On the 5th of June, Textkernel will be sponsoring and presenting a poster at the workshop on Vector Space Modeling (VSM) during the 2015 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT) in Denver, Colorado.
Modern Natural Language Processing (NLP) has evolved over the years from approaches based on pure symbolic analysis of language to statistical methods allowing ‘soft’ reasoning. Over the last decade, vector spaces have been included to represent and analyse language. This has been successful in different areas of NLP such as syntax and semantics.
The workshop will explore the state of the art in Deep Learning and distributional compositional semantics with a focus on applications for analysing language.
The R&D team at Textkernel has already been putting this line of research into practice: they recently started implementing the use of vector spaces (Deep Learning) into its cv parsing (resume parsing) software. Textkernel’s research engineer Carsten Lygteskov Hansen and former intern Melanie Tosik will present their paper: Word Embeddings vs Word Types for Sequence Labeling: the Curious Case of CV Parsing and show how these new methods are used to improve Textkernel’s CV parsing software.