TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

How we built Tagger News: machine learning on a tight schedule

71 点作者 var_explained大约 8 年前

2 条评论

minimaxir大约 8 年前
Link to original HN submission: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14337275" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14337275</a><p>It&#x27;s worth noting for future reference that in terms of supervised learning of labels given a text document input, fasttext (<a href="https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;fastText" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;fastText</a>) is <i>leagues</i> ahead of conventional approaches in both accuracy and training speed, and there is a Python interface (<a href="https:&#x2F;&#x2F;github.com&#x2F;salestock&#x2F;fastText.py" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;salestock&#x2F;fastText.py</a>) for use with Django&#x2F;Flask (unfortunately, recent fasttext changes have broken the interface for now).
评论 #14396165 未加载
评论 #14396625 未加载
_eht大约 8 年前
I noticed some things were pretty terribly tagged earlier this week. Robots have a ways to go, this is good news.