Call-for-Code-for-Racial-Justice / Call-for-Code-for-Racial-Justice/TakeTwo-DataScience

Implement Machine Learning component V2 (dsmvp-v2)

未關閉
#9 1 則留言 0 個 reaction 已指派 0 人 在 GitHub 檢視
Machine Learning
主要語言
Jupyter Notebook
星號
8
分支
8
PR 合併指標
30 天內沒有已合併 PR

描述

As part of the progression of machine learning components with increasing levels of sophistication, implement version 2 ("dsmvp-v2") with the following characteristics:

A machine learning module that can learn to detect racially biased expressions in context based on input labeled data of triples.

A possible implementation can make use of contextual text classifiers, such as those based on RNN = Recurrent Neural Networks such as the LTST architecture (Reference: https://spacy.io/usage/examples#textcat).

RNN allows the classifier to be "sequentially contextual", i.e. to classify a given phrase or expression dependent on the context in which it is used.

Coding of dsmvp-v2 should be similar to and share many aspects of how dsmvp-v1 in the repository is implemented, using Jupyter notebook and accessing the database via webapi, etc.

貢獻指南

開啟貢獻指南

研究方向

首先檢視儲存庫中現有的 dsmvp-v1 實作,包括其 Jupyter notebook 和 webapi 資料庫存取。參考連結的 spaCy 文字分類範例,定義 dsmvp-v2 應如何使用 三元組並提供情境偏誤分類。新元件已依照所述的情境行為完成實作,並遵循 v1 的整合模式,即視為完成。

由索引模型根據 Issue 內容生成。

評估

技術堆疊
jupyter-notebook
領域
api, machine-learning
Issue 類型
功能
難度
5/5
預估耗時
一週以上
活躍度
停滯
描述清晰度
需要釐清
新手友好度
25/100

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。