Related papers: Text Classification with Few Examples using Contro…

In the context of few-shot learning, one cannot measure the generalization ability of a trained classifier using validation sets, due to the small number of labeled samples. In this paper, we are interested in finding alternatives to answer…

A well-known but rarely used approach to text categorization uses conditional entropy estimates computed using data compression tools. Text affinity scores derived from compressed sizes can be used for classification and ranking tasks, but…

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…

In this paper, we explore text classification with extremely weak supervision, i.e., only relying on the surface text of class names. This is a more challenging setting than the seed-driven weak supervision, which allows a few seed words…

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…

The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential…

Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. We show that examples that depend critically on a rarer…

We consider the supervised training setting in which we learn task-specific word embeddings. We assume that we start with initial embeddings learned from unlabelled data and update them to learn task-specific embeddings for words in the…

Textual representations based on pre-trained language models are key, especially in few-shot learning scenarios. What makes a representation good for text classification? Is it due to the geometric properties of the space or because it is…

Obtaining labelled data in a particular context could be expensive and time consuming. Although different algorithms, including unsupervised learning, semi-supervised learning, self-learning have been adopted, the performance of text…

Recently, few-shot video classification has received an increasing interest. Current approaches mostly focus on effectively exploiting the temporal dimension in videos to improve learning under low data regimes. However, most works have…

The task of text classification is usually divided into two stages: {\it text feature extraction} and {\it classification}. In this standard formalization categories are merely represented as indexes in the label vocabulary, and the model…

Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of annotated data which may not be available. To overcome the…

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…

Recent advancements in language representation learning primarily emphasize language modeling for deriving meaningful representations, often neglecting style-specific considerations. This study addresses this gap by creating generic,…

In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vision. In a first…

We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but random parameterizations. Our aim is to put sentence embeddings on more solid footing by 1)…

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent and meaningless…

The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data…