Title: Inducing Interpretable Word Senses for WSD and Enrichment of Lexical Resources

Abstract: In this talk, we will discuss induction of sparse and dense
word sense representations using graph-based approaches and
distributional models. Induced senses are represented by a vector, but
also a set of hypernyms, images, and usage examples, derived in an
unsupervised and knowledge-free manner, which ensure interpretability
of the discovered senses by humans. We showcase the usage of the
induced representations for the tasks of word sense disambiguation and
enrichment of lexical resources, such as WordNet.

Bio: Alexander Panchenko is a Postdoctoral Researcher in the Language
Technology Group at the University of Hamburg, Germany. His background
is almost a decade of research and developments in the field of
NLP. He worked on a range of problems and tasks, such as semantic
relatedness, word sense disambiguation, and induction, sentiment
analysis, gender detection, taxonomy induction, etc. Prior to the
appointment in Hamburg, Alexander was a a Postdoctoral Researcher at
TU Darmstadt and Research Engineer at a start-up focusing on
large-scale NLP applied to social networks. He received his PhD in
Computational Linguistics from the Universite catholique de Louvain,
Belgium in 2013 and an Engineering degree in Computer Science from
Moscow State Technical University in 2008. Alexander is interested in
representation learning, distributional semantics and word sense
induction and disambiguation. He has (co-)authored more than 40
peer-reviewed research publications, including papers in top-tier
conference proceedings, such as ACL, EMNLP, EACL, and ECIR. He
received (with co-authors) the best paper award at the `Representation
Learning for NLP' (RepL4NLP) workshop at ACL 2016. He co-organised two
shared tasks on semantic relatedness and word sense induction
evaluation for the Russian language (RUSSE'15 and RUSSE'18). He is a
founding co-editor of a data science conference on Analysis of Social
Networks, Images, and Texts (AIST) with the proceedings published in
Springer LNCS series.