arXiv research

Funnelling improves cross-lingual text classification accuracy.

We describe our language-independent unsupervised word sense induction system. This system only uses topic features to cluster different word senses in their global context topic space. Using unlabeled data, this system trains a latent Dirichlet allocation (LDA) topic model then uses it to infer the topics distribution…

Many methods have been used to recognize author personality traits from text, typically combining linguistic feature engineering with shallow learning models, e.g. linear regression or Support Vector Machines. This work uses deep-learning-based models and atomic features of text, the characters, to build hierarchical, …

Recently, due to the increasing popularity of social media, the necessity for extracting information from informal text types, such as microblog texts, has gained significant attention. In this study, we focused on the Named Entity Recognition (NER) problem on informal text types for Turkish. We utilized a semi-supervi…

New ASR system handles multiple languages without needing language-specific encoding.

Twitter provides an open and rich source of data for studying human behaviour at scale and is widely used in social and network sciences. However, a major criticism of Twitter data is that demographic information is largely absent. Enhancing Twitter data with user ages would advance our ability to study social network …

Entity relatedness has emerged as an important feature in a plethora of applications such as information retrieval, entity recommendation and entity linking. Given an entity, for instance a person or an organization, entity relatedness measures can be exploited for generating a list of highly-related entities. However,…

HTMLPhish detects phishing web pages using deep learning on HTML content.

NP-HMC extends HMC for nonparametric models in probabilistic programming.

Paper benchmarks mutual info estimators on diverse distributions.

Sentiment analysis (SA) is a task related to understanding people's feelings in written text; the starting point would be to identify the polarity level (positive, neutral or negative) of a given text, moving on to identify emotions or whether a text is humorous or not. This task has been the subject of several researc…

Geometric deep learning detects fake news on social media.

A new framework learns system design using neural features in function space.

Quantum machine learning models can approximate any continuous function.

In this paper we consider a problem of searching a space of predictive models for a given training data set. We propose an iterative procedure for deriving a sequence of improving models and a corresponding sequence of sets of non-linear features on the original input space. After a finite number of iterations N, the n…

A framework to compare atomistic descriptors and their transformations.

SFM uses linear models in extended feature spaces to avoid kernel issues.

Featurization improves density ratio estimation for complex data.

Paper proposes FKR-F$^2$E to make kernel regression fair.

Study characterizes cryospheric spectral feature space using joint PC+t-SNE approach.

A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes' …

SCOPE-FE improves feature engineering efficiency for high-dimensional datasets.

Gradient descent reshapes the function space of neural networks.

Invertible networks help explain decisions and identify important features.

New approach interprets machine learning models through feature space transformations.

New framework analyzes temporal features in state space models.

Proposes feature conformal prediction for broader application in semantic feature spaces.

Random feature models approximate functions in Banach spaces efficiently.

We tackle linear bandits with partially observable features, achieving sublinear regret.

This paper considers the multi-task learning problem and in the setting where some relevant features could be shared across few related tasks. Most of the existing methods assume the extent to which the given tasks are related or share a common feature space to be known apriori. In real-world applications however, it i…

Steerable neural ODEs on homogeneous spaces for equivariant feature dynamics.

This paper develops a geometric framework for SHM using feature bundles and gauge theories.

A new algorithm detects out-of-distribution samples by concentrating them in feature space.

This paper uses Reinforcement Learning to select features from a large dataset.

Paper proposes redundancy-free features for zero-shot object recognition.

FFCP improves FCP's speed without sacrificing accuracy.

A single pre-trained agent guides feature selection using knockoffs.

New method scales features for better clustering.

Improved detection of burnt areas in satellite images using evolved hyper-features.

A new algorithm interprets DR dimensions and selects features.

This paper analyzes kNN convergence over feature transformations.

Quantum machine learning for 2D classification tasks using optimized feature maps.

We add prior knowledge to deep networks to make them invariant to transformations.

PML-LFC improves PML by estimating label confidence from both feature and label spaces.

A new framework CL embeds features and labels for multi-label classification.

Improves few-shot learning for hierarchical data using hyperbolic space.

Proposes optimizing neural network ensemble diversity in feature space.

This paper makes kernels interpretable for wide feature matrices.