Timeline generation is a summarisation task which transforms a narrative, roughly chronological input text into a set of timestamped summary sentences, each expressing an atomic historical event. We present a methodology for evaluating systems which create such timelines, based on a novel corpus consisting of 36 humancreated timelines. Our evaluation relies on deep semantic units which we call ...

A key challenge in computational narrative is story generation. In this paper we focus on analogy-based story generation, and, specifically, on how to generate both story and text using analogy. We present a dual representation formalism where a human-understandable representation (composed of English sentences) and a computer-understandable representation (consisting in a graph) are linked tog...

This paper describes a word and phrase alignment approach based on a dependency analysis of French/English parallel corpora, referred to as alignment by “syntax-based propagation.” Both corpora are analysed with a deep and robust dependency parser. Starting with an anchor pair consisting of two words that are translations of one another within aligned sentences, the alignment link is propagated...

We describe a package that performs inferences for the probabilistic description logic crALC: given a terminology consisting of a set of sentences in crALC, and a set of assertions, the package computes the probability of additional assertions using an approximate variational method. We briefly review the essentials of crALC, mention some recent applications, and describe the package. We then d...