In this paper we present the first ever, to the best of our knowledge, discourse parser for multi-party chat dialogues.Discourse in multi-party dialogues dramatically differs from monologues since threaded conversations are commonplace rendering prediction of the discourse structure compelling.Moreover, the fact that our data come from chats renders the use of syntactic and lexical information useless since people take great liberties in expressing themselves lexically and syntactically.We use the dependency parsing paradigm as has been done in the past (Muller et al., 2012;Li et al., 2014).We learn local probability distributions and then use MST for decoding.We achieve 0.680 F 1 on unlabelled structures and 0.516 F 1 on fully labeled structures which is better than many state of the art systems for monologues, despite the inherent difficulties that multi-party chat dialogues have.

In this article we present GenI, a chart based surface realisation tool implemented in Haskell. GenI takes as input a set of first order terms (the input semantics) and a grammar for a given target language (e.g., English, French, Spanish, etc.) and generates sentences in the target language, whose semantic meaning corresponds to the input semantics.The aim of the article is not so much to present GenI or to describe how it is implemented. Rather, we will focus on the aspects of functional programming (higher order functions, monads) and Haskell (typeclasses) that we found important to its design.