From Word2Vec to BERT: The Evolution of NLP Pre-trained Models

From Word2Vec to BERT: The Evolution of NLP Pre-trained Models

Natural Language Processing Author: Zhang Junlin Source: Deep Learning Frontier Notes Zhihu Column Original Link: https://zhuanlan.zhihu.com/p/49271699 The theme of this article is the pre-training process in natural language processing (NLP). It will roughly explain how pre-training techniques in NLP have gradually developed into the BERT model, naturally illustrating how the ideas behind BERT were formed, … Read more

The Arrival of ImageNet Era in NLP: Word Embeddings Are Dead

The Arrival of ImageNet Era in NLP: Word Embeddings Are Dead

Selected fromthe Gradient Author:Sebastian Ruder Translated by Machine Heart In the field of computer vision, models pre-trained on ImageNet are commonly used for various CV tasks such as object detection and semantic segmentation. In contrast, in the field of natural language processing (NLP), we typically only use pre-trained word embedding vectors to encode the relationships … Read more

Introduction to Contextual Word Representations in NLP

Introduction to Contextual Word Representations in NLP

Excerpt from arXiv Author: Noah A. Smith Translated by Machine Heart Contributors: Panda The basics of natural language processing involve the representation of words. Noah Smith, a professor of Computer Science and Engineering at the University of Washington, recently published an introductory paper on arXiv that explains how words are processed and represented in natural … Read more

Pre-training Methods for Language Models in NLP

Pre-training Methods for Language Models in NLP

Recently, in the field of Natural Language Processing (NLP), the use of pre-training methods for language models has achieved significant improvements across various NLP tasks, attracting widespread attention from various sectors. In this article, I will summarize some relevant papers I have recently read, selecting a few representative models (including ELMo [1], OpenAI GPT [2], … Read more