The 3rd Workshop on Multi-word Units in Machine Translation and Translation Technology (MUMTTT 2017)
In conjunction with EUROPHRAS 2017 – International Conference “Computational and Corpus-based Phraseology: Recent advances and interdisciplinary approaches” (London, 13-14 November 2017)
Following the success of the two previous editions of the workshop on Multi-word Units in Machine Translation and Translation Technology – the 2013 edition at the MT Summit in Nice, France, and the 2015 edition at the European Society of Phraseology Conference in Malaga, Spain, we are announcing the third edition to be held in conjunction with the International Conference “Computational and Corpus-based Phraseology: Recent advances and interdisciplinary approaches” which is jointly organised by the European Association for Phraseology (EUROPHRAS), the University of Wolverhampton (Research Institute of Information and Language Processing) and the Association for Computational Linguistics – Bulgaria (London, 13-14 November 2017).
The MUMTTT workshop will be held on the second day of the conference, 14 November 2017. It will provide a forum for researchers and practitioners in the fields of (Computational) Linguistics, (Computational) Phraseology, Translation Studies and Translation Technology to discuss recent advances in the area of multi-word unit processing and to coordinate research efforts across disciplines in order to improve the integration of multi-word units in machine translation and translation technology tools.
Multi-word units are acknowledged as one of the major challenges in natural language processing (NLP). In spite of the relative progress achieved for particular types of units such as verb-particle constructions, the identification, interpretation and translation of multi-word units in general still represent open challenges, both from a theoretical and a practical point of view. The idiosyncratic morpho-syntactic, semantic and translational properties of multi-word units pose many obstacles even to human translators, mainly because of intrinsic ambiguities, structural and lexical asymmetries between languages, and, finally, cultural differences.
In recent years, growing attention has been paid to integrating multi-word units (MWUs) in machine translation and translation technology tools, as it has been acknowledged that it is not possible to create large scale language solutions without properly handling MWUs of all types. As a matter of fact, researchers are now addressing the problems posed by MWU processing and translation using different formalisms and techniques, such as: automatic recognition of MWUs in a monolingual or bilingual setting; alignment and paraphrasing techniques; development and use of (handcrafted) monolingual and bilingual language resources; creation of annotated monolingual and parallel corpora, development of strategies for handling syntactically flexible units in language analysis and translation modules, development of evaluation projects.
The aim of the workshop is to bring together researchers and practitioners working on MWU processing from various perspectives, in order to enable cross fertilisation and foster the creation of innovative solutions that can only arise from interdisciplinary collaborations. In particular, the workshop welcomes interactions between NLP researchers working on the computational treatment of multi-word units, experts in (computational) phraseology working on challenging topics of their discipline, as well as translation practitioners, to the benefit of applying their latest results to advance the state of the art in MWU processing.
The MUMTTT 2017 workshop invites the submission of full-text papers (6 to 8 pages long) reporting on original and unpublished research on topics related to MWU processing in machine translation and translation technology, including:
- Lexical, syntactic, semantic and translational aspects in MWU representation
- Theoretical approaches to MWUs (e.g., collostructional analysis of MWU, cognitive approaches to processing MWUs, etc.
- Development of multilingual MWU resources
- Identification and acquisition of MWUs and variants
- Learning semantic information about MWUs from monolingual, parallel or comparable corpora
- Development and use of MWU resources in machine translation and translation technology
- Development of corpora for the extraction and translation of MWUs
- Compilation of resources for the extraction and translation of multiword units
- Creation of MWU-annotated corpora with a focus on translation aspects
- Paraphrasing of MWUs applied to the improving of machine translation
- MWUs and word alignment techniques
- MWUs in machine translation
- MWU-centred machine translation evaluation
- Evaluation of MWU translation
- MWUs in CAT tools
- Multilingualism and MWU processing
- Psycholinguistic studies of MWU processing in a bilingual setting.
Submissions must be formatted according to guidelines that will be provided both for Word and LaTeX text processor. Each submission will be reviewed by at least three programme committee members. As reviewing will be double blind, papers must not reveal author’s identify. Accepted papers will be presented orally or as posters, as determined by the programme committee. There will be no distinction in the workshop proceedings between papers presented orally or as posters.
The first call for papers, expected in January 2017, will provide details on the submission procedure, including deadlines.
Gloria Corpas Pastor, Universidad de Málaga, Spain
Ruslan Mitkov, University of Wolverhampton, United Kingdom
Johanna Monti, Università degli Studi di Napoli “L’Orientale”, Italy
Violeta Seretan, Université de Genève, Switzerland (Chair for contacts)