Uniform parsing for hyperedge replacement grammars

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Using intelligent virtual assistants for controlling employee population in workspaces is a research area that remains unexplored. This paper presents a novel application of virtual humans to enforce Covid-19 safety measures in a corporate workplace. For t ...

This paper presents a methodology for eliciting the behavioural model of purchasers' decision-making in a supply chain environment. The objective of the work is to explicitly describe the relationship between a human user's behaviour and the resulting perf ...

We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical ...

Many of the currently best-known approximation algorithms for NP-hard optimization problems are based on Linear Programming (LP) and Semi-definite Programming (SDP) relaxations. Given its power, this class of algorithms seems to contain the most favourable ...

Soft Magnetic Composites (SMCs) have huge application potential in electrical devices. With the development of additive manufacturing (AM), the properties of SMCs can be boosted. It is therefore required an optimization algorithm to design SMCs considering ...

Many software systems consist of data processing components that analyse large datasets to gather information and learn from these. Often, only part of the data is relevant for analysis. Data processing systems contain an initial preprocessing step that fi ...

While theoretical and empirical insights suggest that the capacity to represent and process complex syntax is crucial in language as well as other domains, it is still unclear whether specific parsing mechanisms are also shared across domains. Focusing on ...

For a long time, natural language processing (NLP) has relied on generative models with task specific and manually engineered features. Recently, there has been a resurgence of interest for neural networks in the machine learning community, obtaining state ...

In this work, we present a simple biometric indexing scheme which is binning and retrieving cancelable deep face templates based on frequent binary patterns. The simplicity of the proposed approach makes it applicable to unprotected as well as protected, i ...

We consider from a practical perspective the problem of checking equivalence of context-free grammars. We present techniques for proving equivalence, as well as techniques for finding counter-examples that establish non-equivalence. Among the key building ...

There are increasing interests in document layout representation learning and understanding. Transformer, with its great power, has become the mainstream model architecture and achieved promising results in this area. As elements in a document layout consi ...

Previous works on age of information and erasure channels have dealt with specific models and computed the average age or average peak age for certain settings. In this paper, given a source that produces a letter every T-s seconds and an erasure channel t ...

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount of data annotation to achieve good performance, which stops these models from ...

Kinetic models of metabolism relate metabolic fluxes, metabolite concentrations and enzyme levels through mechanistic relations, rendering them essential for understanding, predicting and optimizing the behaviour of living organisms. However, due to the la ...

Parsers are ubiquitous in computing, and many applications depend on their performance for decoding data efficiently. Parser combinators are an intuitive tool for writing parsers: tight integration with the host language enables grammar specifications to b ...

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from keypoint correspondences established between monocular 2D images. Current NRSfM methods lack statistical robustness, which is the ability to cope with correspondence errors. T ...

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show that data heteroge ...

Parser combinators provide an elegant way of writing parsers: parser implementations closely follow the structure of the underlying grammar, while accommodating interleaved host language code for data processing. However, the host language features used fo ...

To shrink the environmental footprint of housing, reducing dwellings' size is key. There is agreement among scholars on the measures that should be taken to achieve this goal, however their effectiveness and effects have not been sufficiently investigated. ...

Uniform parsing for hyperedge replacement grammars

Chat with Graph Search

Virtual Safety Assistant: An Efficient Tool for Ensuring Safety During Covid-19 Pandemic

A pilot study on eliciting human operations decision in purchasing and measuring their impact on supply chain efficiency

An Accelerated First-Order Method for Non-convex Optimization on Manifolds

Strengths and Limitations of Linear Programming Relaxations

Topology Optimization of Soft Magnetic Composites with Integer Programming

Specialising Parsers for Queries

Musical Garden Paths: Evidence for Syntactic Revision Beyond the Linguistic Domain

Word Sequence Modeling using Deep Learning : an End-to-end Approach and its Applications

Indexing Protected Deep Face Templates by Frequent Binary Patterns

Automating Grammar Comparison

Exploring Heterogeneous Feature Representation for Document Layout Understanding

Optima Age Over Erasure Channels

Leveraging Self-Supervision for Cross-Domain Crowd Counting

Reconstructing Kinetic Models for Dynamical Studies of Metabolism using Generative Adversarial Networks

Staged parser combinators for efficient data processing

Robust Isometric Non-Rigid Structure-From-Motion

Staged Parser Combinators for Efficient Data Processing

Implicit Gradient Alignment in Distributed and Federated Learning

Accelerating parser combinators with macros

Shrinking Housing's Size: Using Agent-Based Modelling to Explore Measures for a Reduction of Floor Area Per Capita