Giter Site home page Giter Site logo

ctc-report's Introduction

Hi there 👋

My name is Yue Zhang (章岳). You can call me Yue or Hill (岳 means hill in Chinese).

  • 🌱 I am currently a final-year graduate student (expected to graduate in 2024) at HLT@SUDA, advised by Prof. Zhenghua Li. Before this, I received my Bachelor's degree (2017-2021, software engineering) from Soochow University.
  • 👯 I am also currently an NLP intern at Bytedance LLM team. Previously, I also interned at Alibaba DAMO Academy (from 2021.07 to 2023) and Tencent AI Lab (from 2023.02 to 2024).
  • 🤔 Previously, my main research interests focused on deep learning for natural language generation (NLG), e.g., grammatical error correction. Now, I am trying to adjust my research direction to Large Language Models (LLM) and their applications.
  • 📫 How to reach me: E-mail

View my homepage.

Hill's GitHub stats

ctc-report's People

Contributors

hillzhang1999 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

ctc-report's Issues

关于代码获取

作者您好,我看了您们团队在CTC2021比赛中所用方法的报告,我想学习一下,所以请问一下能否方便提供一下你们实现的整个纠错流程的源代码,仅供学习使用。本人邮箱:[email protected] ,如果方便提供源代码,麻烦联系我一下,谢谢。

关于模型集成

感谢开源,请问,模型集成是在训练的时候将概率平均,还是模型训练好之后的推理阶段,再将概率平均

拼写纠错

拼写纠错模型是不是类似于pycorrector开源项目中macbert4csc?另外,拼写纠错中的解码trick是在预测时使用吗?在训练时要使用吗?

GECToR训练

你好,打扰了,我在训练中文gector模型时,使用大量伪数据训练的效果,与直接在任务数据微调效果差不多。想请问下:1)你们在ctc比赛中的方案,只做伪数据预训(不做任务微调)可以达到什么效果呢?(或者有测试过ctc提供的baseline模型效果吗)2)你们训练gector的代码是基于ctc比赛提供的代码修改的吗?感谢。

关于解码策略的性能问题

”对句子中的每个位置,挑选出所对应的 10 个概率最大的候选字符;“
该步骤涉及topk求解问题,性能影响是否较大?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.