3rd Call for Papers and Deadline Extension: Multilingualism at the intersection of Knowledge Bases and Machine Translation (1st MomenT Workshop)
Submission Deadline : January 19th, 2018
Date: May 12th, 2018. To be held as part of the 11th edition of the Language Resources and Evaluation Conference (LREC), at the Phoenix Seagaia Resort, Miyazaki, Japan.
The increasing availability of knowledge bases, generated by researchers in the academia and industry, enables extensions of NLP applications with the vast amount of background knowledge available in open formats. However, most of the information that we find in knowledge bases, like knowledge graphs, ontologies, taxonomies, thesauri, dictionaries or terminological datasets, contain descriptions in natural language, mostly only in English, which severely limits their exploitation. Machine translation (MT) can be applied to automatically translate the terminological expressions into multiple languages, but not without its challenges. Usually, they contain domain-specific terminology, which is notoriously difficult to deal with since it is underrepresented in the MT training data.
On the other hand, growing attention has also been paid to the integration of domain-specific knowledge into MT systems or CAT tools. To reduce the post-editing effort involved in the translation process, approaches that enhance the MT systems with existing multilingual domain-specific knowledge, (e.g. DBpedia, IATE or ETB) are becoming increasingly popular. In this sense, the provision of multilingual knowledge bases that could be integrated better into the MT pipeline is a crucial step towards increasing the translation quality of highly-specific texts.
We believe that in the same way that domain ontologies and terminologies can benefit from NLP tools and MT systems that help to overcome the language barrier, NLP tools and MT systems would also profit from the specialized semantic knowledge and the terms that are captured in multilingual ontologies or terminologies. The workshop, therefore, aims at building a bridge between the knowledge base and machine translation communities.
This workshop aims to offer a forum for discussions to researchers who find themselves at the intersection of the two strands of research, namely, knowledge representations of high-specialized domains (represented by domain ontologies, terminologies, dictionaries) and MT, where the intersection point is precisely multilingualism. On the one hand, there is an impending need to cater for multilingual knowledge resources that support NLP, content analytics or information extraction across languages. On the other hand, there is a growing interest in exploiting the knowledge captured in such resources for MT systems that often lack the knowledge of domain-specific expressions.
We would like to bring together researchers from different communities as well as other interested stakeholders from the industry and the public sector in order to identify common interests, exploit synergies, provide use cases, and share methods, tools and resources. We are particularly interested to bring together researchers and practitioners working on MT, specifically statistical (SMT) or neural (NMT), on the one hand and experts on knowledge bases from various perspectives on the other, in order to enable cross fertilisation and foster the creation of innovative solutions that can only arise from interdisciplinary collaborations.
Topics of Interest
The workshop invites the submission of papers reporting on research on topics related to terminological/ontological resources processing in MT, including, but not limited to:
- Multilingual knowledge base generation with MT
- Injection of multilingual knowledge into MT
- Provenance of multiple multilingual resources for MT
- Terminological variations and MT
- MT used for cross-lingual information access, search and retrieval
- Neural MT applied to terminology translation
- Exploiting relational knowledge graphs for Neural MT
- Morphological variations of terminological expressions in MT
- Multilingual knowledge generation for under-resourced languages
- Enriching MT with Linked Data (BabelNet, DBpedia, UMLS, …)
- Multilingual terminology and linguistic resource development, integration and mapping in a Linked Data context
- Multilingual Semantic Web and Linked Data use cases
Submission & Publication
We accept submission of both long (up to 8 pages) and short papers (up to 4 pages) to be presented as long or short oral presentations at the workshop. The papers of the workshop will be published as online proceedings on the LREC 2018 website. Please check the LREC author’s kit website for the proceedings template.
In addition, we aim for a journal special issue as post-conference proceedings in which a selected amount of papers presented at the workshop will be published.
When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research.
For contact data, stylesheets, up-to-date details on submission and the workshop itself, please consult the workshop website (http://moment2018.insight-centre.org/).
Identify, Describe and Share your LRs!
Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). To continue the efforts initiated at LREC 2014 about “Sharing LRs” (data, tools, web-services, etc.), authors will have the possibility, when submitting a paper, to upload LRs in a special LREC repository. This effort of sharing LRs, linked to the LRE Map for their description, may become a new “regular” feature for conferences in our field, thus contributing to creating a common repository where everyone can deposit and share data.
As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, LREC 2018 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.
Paper submission deadline: January 19th 2018
Notification of Acceptance: February 12th 2018
Camera-ready paper: February 23rd 2018
Workshop date: May 12th 2018
Mihael Arcan, National University of Ireland, Galway, Ireland
Elena Montiel-Ponsoda, Universidad Politécnica de Madrid, Spain
Darja Fiser, University of Ljubljana, Jožef Stefan Institute, CLARIN ERIC
Tatjana Gornostaja, Tilde, Latvia, ELRA, BDVA
For further information please contact: email@example.com
The workshop is supported by the CLARIN research infrastructure.
Guadalupe Aguado-de-Cea – Universidad Politécnica de Madrid, Spain
Paul Buitelaar – National University of Ireland, Galway, Ireland
Philipp Cimiano – Bielefeld University, Germany
Christian Chiarcos – Goethe-Universität, Germany
Christopher Crowhurst – United Language Group, USA
Béatrice Daille – University of Nantes, France
Brian Davis – Maynooth University, Ireland
Thierry Declerck – German Research Center for Artificial Intelligence (DFKI), Germany
Arantza Diaz de Ilarraza Sanchez – University of the Basque Country, Spain
Mauro Dragoni – Fondazione Bruno Kessler (FBK), Italy
Tomaž Erjavec – Jožef Stefan Institute, Slovenia
Miquel Esplà-Gomis – Universitat d’Alacant, Spain
Gema Ramírez – Prompsit Language Engineering, Spain
Natalia Grabar – Université de Lille, France
Jorge Gracia – University of Zaragoza, Spain
Miloš Jakubiček – University in Brno / Lexical Computing Limited, Czech Republic
John Judge – Dublin City University, Ireland
Ilan Kernerman – K Dictionaries, Israel
Iztok Kosem – University of Ljubljana, Slovenia
Simon Krek – Jožef Stefan Institute, Slovenia
Els Lefever – Ghent University, Belgium
Gudrun Magnusdottir – ESTeam AB, Sweden / Coreon GmbH, Germany
Qun Liu – Dublin City University, Ireland & Chinese Academy of Sciences, China
John P. McCrae – National University of Ireland, Galway, Ireland
Roberto Navigli – Sapienza University of Rome, Italy
Mārcis Pinnis – Tilde, Latvia
Laurette Pretorius – University of South Africa (UNISA), South Africa
Georg Rehm – German Research Center for Artificial Intelligence (DFKI), Germany
Antonio Toral – University of Groningen, Netherlands
Marco Turchi – Fondazione Bruno Kessler (FBK), Italy
Špela Vintar – University of Ljubljana, Slovenia