Workshop on Multi-word Units in Machine Translation
The 5th Workshop on Multi-word Units in Machine Translation and Translation Technology (MUMTTT 2022) was held in conjunction with the International Conference “Computational and Corpus-based Phraseology”.
The MUMTTT 2022 workshop took place on 30 September, 2022, in Malaga, Spain.
The conference was jointly organised by the European Association for Phraseology (EUROPHRAS), the University of Malaga, the University of Wolverhampton, and the Bulgarian Association for Computational Linguistics.
|Deadline for paper submission||1 July 2022|
|Acceptance notification||22 July 2022|
|Final camera-ready version||2 September 2022|
|MUMTTT 2022 workshop||30 September 2022|
- Gloria Corpas Pastor, Universidad de Málaga, Spain
- Ruslan Mitkov, University of Wolverhampton, United Kingdom
- Johanna Monti, Università degli Studi di Napoli “L’Orientale”, Italy
- Maria Pia di Buono, Università degli Studi di Napoli “L’Orientale”, Italy
- Gennaro Nolano, Università degli Studi di Napoli “L’Orientale”, Italy
- Giulia Speranza, Università degli Studi di Napoli “L’Orientale”, Italy
- Khadija Ait ElFqih, Università degli Studi di Napoli “L’Orientale”, Italy
- 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 improvement of machine translation
- MWUs and word alignment techniques
- MWUs in machine translation
- MWUs in translation memory systems
- MWUs in term extraction
- 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 consist of full-text papers and should not exceed 7 pages excluding references, they should be minimum of 5 pages long. The accepted papers will be published as workshop e-proceedings together with Europhras short papers and posters with ISBN, will be assigned a DOI and will be also available at the time of the conference. The papers should be in English. Authors of accepted papers will receive guidelines regarding how to produce camera-ready versions of their papers for inclusion in the proceedings. Each submission will be reviewed by at least three programme committee members. 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.
For assistance with submissions, contact the committees at [email protected].