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。

Conceptarium

49 点作者 rajlego超过 3 年前

5 条评论

gradys超过 3 年前
Great write up! Using learned representations for content in personal knowledge bases seems like a huge missing piece of tools like Roam. This appears to go all the way to the other side of the spectrum, not supporting any explicit graph links, IIUC.<p>I feel like ultimately you want both. Explicit links are a useful navigation affordance with nice properties that spatial embeddings won&#x27;t give you (e.g. you can explicitly establish a link between things that are not similar according to the embedding space).<p>More important than that though, explicit links let you train the embedding model to understand the dataset the way the user does. All of these embedding models are trained on graphs (word or sentence cooccurence graphs, parent&#x2F;child comment graphs on social media, etc.). The graph structure in something like Roam can provide training data for updating and adapting the embedding space to the specific knowledge context in which it&#x27;s used.<p>Conversely, if you have an embedding representation of your knowledge base, you can use that to suggest explicit links. The embedding space is the dense dual to the sparse graph of explicit links in something like Roam. It&#x27;s a fully connected weighted graph rather than a sparse unweighted graph.<p>Maybe this system is meant to only focus on the spatial embedding representation. That makes a lot of sense. A fully-fledged version of this vision though IMO should include a bridge between these two dual representations.
评论 #29225524 未加载
makeitrain超过 3 年前
I have been working on a knowledge base for things I&#x27;m leaning about bike parts. Notes on compatibility, part weights, bookmarks to helpful links, etc<p>A big challenge I have is when I add a new tag, I&#x27;ll want to apply it to relevant content I already have. But this takes a long time and until it happens the relevant data can&#x27;t be retrieved by the tag.<p>I am curious how the semantic hash is implemented in a conceptarium. If I could focus on adding content and it can drive relationships automatically, that is awesome.
评论 #29225591 未加载
gardenfelder超过 3 年前
Corrected internal link: <a href="https:&#x2F;&#x2F;paulbricman.com&#x2F;thoughtware&#x2F;semantica" rel="nofollow">https:&#x2F;&#x2F;paulbricman.com&#x2F;thoughtware&#x2F;semantica</a>
etherio超过 3 年前
I&#x27;m currently looking into similar ideas with auto-generation of organization in knowledge bases: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;uzpg_&#x2F;status&#x2F;1458774952786681856" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;uzpg_&#x2F;status&#x2F;1458774952786681856</a><p>I plan on releasing something soon, this is super interesting!
yukiookami29超过 3 年前
I would be very interested to see how the distances between documents that arises out of Conceptarium compares to some user(s) other knowledge graphs they have painstakingly made by hand.<p>Also, I appreciate the heavy use of Greg Egan novels at the end!
评论 #29249576 未加载