Natural Language Processing Advancements By Deep Learning: A Survey

Abstract

Natural Language Processing (NLP) helps empower intelligent machines by enhancing a better understanding of the human language for linguistic-based human-computer communication. Recent developments in computational power and the advent of large amounts of linguistic data have heightened the need and demand for automating semantic analysis using data-driven approaches. The utilization of data-driven strategies is pervasive now due to the significant improvements demonstrated through the usage of deep learning methods in areas such as Computer Vision, Automatic Speech Recognition, and in particular, NLP. This survey categorizes and addresses the different aspects and applications of NLP that have benefited from deep learning. It covers core NLP tasks and applications and describes how deep learning methods and models advance these areas. We further analyze and compare different approaches and state-of-the-art models.

References in corpus (71)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Natural Language Processing (almost) from Scratch
• Distributed Representations of Sentences and Documents
• Teaching Machines to Read and Comprehend
• Convolutional Sequence to Sequence Learning
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Survey on Deep Learning for Named Entity Recognition
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• A Neural Conversational Model
• A Deep Reinforced Model for Abstractive Summarization
• Recent Trends in Deep Learning Based Natural Language Processing
• Convolutional Neural Networks for Sentence Classification
• VQA: Visual Question Answering
• Recurrent Models of Visual Attention
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Sequence Level Training with Recurrent Neural Networks
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Skip-Thought Vectors
• End-To-End Memory Networks
• A C-LSTM Neural Network for Text Classification
• Multilingual Denoising Pre-training for Neural Machine Translation
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Dynamic Coattention Networks For Question Answering
• A Survey on Recent Advances in Named Entity Recognition from Deep Learning models
• Enriching Word Vectors with Subword Information
• Deep Reinforcement Learning for Dialogue Generation
• Deep Learning Based Text Classification: A Comprehensive Review
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Adversarial Learning for Neural Dialogue Generation
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
• An Information Retrieval Approach to Short Text Conversation
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Compositional Morphology for Word Representations and Language Modelling
• Empower Sequence Labeling with Task-Aware Neural Language Model
• Weighted Transformer Network for Machine Translation
• Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
• Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
• Understanding Chatbot-mediated Task Management
• End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
• Question Answering with Subgraph Embeddings
• Reinforcement Learning Neural Turing Machines - Revised
• Understanding Back-Translation at Scale
• A Survey of Deep Learning Techniques for Neural Machine Translation
• Learning End-to-End Goal-Oriented Dialog
• Neural Abstractive Text Summarization with Sequence-to-Sequence Models
• Adversarial Evaluation of Dialogue Models
• Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
• HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
• Massively Multilingual Neural Machine Translation
• Constituency Parsing with a Self-Attentive Encoder
• Robust Neural Machine Translation with Doubly Adversarial Inputs
• Bridging the Gap between Training and Inference for Neural Machine Translation
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Semi-Supervised Sequence Modeling with Cross-View Training
• Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
• Robust Multilingual Part-of-Speech Tagging via Adversarial Training
• What Do Recurrent Neural Network Grammars Learn About Syntax?
• GRAPPA-GANs for Parallel MRI Reconstruction
• Improving Neural Parsing by Disentangling Model Combination and Reranking Effects
• Efficient Second-Order TreeCRF for Neural Dependency Parsing
• Joint RNN-Based Greedy Parsing and Word Composition
• Syntax-aware Multilingual Semantic Role Labeling
• A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis
• In-Order Transition-based Constituent Parsing

Cited by in corpus (13)

• Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
• Engineering Semantic Communication: A Survey
• Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization
• BERT-Based Sentiment Analysis: A Software Engineering Perspective
• A Unified Review of Deep Learning for Automated Medical Coding
• ViscoelasticNet: A physics informed neural network framework for stress discovery and model selection
• Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications
• GRAPPA-GANs for Parallel MRI Reconstruction
• BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets
• Focusing on Potential Named Entities During Active Label Acquisition
• Contemporary Research Trends in Response Robotics
• Learning Potentials of Quantum Systems using Deep Neural Networks
• Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers