You are here

Language Complexity and Readability

Speaker: Aivars Glaznieks, Senior Researcher at the Institute for Specialised Communication and Multilingualism, European Academy Bolzano (EURAC)

The MADRE project is a joint project involving the University of Trento and the Digital Humanities unit at FBK. It has been funded by the Office for Equal Opportunities and Family Policies of the Autonomous Province of Trento, in order to support equal opportunities and better understand discourse on gender. 

The paper "TAF Language and Games for Story Comprehension" by Rosella Gennari, Sara Tonelli and Pierpaolo Vittorini has been accepted at Digital Intelligence 2014, the First International Scientific and Interdisciplinary Conference dedicated to digital society and cultures.

The DH reading group on multiword expressions is going to discuss the following paper:

M. Constant, M. Candito and Djame Seddah (2013) "The LIGM-Alpage Architecture for the SPMRL 2013 Shared Task: Multiword Expression Analysis and Dependency Parsing". In Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically Rich Languages. Seattle, Washington, USA. 

Speaker: Andreas van Cranenburgh, Phd student, UvA Amsterdam

Title: Literary genre classification with syntactic and lexical features

Abstract:

Federico Sangati from DH is presenting today his work on the recognition of multiword expressions using recurring tree fragments at the 2nd PARSEME general meeting, Athens, Greece.

SemEval-2014 workshop will be held in conjunction with the COLING 2014 conference.

A session will be devoted to Task 1"Evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment" organized by DH-FBK (Stefano Menini), HLT-FBK (Luisa Bentivogli) and UNITN (Marco Marelli, Marco Baroni, Raffaella Bernardi, and Roberto Zamparelli).

The DH unit has organized a reading group on different topics related to Natural Language Processing and Digital Humanities. The meetings are open to anyone, especially to students.

In the first meeting we will deal with multiword expressions, and we will discuss the paper 'Collocations and statistical analysis of n-grams' by Gunn Inger and Gisle Andersen.

Three papers accepted at LREC 2014: "CROMER: A Tool for Cross-Document Event and Entity Coreference", "Crowdsourcing for the identification of event nominals: an experiment", "A SICK cure for the evaluation of compositional distributional semantic models".

Pages