Topics of Interest

This workshop aims to offer a forum for discussions to researchers that 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.

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 (knowledge graphs, ontologies, thesaurie) generation with MT
  • Multilingual and Crosslingual Information extraction for MT
  • Injection of multilingual domain-specific knowledge into MT
  • Provenance of multiple multilingual knowledge bases for MT
  • MT used for cross-lingual information access, search and retrieval
  • Enhancements to OOV word translation for NMT
  • Exploiting relational knowledge graphs for Neural MT
  • Addressing variations of terms in MT
  • Multilingual knowledge generation for under-resourced languages with MT
  • Enriching MT with Linked Data (e.g. BabelNet, DBpedia, UMLS)
  • Multilingual terminology and linguistic resource development, integration and mapping in a Linked Data context for MT
  • Multilingual Semantic Web and Linked Data use cases