Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks

06/15/2019
by   Ahmad Aghaebrahimian, et al.
0

We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical hypothesis testing method is used to extract the most informative words for each given class. These words are used as a class description for more label-aware text classification. Intuition is to help the model to concentrate on more informative words rather than more frequent ones. The model leverages the use of label descriptions in addition to the input text to enhance text classification performance. Our method is entirely data-driven, has no dependency on other sources of information than the training data, and is adaptable to different classification problems by providing appropriate training data without major hyper-parameter tuning. We trained and tested our system on several publicly available datasets, where we managed to improve the state-of-the-art on one set with a high margin, and to obtain competitive results on all other ones.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/23/2022

Prompt-Learning for Short Text Classification

In the short text, the extreme short length, feature sparsity and high a...
research
04/06/2020

A Hierarchical Fine-Tuning Approach Based on Joint Embedding of Words and Parent Categories for Hierarchical Multi-label Text Classification

Many important classification problems in real world consist of a large ...
research
11/23/2018

Explicit Interaction Model towards Text Classification

Text classification is one of the fundamental tasks in natural language ...
research
04/02/2022

Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptions

Extreme Multi-label Text Classification (XMTC) has been a tough challeng...
research
09/01/2019

Topics to Avoid: Demoting Latent Confounds in Text Classification

Despite impressive performance on many text classification tasks, deep n...
research
04/01/2019

Summarizing Event Sequences with Serial Episodes: A Statistical Model and an Application

In this paper we address the problem of discovering a small set of frequ...
research
01/20/2018

Using Deep Learning For Title-Based Semantic Subject Indexing To Reach Competitive Performance to Full-Text

For (semi-)automated subject indexing systems in digital libraries, it i...

Please sign up or login with your details

Forgot password? Click here to reset