Giter Club home page Giter Club logo

zhaojin's Projects

aggcn icon aggcn

Attention Guided Graph Convolutional Networks for Relation Extraction (authors' PyTorch implementation for the ACL19 paper)

airplay-sdk icon airplay-sdk

Airplay Receiver SDK supports Airplay Mirroring and AirPlay Casting to a receiver device.

allennlp_attention_ner icon allennlp_attention_ner

Source code for AAAI 2021 paper "A Supervised Multi-Head Self-Attention Network for Nested Named Entity Recognition""

camelot icon camelot

A Python library to extract tabular data from PDFs

d2l-zh icon d2l-zh

《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被全球140所大学采用教学。

dive-into-dl-pytorch icon dive-into-dl-pytorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

hello_fudan icon hello_fudan

⚙ 自动化平安复旦助手 (带验证码识别)

hellogithub icon hellogithub

:octocat: Find pearls on open-source seashore 分享 GitHub 上有趣、入门级的开源项目

mtbook icon mtbook

《机器翻译:统计建模与深度学习方法》肖桐 朱靖波 著 - Machine Translation: Statistical Modeling and Deep Learning Methods

n-ary-dataset icon n-ary-dataset

Datasets for cross-sentence n-ary relation extraction dataset.

n-ary-relation-extraction-from-news-articles icon n-ary-relation-extraction-from-news-articles

This thesis presents three main contributions to the essential questions of the corresponding research. The first contribution is data scraping from Wikipedia news articles using web-scraper, which further deals with extraction of entities and relations from news events by using constituency parser from natural language processing toolkit. The second contribution presents the annotation interface for annotation purposes. Finally, the third contribution pertains to annotated arguments and entities from the annotation interface, passed through the relation extraction framework based on Long Short Term Memory (LSTM) and Multi-Task Learning (MTL). The model has been evaluated on datasets and its performance is measured on the evaluation metrics, demonstrating the model’s effectiveness with supervised learning and MTL, which has significantly improved the extraction accuracy. Keywords: Information extraction, relation extraction, entity extraction, n-ary relation extraction, constituency parser, annotation interface, Long Short Term Memory (LSTM) and Multi-Task Learning (MTL).

ner icon ner

命名实体识别实践与探索

nlp-tutorial icon nlp-tutorial

Natural Language Processing Tutorial for Deep Learning Researchers

nlp_textclassifier icon nlp_textclassifier

基于word2vec预训练词向量; textCNN 模型 ;charCNN 模型 ;Bi-LSTM模型;Bi-LSTM + Attention 模型 ;Transformer 模型 ;ELMo 预训练模型 ;BERT 预训练模型的文本分类项目

nndl.github.io icon nndl.github.io

《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning

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.