ASR Error Correction Based on BERT

ASR Error Correction Based on BERT

Guest Speaker: Wei Tianwen, Xiaomi AI Department Edited by: Li Shuna Source: DataFunTalk Introduction: Xiao Ai is an intelligent voice system developed by Xiaomi, widely used in smartphones, bands, speakers, TVs, and other electronic products, supporting various voice interaction scenarios such as casual conversation, Q&A, and voice control. The accuracy of Automatic Speech Recognition (ASR) … Read more

The Art of Fine-Tuning BERT

The Art of Fine-Tuning BERT

Authorized Reprint from Andy’s Writing Room Author:ANDY The BERT pre-trained model is like a pig ready for cooking, and fine-tuning is the cooking method. The pig’s head can be made into fragrant and rich roasted pig head meat, the trotters can be made into hearty braised trotters, and the various cuts like pork belly and … Read more

Understanding Deep Learning: From Neurons to BERT

Understanding Deep Learning: From Neurons to BERT

Ali Sister’s Guide: BERT, a landmark in the field of natural language processing, did not appear out of nowhere; it has its development principles behind it. Today, the Ant Financial Wealth Dialogue Algorithm Team has organized and compared the development history of deep learning models in the field of natural language processing. From simple neurons … Read more

Chronos: Slow Thinking RAG Technology for News Timeline Summarization

Chronos: Slow Thinking RAG Technology for News Timeline Summarization

Paper: https://arxiv.org/abs/2501.00888 Github: https://github.com/Alibaba-NLP/CHRONOS Demo: https://modelscope.cn/studios/vickywu1022/CHRONOS In the digital age, the exponential growth of news information makes it crucial to extract and organize historical event timelines from massive texts. To address this challenge, Alibaba’s Tongyi Lab and researchers from Shanghai Jiao Tong University proposed a new framework for news timeline summarization based on agents—CHRONOS, named … Read more

Reject Module in Large Model RAG

Reject Module in Large Model RAG

To effectively implement <span>RAG</span>, there are indeed many aspects that need refinement, and today we will learn about the Reject Module. Official Explanation In the RAG (Retrieval-Augmented Generation) model, the Reject Module is an important component designed to enhance the robustness of the generation model when facing irrelevant queries or information. Plain Explanation A simple … Read more

Introduction to RAG in Large Models

Introduction to RAG in Large Models

This is the sixth article in the large model programming series, and also my notes from the free course on some cloud large model engineer ACA certification[1]. This course is really good, highly recommended! 👍🏻 If you’re interested in the course, please click the link at the bottom to view the original article. Here are … Read more

Summary and Implementation Ideas of RAG Chunking Technology

Summary and Implementation Ideas of RAG Chunking Technology

TrustRAG Project Address🌟: **https://github.com/gomate-community/TrustRAG** Configurable Modular RAG Framework Introduction to Chunking In the RAG (Retrieval-Augmented Generation) task, chunking is a critical step, especially when dealing with complex PDF documents.PDF documents may contain images, strange layouts, etc., which increases the difficulty of chunking. Impact of Chunk Granularity Sentence/Word Granularity: Focuses on local, key information queries but … Read more

Understanding Retrieval-Augmented Generation (RAG) in AI

Understanding Retrieval-Augmented Generation (RAG) in AI

Reply ‘data’ to receive a collection of algorithm interview questions (large models, deep learning, machine learning). 1. What is Retrieval-Augmented Generation (RAG)? RAG is a hybrid approach that combines retrieval systems and generative language models. It consists of two steps: Retrieval Component: Searches for relevant information in large external corpora or datasets based on the … Read more

Reinventing RNNs for the Transformer Era: RWKV Model

Reinventing RNNs for the Transformer Era: RWKV Model

Machine Heart Report Machine Heart Editorial Department Transformer models have revolutionized almost all natural language processing (NLP) tasks, but their memory and computational complexity grows quadratically with sequence length. In contrast, Recurrent Neural Networks (RNNs) grow linearly in memory and computational requirements, but due to limitations in parallelization and scalability, it is difficult to achieve … Read more

A Comprehensive Guide to Building Transformers

A Comprehensive Guide to Building Transformers

This article aims to introduce the Transformer model. Originally developed for machine translation, this model has since been widely applied in various fields such as computer recognition and multimodal tasks. The Transformer model introduces self-attention mechanisms and positional encoding, and its architecture mainly consists of an input part, an output part, and encoders and decoders. … Read more