Home

LexSub is a framework for supervised all-words lexical substitution using delexicalized features [1]. This particularly means that it requires only one trained classifier that can be applied on all seen and unseen words ("all-words"). This is achieved by using features that only characterize a word's context that is independent of the lexical surface form of the word itself ("delexicalized"). This includes n-gram frequencies, for example, and distributional similarity scores.

For an introduction on how to run LexSub, see [Running LexSub].

[1] Szarvas, G., Biemann, C., and Gurevych, G. (2013): Supervised All-Words Lexical Substitution using Delexicalized Features. Proceedings of NAACL-2013, Atlanta, GA, USA [pdf] [Slides][Video]

Project Members:

• Johannes Simon (admin)
• Martin Riedl (admin)
• Seid Muhie Yimam (admin)