DeepAI AI Chat
Log In Sign Up

Concept Matching for Low-Resource Classification

by   Federico Errica, et al.

We propose a model to tackle classification tasks in the presence of very little training data. To this aim, we approximate the notion of exact match with a theoretically sound mechanism that computes a probability of matching in the input space. Importantly, the model learns to focus on elements of the input that are relevant for the task at hand; by leveraging highlighted portions of the training data, an error boosting technique guides the learning process. In practice, it increases the error associated with relevant parts of the input by a given factor. Remarkable results on text classification tasks confirm the benefits of the proposed approach in both balanced and unbalanced cases, thus being of practical use when labeling new examples is expensive. In addition, by inspecting its weights, it is often possible to gather insights on what the model has learned.


EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

We present EDA: easy data augmentation techniques for boosting performan...

Knowledge-Aware Meta-learning for Low-Resource Text Classification

Meta-learning has achieved great success in leveraging the historical le...

An Amharic News Text classification Dataset

In NLP, text classification is one of the primary problems we try to sol...

Multinomial Adversarial Networks for Multi-Domain Text Classification

Many text classification tasks are known to be highly domain-dependent. ...

Distribution Matching for Rationalization

The task of rationalization aims to extract pieces of input text as rati...

Model Stability with Continuous Data Updates

In this paper, we study the "stability" of machine learning (ML) models ...

A Marketplace for Data: An Algorithmic Solution

In this work, we aim to create a data marketplace; a robust real-time ma...