Natural Language Understanding Wiki

Markov logic network is a fundamental framework for probabilistic logic. It is readily implemented in some software package like Alchemy or ProbCog. However, the computational efficiency of MLN is questionable and researchers need to pay special attention (e.g. Beltagy et al., 2014[1]).

From Fahrni (2016)[2]: "Markov Logic has been recently used for various natural language processing tasks such as coreference resolution (Poon & Domingos, 2008; Bögel & Frank, 2013), sentiment analysis (Zirn et al., 2011) and joint semantic role labeling and word sense disambiguation (Meza-Ruiz & Riedel, 2009; Che & Liu, 2010)."


  1. Beltagy, I., & Mooney, R. J. (2014, June). Efficient Markov logic inference for natural language semantics. In Proceedings of AAAI 2014 Workshop on Statistical Relational AI (StarAI-14).
  2. Fahrni, Angela Petra. Joint Discourse-aware Concept Disambiguation and Clustering. Diss. 2016.
Wikipedia has an article on: Markov logic network