Recurrent Neural Network for Text Classification with Multi-Task Learning

Abstract

Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we use the multi-task learning framework to jointly learn across multiple related tasks. Based on recurrent neural network, we propose three different mechanisms of sharing information to model text with task-specific and shared layers. The entire network is trained jointly on all these tasks. Experiments on four benchmark text classification tasks show that our proposed models can improve the performance of a task with the help of other related tasks.

IJCAI 2016

References in corpus (2)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• A Convolutional Neural Network for Modelling Sentences

Cited by in corpus (101)

• Pre-trained Models for Natural Language Processing: A Survey
• Multi-Task Learning with Deep Neural Networks: A Survey
• Deep Learning Based Text Classification: A Comprehensive Review
• Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
• A Survey Of Cross-lingual Word Embedding Models
• EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
• No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence
• Pretrained Domain-Specific Language Model for General Information Retrieval Tasks in the AEC Domain
• Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks
• A Survey on Text Classification: From Shallow to Deep Learning
• How to Fine-Tune BERT for Text Classification?
• Paradigm Shift in Natural Language Processing
• Representation Learning for Natural Language Processing
• Deep Learning for Technical Document Classification
• DAVE: Deriving Automatically Verilog from English
• Graph Neural Networks for Natural Language Processing: A Survey
• An ensemble deep learning technique for detecting suicidal ideation from posts in social media platforms
• TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
• Unsupervised Law Article Mining based on Deep Pre-Trained Language Representation Models with Application to the Italian Civil Code
• A Survey of Optimization Methods from a Machine Learning Perspective
• A Text Classification-Based Approach for Evaluating and Enhancing the Machine Interpretability of Building Codes
• Refiner: Refining Self-attention for Vision Transformers
• Keyphrase Extraction from Disaster-related Tweets
• A Neural Compositional Paradigm for Image Captioning
• Natural Language Adversarial Defense through Synonym Encoding
• Hate Speech Detection on Vietnamese Social Media Text using the Bi-GRU-LSTM-CNN Model
• Progress Notes Classification and Keyword Extraction using Attention-based Deep Learning Models with BERT
• Towards Explainable NLP: A Generative Explanation Framework for Text Classification
• Transformer to CNN: Label-scarce distillation for efficient text classification
• Corporate Bankruptcy Prediction with Domain-Adapted BERT
• Improving Sentiment Analysis with Multi-task Learning of Negation
• Multi-Task Bidirectional Transformer Representations for Irony Detection
• Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers
• NetReduce: RDMA-Compatible In-Network Reduction for Distributed DNN Training Acceleration
• Simplified DOM Trees for Transferable Attribute Extraction from the Web
• Recursive Graphical Neural Networks for Text Classification
• Identifying Harm Events in Clinical Care through Medical Narratives
• Efficient Feature Selection techniques for Sentiment Analysis
• Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
• Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model
• Label-guided Learning for Text Classification
• Rethinking Recurrent Neural Networks and Other Improvements for Image Classification
• Meta-Learning Multi-task Communication
• Recurrent neural network-based user authentication for freely typed keystroke data
• Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology
• Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN
• Understanding COVID-19 Vaccine Campaign on Facebook using Minimal Supervision
• An Attention-Gated Convolutional Neural Network for Sentence Classification
• Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Label-Aware Distribution Calibration for Long-tailed Classification
• #phramacovigilance - Exploring Deep Learning Techniques for Identifying Mentions of Medication Intake from Twitter
• Arabic aspect based sentiment analysis using bidirectional GRU based models
• DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect
• Interpretable Text Classification Using CNN and Max-pooling
• NewB: 200,000+ Sentences for Political Bias Detection
• Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots
• Deep Search Query Intent Understanding
• Empirical Evaluation of RNN Architectures on Sentence Classification Task
• Dual Adversarial Co-Learning for Multi-Domain Text Classification
• CHECKED: Chinese COVID-19 Fake News Dataset
• Dual-Attention Graph Convolutional Network
• Development of deep learning algorithms to categorize free-text notes pertaining to diabetes: convolution neural networks achieve higher accuracy than support vector machines
• Improving Aspect-Level Sentiment Analysis with Aspect Extraction
• Meta-Embeddings Based On Self-Attention
• Preliminary Steps Towards Federated Sentiment Classification
• Cross-lingual Data Transformation and Combination for Text Classification
• Hybrid Low-order and Higher-order Graph Convolutional Networks
• Neural Text Classification by Jointly Learning to Cluster and Align
• Multi-Task Deep Learning for Legal Document Translation, Summarization and Multi-Label Classification
• Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning
• TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis
• Online publication of court records: circumventing the privacy-transparency trade-off
• Self-supervised Regularization for Text Classification
• Does a Hybrid Neural Network based Feature Selection Model Improve Text Classification?
• Financial ticket intelligent recognition system based on deep learning
• A Deep Neural Framework for Contextual Affect Detection
• Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge
• Indoor Distance Estimation using LSTMs over WLAN Network
• Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing
• Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts
• Joint Embedding of Words and Category Labels for Hierarchical Multi-label Text Classification
• A Spark ML driven preprocessing approach for deep learning based scholarly data applications
• TDRE: A Tensor Decomposition Based Approach for Relation Extraction
• Multi-task Learning for Low-resource Second Language Acquisition Modeling
• Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification
• Enhancing Interpretable Clauses Semantically using Pretrained Word Representation
• Sparse tree-based initialization for neural networks
• Graph Convolutional Network with Generalized Factorized Bilinear Aggregation
• geoGAT: Graph Model Based on Attention Mechanism for Geographic Text Classification
• An Attention Ensemble Approach for Efficient Text Classification of Indian Languages
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures
• DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings
• Item Tagging for Information Retrieval: A Tripartite Graph Neural Network based Approach
• Relation Detection for Indonesian Language using Deep Neural Network -- Support Vector Machine
• Meta-Embedding as Auxiliary Task Regularization
• Translation, Sentiment and Voices: A Computational Model to Translate and Analyse Voices from Real-Time Video Calling
• Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning
• Centroid estimation based on symmetric KL divergence for Multinomial text classification problem
• A cost-reducing partial labeling estimator in text classification problem
• Parallel Intent and Slot Prediction using MLB Fusion