Description Based Text Classification with Reinforcement Learning

Abstract

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 lacks for explicit instructions on what to classify. Inspired by the current trend of formalizing NLP problems as question answering tasks, we propose a new framework for text classification, in which each category label is associated with a category description. Descriptions are generated by hand-crafted templates or using abstractive/extractive models from reinforcement learning. The concatenation of the description and the text is fed to the classifier to decide whether or not the current label should be assigned to the text. The proposed strategy forces the model to attend to the most salient texts with respect to the label, which can be regarded as a hard version of attention, leading to better performances. We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.

arXiv commentAccepted by ICML 2020

References in corpus (27)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Bidirectional Attention Flow for Machine Comprehension
• Supervised Topic Models
• Sequence Level Training with Recurrent Neural Networks
• Finding Deceptive Opinion Spam by Any Stretch of the Imagination
• Dynamic Coattention Networks For Question Answering
• A Convolutional Neural Network for Modelling Sentences
• Understanding Neural Networks through Representation Erasure
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
• The Natural Language Decathlon: Multitask Learning as Question Answering
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• DocBERT: BERT for Document Classification
• Adversarial Learning for Neural Dialogue Generation
• When Are Tree Structures Necessary for Deep Learning of Representations?
• Multi-Perspective Context Matching for Machine Comprehension
• Generative and Discriminative Text Classification with Recurrent Neural Networks
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• Aspect Level Sentiment Classification with Deep Memory Network
• Neural Speed Reading via Skim-RNN
• SGM: Sequence Generation Model for Multi-label Classification
• Entity-Relation Extraction as Multi-Turn Question Answering
• A Fast Unified Model for Parsing and Sentence Understanding
• Question Answering is a Format; When is it Useful?
• Coreference Resolution as Query-based Span Prediction

Cited by in corpus (6)

• Paradigm Shift in Natural Language Processing
• Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions
• Self-Explaining Structures Improve NLP Models
• Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
• Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
• ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information