• Aucun résultat trouvé

Creative Natural Language Processing

N/A
N/A
Protected

Academic year: 2022

Partager "Creative Natural Language Processing"

Copied!
1
0
0

Texte intégral

(1)

Creative Natural Language Processing

Carlo Strapparava

Fondazione Bruno Kessler (FBK-irst) via Sommarive, 18

38100 Trento, Italy [email protected]

Abstract Dealing with creative language and in particular with affective, per- suasive and even humorous language has often been considered outside the scope of computational linguistics. Nonetheless it is possible to exploit current NLP techniques starting some explorations about it. We briefly review some com- putational experiences about these typical creative genres. Then we will talk about the exploitation of some extra-linguistic features: for example music and lyrics in emotion detection, and an audience-reaction tagged corpus of political speeches for the analysis of persuasive language. As further examples of practical applications, we will present a system for automatized memory techniques for vocabulary acquisition in a second language, and an application for automatizing creative naming (branding).

Short Biography Carlo Strapparava is a senior researcher at FBK-irst (Fon- dazione Bruno Kessler - Istituto per la ricerca scientifica e Tecnologica) in the Human Language Technologies Unit. His research activity covers artificial in- telligence, natural language processing, intelligent interfaces, human-computer interaction, cognitive science, knowledge-based systems, user models, adaptive hypermedia, lexical knowledge bases, word-sense disambiguation, affective com- puting and computational humour. He is the author of over 150 papers, published in scientific journals, book chapters and in conference proceedings. He also played a key role in the definition and the development of many projects funded by Eu- ropean research programmes. He regularly serves in the program committees of the major NLP conferences (ACL, EMNLP, etc.). He was executive board mem- ber of SIGLEX, a Special Interest Group on the Lexicon of the Association for Computational Linguistics (2007-2010), Senseval (Evaluation Exercises for the Semantic Analysis of Text) organisation committee (2005-2010). On June 2011, he was awarded with a Google Research Award on Natural Language Processing, specifically on the computational treatment of creative language.

Références

Documents relatifs

Natural language processing would benefit from a better understanding of human processes: as it has been said by several researchers recently, traditional ma- chine learning

2 We abstract over these different types of semantic networks with the formal notion of a directed graph G defined as a pair (V, E), where V is a finite set of elements called

This module searches a file of code or documentation for blocks of text that look like an interactive Python session, of the form you have already seen many times in this book.

We have described how we induced useful word embeddings by applying our architecture to a language modeling task trained using a large amount of unlabeled text data.. These

During the implementation of the above method, existing models for identifying the most informative components of the natural language text from the position of

This paper overviews the ef- fectiveness of instant messaging applications as a user data environment, the primary method for extracting said user data by using bots, proposes

Keywords: Natural Language Processing, Compositional Distributional Model of Meaning, Quantum Logic, Similarity Measures..

In this paper we show that is possible to represent NLP models such as Probabilistic Context Free Grammars, Probabilistic Left Corner Grammars and Hidden Markov Models