Header logo is
Institute Talks

Using Wikipedia Edits in Low Resource Grammatical Error Correction

  • 25 June 2019 • 14:30 15:15
  • Adriane Boyd
  • PS-Aquarium

We develop a grammatical error correction system for German using a small gold corpus augmented with edits extracted from Wikipedia revision history. We extend the automatic error annotation tool ERRANT (Bryant et al., 2017) for German and use it to analyze both gold corrections and Wikipedia edits (Grundkiewicz and Junczys-Dowmunt, 2014) in order to select as additional training data Wikipedia edits containing grammatical corrections similar to those in the gold corpus. Using a neural machine translation approach (Chollampatt and Ng, 2018), we evaluate the contribution of Wikipedia edits and find that carefully selected Wikipedia edits increase performance by over 5%.

Organizers: Jean-Claude Passy

Programming Intelligence through Geometry, Topology, and Anisotropy

  • 28 June 2019 • 11:00 12:00
  • Prof. Shu Yang
  • 2P04

Geometry is concerned with the properties of configurations of points, lines, and circles, while topology is concerned with space, dimension, and transformation. Geometry is also materials independent and scale invariant. By introducing holes and cuts in 2D sheets, we demonstrate dramatic shape change and super-conformability via expanding or collapsing of the hole arrays without deforming individual lattice units. When choosing the cuts and geometry correctly, we show folding into the third dimension, known as kirigami. The kirigami structures can be rendered pluripotent, that is changing into different 3D structures from the same 2D sheet. We explore their potential applications in energy efficient building facade, super-stretchable and shape conformable energy storage devices and medical devices, as well as bioinspired robotics. Programmable shape-shifting materials can take different physical forms to achieve multifunctionality in a dynamic and controllable manner. Through designs of geometric surface patterns, e.g. microchannels, we program the orientational elasticity in liquid crystal elastomers (LCEs), to direct folding of the 2D sheets into 3D shapes, which can be triggered by heat, light, and electric field. Taking this knowledge of guided inhomogeneous local deformations in LCEs, we then tackle the inverse problem – pre-programming geometry on a flat sheet to take an arbitrary desired 3D shape. Lastly, I will show the prospective of taking geometry to create smart fabrics and tendon-like filaments for soft robotic applications.

Uri Shalit - TBA

IS Colloquium
  • 08 July 2019 • 11:15 a.m. 12:15 a.m.
  • Uri Shalit

Organizers: Krikamol Muandet

Haptic Engineering and Science at Multiple Scales

IS Colloquium
  • 20 June 2018 • 11:00 12:00
  • Yon Visell, PhD
  • MPI-IS Stuttgart, Heisenbergstr. 3, Room 2P4

I will describe recent research in my lab on haptics and robotics. It has been a longstanding challenge to realize engineering systems that can match the amazing perceptual and motor feats of biological systems for touch, including the human hand. Some of the difficulties of meeting this objective can be traced to our limited understanding of the mechanics, and to the high dimensionality of the signals, and to the multiple length and time scales - physical regimes - involved. An additional source of richness and complication arises from the sensitive dependence of what we feel on what we do, i.e. on the tight coupling between touch-elicited mechanical signals, object contacts, and actions. I will describe research in my lab that has aimed at addressing these challenges, and will explain how the results are guiding the development of new technologies for haptics, wearable computing, and robotics.

Organizers: Katherine J. Kuchenbecker

Less-artificial intelligence

  • 18 June 2018 • 15:00 16:00
  • Prof. Dr. Matthias Bethge
  • MPI-IS Stuttgart - 2R04

  • Karl Rohe
  • MPI IS Lecture Hall (N0.002)

This paper uses the relationship between graph conductance and spectral clustering to study (i) the failures of spectral clustering and (ii) the benefits of regularization. The explanation is simple. Sparse and stochastic graphs create a lot of small trees that are connected to the core of the graph by only one edge. Graph conductance is sensitive to these noisy "dangling sets." Spectral clustering inherits this sensitivity. The second part of the paper starts from a previously proposed form of regularized spectral clustering and shows that it is related to the graph conductance on a "regularized graph." We call the conductance on the regularized graph CoreCut. Based upon previous arguments that relate graph conductance to spectral clustering (e.g. Cheeger inequality), minimizing CoreCut relaxes to regularized spectral clustering. Simple inspection of CoreCut reveals why it is less sensitive to small cuts in the graph. Together, these results show that unbalanced partitions from spectral clustering can be understood as overfitting to noise in the periphery of a sparse and stochastic graph. Regularization fixes this overfitting. In addition to this statistical benefit, these results also demonstrate how regularization can improve the computational speed of spectral clustering. We provide simulations and data examples to illustrate these results.

Organizers: Damien Garreau

  • Adrián Javaloy
  • S2 seminar room

The problem of text normalization is simple to understand: transform a given arbitrary text into its spoken form. In the context of text-to-speech systems – that we will focus on – this can be exemplified by turning the text “$200” into “two hundred dollars”. Lately, the interest of solving this problem with deep learning techniques has raised since it is a highly context-dependent problem that is still being solved by ad-hoc solutions. So much so that Google even started a contest in the web Kaggle to solve this problem. In this talk we will see how this problem has been approached as part of a Master thesis. Namely, the problem is tackled as if it were an automatic translation problem from English to normalized English, and so the architecture proposed is a neural machine translation architecture with the addition of traditional attention mechanisms. This network is typically composed of an encoder and a decoder, where both of them are multi-layer LSTM networks. As part of this work, and with the aim of proving the feasibility of convolutional neural networks in natural-language processing problems, we propose and compare different architectures for the encoder based on convolutional networks. In particular, we propose a new architecture called Causal Feature Extractor which proves to be a great encoder as well as an attention-friendly architecture.

Organizers: Philipp Hennig

  • Prof. Andrew Blake
  • Ground Floor Seminar Room N0.002

Organizers: Ahmed Osman

Learning Representations for Hyperparameter Transfer Learning

IS Colloquium
  • 11 June 2018 • 11:15 12:15
  • Cédric Archambeau
  • MPI IS Lecture Hall (N0.002)

Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization, such as hyperparameter optimization. Typically, BO relies on conventional Gaussian process regression, whose algorithmic complexity is cubic in the number of evaluations. As a result, Gaussian process-based BO cannot leverage large numbers of past function evaluations, for example, to warm-start related BO runs. After a brief intro to BO and an overview of several use cases at Amazon, I will discuss a multi-task adaptive Bayesian linear regression model, whose computational complexity is attractive (linear) in the number of function evaluations and able to leverage information of related black-box functions through a shared deep neural net. Experimental results show that the neural net learns a representation suitable for warm-starting related BO runs and that they can be accelerated when the target black-box function (e.g., validation loss) is learned together with other related signals (e.g., training loss). The proposed method was found to be at least one order of magnitude faster than competing neural network-based methods recently published in the literature. This is joint work with Valerio Perrone, Rodolphe Jenatton, and Matthias Seeger.

Organizers: Isabel Valera

  • Prof. Martin Spindler
  • MPI IS Lecture Hall (N0.002)

In this talk first an introduction to the double machine learning framework is given. This allows inference on parameters in high-dimensional settings. Then, two applications are given, namely transformation models and Gaussian graphical models in high-dimensional settings. Both kind of models are widely used by practitioners. As high-dimensional data sets become more and more available, it is important to allow situations where the number of parameters is large compared to the sample size.

  • Prof. Martin Spindler
  • MPI IS Lecture Hall (N0.002)

In this talk first an introduction to the double machine learning framework is given. This allows inference on parameters in high-dimensional settings. Then, two applications are given, namely transformation models and Gaussian graphical models in high-dimensional settings. Both kind of models are widely used by practitioners. As high-dimensional data sets become more and more available, it is important to allow situations where the number of parameters is large compared to the sample size.

Organizers: Philipp Geiger

  • Dr. Greg Byrnes
  • Room 3P02 - Stuttgart

Gliding evolved at least nine times in mammals. Despite the abundance and diversity of gliding mammals, little is known about their convergent morphology and mechanisms of aerodynamic control. Many gliding animals are capable of impressive and agile aerial behaviors and their flight performance depends on the aerodynamic forces resulting from airflow interacting with a flexible, membranous wing (patagium). Although the mechanisms that gliders use to control dynamic flight are poorly understood, the shape of the gliding membrane (e.g., angle of attack, camber) is likely a primary factor governing the control of the interaction between aerodynamic forces and the animal’s body. Data from field studies of gliding behavior, lab experiments examining membrane shape changes during glides and morphological and materials testing data of gliding membranes will be presented that can aid our understanding of the mechanisms gliding mammals use to control their membranous wings and potentially provide insights into the design of man-made flexible wings.

Organizers: Metin Sitti Ardian Jusufi

Lessons from the visual system to understand (and help) the brain

IS Colloquium
  • 08 June 2018 • 11:00 12:00
  • Prof. Javier Cudeiro
  • MPI-IS lecture hall (N0.002)

Visual perception involves a complex interaction between feedforward and feedback processes. A mechanistic understanding of these processing, and its limitations, is a necessary first step towards elucidating key aspects of perceptual functions and dysfunctions. In this talk, I will review our ongoing effort towards the understanding of how feedback visual processing operates at the level of the thalamus, a dynamic relay station halfway between the retina and the cortex. I will present experimental evidence from several recent electrophysiology studies performed on subjects engaged in visual detection tasks. The results show that modulatory driving provided by top-down processes (the feedback from primary visual cortex) critically influences the ongoing thalamic activity and shapes the message to be delivered to the cortex. When neuromodulatory techniques (Transcranial Magnetic Stimulation or static magnetic fields) are used to transiently disrupt cortical activity two very interesting effects show up: (1) alterations in stimulus detection and (2) the spatial properties of thalamic receptive fields are dramatically modified. Finally, I will show how sensory information can be a powerful tool to interact with the motor system and re-organize altered patterns of movement in neurological disorders such as Parkinson's disease.

Organizers: Daniel Cudeiro