Output Subword-based representations for language modeling 

Get Complete Project Material File(s) Now! » The computational bottleneck The main limitation of neural networks language models is their expensive computational cost. This was already pointed out by Bengio et al. (2003). Schwenk and Gauvain (2004) provide, for the...

Heterogeneity in parsing: monolingual and cross-lingual issues 

Get Complete Project Material File(s) Now! » Improving the classifiers: from the averaged perceptron to Stack-LSTMs Since Collins and Roark (2004), the main classifier used to predict transitions in parsing has been the averaged multi-class perceptron. The multi-class perceptron is...

Dagger: Digging for Interesting Aggregates in RDF Graphs

Get Complete Project Material File(s) Now! » Research environment We describe below the research environment of the internship: the Cedar team of Inria. Inria Inria, the French Institute for Research in Computer Science and Automation (Insti-tut national de recherche en...

Improving TQ generation in MT into English: our post-edition approach

Get Complete Project Material File(s) Now! » Sequence-to-sequence NMT with attention The major problem with the basic sequence-to-sequence model was the reliance on a xed-length, static representation of the input sequence for all decoding steps. This has several implications. Firstly,...

Study on User Cohabitation 

Get Complete Project Material File(s) Now! » Multi-user Immersive Display Immersive display constitutes a main component of immersive virtual environment as the visual sense plays a predominant role in user’s perception process. As mentioned in previous chapter (section 1.2.3.1), immersive...

Pros and Cons of End-to-End Deep Reinforcement Learning 

Get Complete Project Material File(s) Now! » A BRIEF HISTORY OF STATE ESTIMATION Understanding the current state of controlled systems is part of the requirement to learn tasks, such as those of RL. In a context where the state is...

Procedures for training learners in the ‘Skilled Use of Interaction Strategies’ 

Get Complete Project Material File(s) Now! » From teacher-student communication to student-student communication in small group tasks As established in the first section of this study, for learners to effectively learn a foreign language they must actively take part in...

Robustness of Deep Neural Networks to Erasures in a Reading Task 

Get Complete Project Material File(s) Now! » Willshaw Networks and biological considerations Willshaw networks are models of associative memories constituted of a given number of neurons. A stored message, or memory, is a combination of nodes taken in this set....

Co-typing of a data exchange setting and co-typing graph

Get Complete Project Material File(s) Now! » Relational schema and dependencies We assume an infinite set of attribute names A Va. A relational schema is a tuple R = (R; attrs; fd; ind) where R is a finite set of...

Independent Random Phone-Call Model

Get Complete Project Material File(s) Now! » Overview of Gossip Protocols Classic Results In this section we brie y review what is known about the rumor spreading pro-cesses. We start by clarifying in which processes refer to rumor spreading and...