We present a dataset of manually annotated relationships between characters in literary texts, in order to support the training and evaluation of automatic methods for relation type prediction in this domain (Makazhanov et al., 2014; Kokkinakis, 2013) and the broader computational analysis of literary character (Elson et al., 2010; Bamman et al., 2014; Vala et al., 2015; Flekova and Gurevych, 2...

This paper discusses the concept of semantic repetition in literary texts, that is, the recurrence of elements of meaning, possibly in the absence of repeated formal elements. A typology of semantic repetition is presented, as well as a framework for analysis based on the use of threaded Directed Acyclic Graphs. This model is applied to the script for the movie Groundhog Day. It is shown first ...

We study temporal networks of characters in literature focusing on Alice’s Adventures in Wonderland (1865) by Lewis Carroll and the anonymous La Chanson de Roland (around 1100). The former, one of the most influential pieces of nonsense literature ever written, describes the adventures of Alice in a fantasy world with logic plays interspersed along the narrative. The latter, a song of heroic de...

Currently, there is some scientific interest on studying creativity and how it can be modeled by computer programs. One of the active subareas focuses on the generation of text, with some prior success systems. In this paper, we describe an example of this kind of system that automatically generates texts related to Greek mythology. We have elaborated on ideas coming from computer creativity, s...

In this work a machine learning oriented perspective on computer aided support to literary analysis is presented. A representation of narrative phenomena is proposed and an automatic annotation model for such phenomena is trained on texts provided by a critic. As a short-term research task, we studied how the observable textual piece of evidence impact on the learning agent capabilities, over a...

The MULINCO project (MUltiLINgual Corpus of the University of Copenhagen) started early 2005. The purpose of this crossdisciplinary project is to create a corpus platform for education and research in monolingual and translation studies. The project covers two main types of corpus texts: literary and non-literary. The platform is being developed using available tools as far as possible, and int...

Given multiple corrupted versions of the same text, as is common with ancient manuscripts, we wish to reconstruct the original text from which the extant corrupted versions were copied (typically via latent intermediary versions). This is a challenge of cardinal importance in the humanities. We use a variant of expectation-maximization (EM), to solve this problem. We prove the efficacy of our m...

This paper describes a query system on texts and literary material with advanced information retrieval tools. As a test bed we chose the electronic version of Dante’s Inferno, manually tagged using XML, enriched with a domain ontology describing the historical, social and cultural context represented as a separate XML document.