms of the type of embedded MT technology, language pairs covered, retraining options, licencing and software delivery model, facilities offered for post-editing, etc. We will also encourage the vendors to give workshop attendees the chance to actively try out their system using their own texts.

This workshop will consider questions relating to various forms of human interaction with MT, such as: How do organizations currently measure end-user interaction and satisfaction with MT? How does raw or post-edited MT affect usability of products or content? How does translator interaction with MT differ from translator interaction with human translation? How can MT developers best use end-user interaction data to improve MT output quality and user experience of MT? The term interacting is deliberately used to broaden the focus beyond post-editing and interactive MT, though both of these topics fit comfortably within the theme. The workshop will feature invited talks by prominent researchers in the field, as well as oral presentations of ongoing research work. Presentations will be selected based on submitted extended (500-word) abstracts. Presenting researchers will be invited to submit a paper to a special issue of Machine Translation journal on this topic.

Assessing the quality of production translation has become a key concern for translation consumers and end users, for translators and language service companies, and for researchers seeking to compare or improve tools, particularly machine translation. There are currently three standards in development in ASTM’s Language Services Committee and two standards in ISO’s Technical Committee 37 on Terminology and Other Language and Content Resources that focus on assessing translation quality. The Translation Automation Users Society (TAUS) has created a Quality Dashboard and framework (i.e., the Dynamic Quality Framework, now merged with the Multidimensional Quality Framework) which is extensively influencing some of the standards efforts.

This workshop reviews the types of questions asked by customers and end users of translation and by Language Service Providers. It then addresses the types of metrics and assessment methods currently available, looking at how effectively and under what conditions the assessment meets both the metric and the user or provider questions. The workshop then generates recommendations for ASTM, ISO, and TAUS, and for providers and consumers of translation, and for researchers and developers.
Organizer: Jennifer DeCamp (MITRE)

Semitic languages are used by a significantly large population of native speakers and belong to a family that includes classical Arabic, a large number of Arabic dialects, Hebrew, Amharic, Maltese and other languages. These languages are characterized by a system of word formation based on roots and patterns, a rich and productive morphology (including non-concatenative processes), a diversity of orthographic conventions and, unfortunately, limited language resources suitable for computational research and development.

Semitic languages as a whole are still understudied, although over the past decade there has been a body of computational processing research specifically targeted to individual Semitic languages, much of the work to date remains the result of initiatives undertaken by individual researchers or research establishments. Several workshops in recent years – both regional and affiliated with international conferences – have addressed the spectrum of issues relating to the processing of Arabic, Hebrew and other Semitic languages. The progress of recent years has opened the door to advanced computational applications such as machine translation. Research on machine translation of Semitic languages is, however, still in its early stages. Accurate translation of Arabic, Hebrew, Amharic, Maltese and other Semitic languages requires treatment of unique linguistic characteristics, some of which are common to all Semitic languages, others specific to each of these individual languages and their dialects.

The goal of this workshop is to bring together researchers and research specifically concerned with issues pertaining to machine translation to, from, and among Semitic languages. Furthermore, the workshop will be an opportunity for the Special Interest Group on Computational Approaches to Semitic Languages (the SIG) to meet and discuss future direction in Computational Linguistics and Natural Language Processing approaches to Semitic Languages.

Organizers: Mona Diab, GWU, USA; Houda Bouamor, CMU-Qatar; Ahmed ElKholy, Microsoft, USA; Mahmoud Ghoneim, GWU, USA; Yuval Marton, Microsoft, USA