Pierre Roy

IJCAI Conference 2015 Conference Paper

Generating 1/f Noise Sequences as Constraint Satisfaction: The Voss Constraint

• Fran
• ccedil; ois Pachet
• Pierre Roy
• Alexandre Papadopoulos
• Jason Sakellariou

IJCAI Conference 2015 Conference Paper

Generating all Possible Palindromes from Ngram Corpora

• Alexandre Papadopoulos
• Pierre Roy
• Jean-Charles R
• eacute; gin
• Fran
• ccedil; ois Pachet

We address the problem of generating all possible palindromes from a corpus of Ngrams. Palindromes are texts that read the same both ways. Short palindromes (“race car”) usually carry precise, significant meanings. Long palindromes are often less meaningful, but even harder to generate. The palindrome generation problem has never been addressed, to our knowledge, from a strictly combinatorial point of view. The main difficulty is that generating palindromes require the simultaneous consideration of two inter-related levels in a sequence: the “character” and the “word” levels. Although the problem seems very combinatorial, we propose an elegant yet non-trivial graph structure that can be used to generate all possible palindromes from a given corpus of Ngrams, with a linear complexity. We illustrate our approach with short and long palindromes obtained from the Google Ngram corpus. We show how we can control the semantics, to some extent, by using arbitrary text corpora to bias the probabilities of certain sets of words. More generally this work addresses the issue of modelling human virtuosity from a combinatorial viewpoint, as a means to understand human creativity.

IJCAI Conference 2015 Conference Paper

Max Order: A Tale of Creativity

• Fiammetta Ghedini
• Fran
• ccedil; ois Pachet
• Pierre Roy

We present a graphic novel project aiming at illustrating current research results and issues regarding the creative process and its relation with artificial intelligence. The main character, Max Order, is an artist who symbolizes the difficulty of coming up with new, creative ideas, giving up imitation of others and finding one’s own style.

AAAI Conference 2014 Conference Paper

Avoiding Plagiarism in Markov Sequence Generation

• Alexandre Papadopoulos
• Pierre Roy
• François Pachet

Markov processes are widely used to generate sequences that imitate a given style, using random walk. Random walk generates sequences by iteratively concatenating states to prefixes of length equal or less than the given Markov order. However, at higher orders, Markov chains tend to replicate chunks of the corpus with a size possibly higher than the order, a primary form of plagiarism. The Markov order defines a maximum length for training but not for generation. In the framework of constraint satisfaction (CSP), we introduce MAXORDER. This global constraint ensures that generated sequences do not include chunks larger than a given maximum order. We exhibit an automaton that recognises the solution set, with a size linear in the size of the corpus. We propose a linear-time procedure to generate this automaton from a corpus and a given max order. We then use this automaton to achieve generalised arc consistency for the MAXORDER constraint, holding on a sequence of size n, in O(n. T) time, where T is the size of the automaton. We illustrate our approach by generating text sequences from text corpora with a maximum order guarantee, effectively controlling plagiarism.

ECAI Conference 2014 Conference Paper

Imitative Leadsheet Generation with User Constraints

• François Pachet
• Pierre Roy

We introduce the problem of generating musical leadsheets, i. e. a melody with chord labels, in the style of an arbitrary composer, that satisfy arbitrary user constraints. The problem is justified by the very nature of musical creativity, as many composers create music precisely by imitating a given style to which they add their own constraints. We propose a solution of this problem by formulating it as a Markov constraint problem. Markov constraints enable users to create stylistically imitative leadsheets that satisfy a large palette of constraints. We show that generated leadsheets are stylistically consistent by reclassifying them using Markov classifiers.

AAAI Conference 2013 Conference Paper

Enforcing Meter in Finite-Length Markov Sequences

• Pierre Roy
• Francois Pachet

ECAI Conference 2012 Conference Paper

Markov Constraints for Generating Lyrics with Style

• Gabriele Barbieri
• François Pachet
• Pierre Roy
• Mirko Degli Esposti

We address the issue of generating texts in the style of an existing author, that also satisfy structural constraints imposed by the genre of the text. We focus on song lyrics, for which structural constraints are well-defined: rhyme and meter. Although Markov processes are known to be suitable for representing style, they are difficult to control in order to satisfy non-local properties, such as structural constraints, that require long distance modeling. We show that the framework of Constrained Markov Processes allows us to precisely generate texts that are consistent with a corpus, while being controllable in terms of rhymes and meter, a result that no other technique, to our knowledge, could achieve to date. Controlled Markov processes consist in reformulating Markov processes in the context of constraint satisfaction. We describe how to represent stylistic and structural properties in terms of constraints in this framework and we provide an evaluation of our method by comparing it to both pure Markov and pure constraint-based approaches. We show how this approach can be used for the semi-automatic generation of lyrics in the style of a popular author that has the same structure as an existing song.

IJCAI Conference 2011 Conference Paper

Finite-Length Markov Processes with Constraints

• Fran
• ccedil; ois Pachet
• Pierre Roy
• Gabriele Barbieri

Many systems use Markov models to generate finite-length sequences that imitate a given style. These systems often need to enforce specific control constraints on the sequences to generate. Unfortunately, control constraints are not compatible with Markov models, as they induce long-range dependencies that violate the Markov hypothesis of limited memory. Attempts to solve this issue using heuristic search do not give any guarantee on the nature and probability of the sequences generated. We propose a novel and efficient approach to controlled Markov generation for a specific class of control constraints that 1) guarantees that generated sequences satisfy control constraints and 2) follow the statistical distribution of the initial Markov model. Revisiting Markov generation in the framework of constraint satisfaction, we show how constraints can be compiled into a non-homogeneous Markov model, using arc-consistency techniques and renormalization. We illustrate the approach on a melody generation problem and sketch some realtime applications in which control constraints are given by gesture controllers.