Rehabilitation of Count-based Models for Word Vector Representations

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.

This paper examines how the European press dealt with the no-vax reactions against the Covid-19 vaccine and the dis- and misinformation associated with this movement. Using a curated dataset of 1786 articles from 19 European newspapers on the anti-vaccine ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

Robustness of medical image classification models is limited by its exposure to the candidate disease classes. Generalized zero shot learning (GZSL) aims at correctly predicting seen and unseen classes and most current GZSL approaches have focused on the s ...

This paper explores a novel application of textual semantic similarity to user-preference representation for rating prediction. The approach represents a user's preferences as a graph of textual snippets from review text, where the edges are defined by sem ...

Speech recognition-based applications upon the advancements in artificial intelligence play an essential role to transform most aspects of modern life. However, speech recognition in real-life conditions (e.g., in the presence of overlapping speech, varyin ...

This study presents a self-supervised Bayesian Neural Network (BNN) framework using air-borne Acoustic Emission (AE) to identify different Laser Powder Bed Fusion (LPBF) process regimes such as Lack of Fusion, conduction mode, and keyhole without ground-tr ...

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous Graph Neural Networks (GNN) require a large number of labeled ...

Network alignment is the task of identifying topologically and semantically similar nodes across (two) different networks. It plays an important role in various applications ranging from social network analysis to bioinformatic network interactions. Howeve ...

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

The objective of this study was to evaluate the effect of Motor Imagery (MI) training on language comprehension. In line with literature suggesting an intimate relationship between the language and the motor system, we proposed that a MI-training could imp ...

Approaches for estimating the similarity between individual publications are an area of long -standing interest in the scientometrics and informetrics communities. Traditional techniques have generally relied on references and other metadata, while text mi ...

In this work we introduce a manifold learning-based method for uncertainty quantification (UQ) in systems describing complex spatiotemporal processes. Our first objective is to identify the embedding of a set of high-dimensional data representing quantitie ...

In situ scanning transmission electron microscopy enables observation of the domain dynamics in ferroelectric materials as a function of externally applied bias and temperature. The resultant data sets contain a wealth of information on polarization switch ...

We discuss some properties of generative models for word embeddings. Namely, (Arora et al., 2016) proposed a latent discourse model implying the concentration of the partition function of the word vectors. This concentration phenomenon led to an asymptotic ...

Most of the Natural Language Processing (NLP) algorithms involve use of distributed vector representations of linguistic units (primarily words and sentences) also known as embeddings in one way or another. These embeddings come in two flavours namely, sta ...

Topic models are useful tools for analyzing and interpreting the main underlying themes of large corpora of text. Most topic models rely on word co-occurrence for computing a topic, i.e., a weighted set of words that together represent a high-level semanti ...

With the current exponential growth of video-based social networks, video retrieval using natural language is receiving ever-increasing attention. Most existing approaches tackle this task by extracting individual frame-level spatial features to represent ...

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech recognition. Up to ...

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods learn representations that cannot be interpreted in a straightforward way and that are relat ...

We describe the DCU-EPFL submission to the IWPT 2021 Parsing Shared Task: From Raw Text to Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilitative ...

Rehabilitation of Count-based Models for Word Vector Representations

Chat with Graph Search

Examining European Press Coverage of the Covid-19 No-Vax Movement: An NLP Framework

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Class Specific Feature Disentanglement and Text Embeddings for Multi-label Generalized Zero Shot CXR Classification

KNNs of Semantic Encodings for Rating Prediction

Sparse Autoencoders for Speech Modeling and Recognition

Self-Supervised Bayesian representation learning of acoustic emissions from laser powder bed Fusion process for in-situ monitoring

Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining

Network Alignment With Holistic Embeddings

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Kinesthetic motor-imagery training improves performance on lexical-semantic access

Robustness, replicability and scalability in topic modelling

Manifold Learning-Based Polynomial Chaos Expansions For High-Dimensional Surrogate Models

Latent Mechanisms of Polarization Switching from In Situ Electron Microscopy Observations

Further results on latent discourse models and word embeddings

Learning computationally efficient static word and sentence representations

Self-Supervised Neural Topic Modeling

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval

Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing

node2coords: Graph Representation Learning with Wasserstein Barycenters

The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task