Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Analyzing top HN posts with language models

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 44 posts

Re: Show HN: Analyzing top HN posts with language models

#11

Post by toppy »

jayalammar wrote: post #6
toppy wrote: post #3

I don't know how HN score metrics work but after some short review of the datafile [1] I've noticed a lot of the posts has the form of a simple questions and as such seems to be naturally biased when comes to user engagement. Have you considered to add additional metrics to remove that bias and re-analyze? [1] https://storage.googleapis.com/cohere-assets/blog/text-clust...

What do you mean by naturally biased? That people seem to favor them?

People seem to be more engaged in discussions arising from questions rather than statements, no?

Re: Show HN: Analyzing top HN posts with language models

#12

Post by jayalammar »

uniqueuid wrote: post #7
jayalammar wrote: post #5

Earlier quoted context omitted.

So it really depends on what you use for clustering. In this case, I'm clustering by the original embeddings so the UMAP results are different. I've also seen: 1- Clustering by UMAP. Here the plot would show clean separation of topics. But the clustering algorithm would be working on highly compressed data (from the 1024 dimensions of the embedding down to the 2 of UMAP). 2- BERTopic's approach of doing UMAP down to…

Right, bertopic's double clustering is interesting. I've also seen people combine that with louvain instead of k-means. My intuition was: UMAP itself tries to optimize for 2d separation in the projection. So we should expect at least some correspondence between the kmeans results and the layout in the UMAP plot (except in some pathological edge cases perhaps). Nevertheless, nice example and blog post!

TIL louvain clustering! I see it used for graphs. Can also be used for vectors/points?

Thank you!

Re: Show HN: Analyzing top HN posts with language models

#13

Post by uniqueuid »

jayalammar wrote: post #12
uniqueuid wrote: post #7

Earlier quoted context omitted.

Right, bertopic's double clustering is interesting. I've also seen people combine that with louvain instead of k-means. My intuition was: UMAP itself tries to optimize for 2d separation in the projection. So we should expect at least some correspondence between the kmeans results and the layout in the UMAP plot (except in some pathological edge cases perhaps). Nevertheless, nice example and blog post!

TIL louvain clustering! I see it used for graphs. Can also be used for vectors/points? Thank you!

You're welcome!

You can actually create a graph by using k-means similarities as edge weights. Then you do graph clustering on it. (using any algorithm, but louvain is one of the saner ones ... clique percolation, girvan-newman etc all have known problems).

Re: Show HN: Analyzing top HN posts with language models

#15

Post by jayalammar »

toppy wrote: post #11
jayalammar wrote: post #6

Earlier quoted context omitted.

What do you mean by naturally biased? That people seem to favor them?

People seem to be more engaged in discussions arising from questions rather than statements, no?

I think that's part of the expectations out of "ask HN". I don't know that the same effect happens outside of Ask HN.

Re: Show HN: Analyzing top HN posts with language models

#16

Post by wpietri »

The conflict of interest here concerns me. I don't object to content marketing, but I'd rather a) you were clear from the start that you work for this company and are promoting its product, and b) that this "revolves around [...] using Cohere’s Embed endpoint", so that people can judge how much they want to "get into language models" with pay-per-character pricing, as opposed to something more open.

Re: Show HN: Analyzing top HN posts with language models

#17

Post by jayalammar »

jayalammar wrote: post #2

[1] https://txt.cohere.ai/combing-for-insight-in-10-000-hacker-n... [2] https://assets.cohere.ai/blog/text-clustering/askhn_cluster_... [3] https://assets.cohere.ai/blog/text-clustering/askhn_cluster_... [4] https://assets.cohere.ai/blog/text-clustering/askhn_cluster_... [5] https://assets.cohere.ai/blog/text-clustering/askhn_cluster_... [6] https://assets.cohere.ai/blog/text-clustering/hn10k_clustere... [7] https://…

Disclosure: These were made by Cohere's embeddings, a company where I work. The process should work on text embeddings from other sources.

Re: Show HN: Analyzing top HN posts with language models

#18

Post by jayalammar »

wpietri wrote: post #16

The conflict of interest here concerns me. I don't object to content marketing, but I'd rather a) you were clear from the start that you work for this company and are promoting its product, and b) that this "revolves around [...] using Cohere’s Embed endpoint", so that people can judge how much they want to "get into language models" with pay-per-character pricing, as opposed to something more open.

Thanks. I just added a disclosure to the comment (can't edit the parent anymore). The full embeddings are freely provided here without the need to use the service.

Re: Show HN: Analyzing top HN posts with language models

#19

Post by rmbyrro »

wpietri wrote: post #16

The conflict of interest here concerns me. I don't object to content marketing, but I'd rather a) you were clear from the start that you work for this company and are promoting its product, and b) that this "revolves around [...] using Cohere’s Embed endpoint", so that people can judge how much they want to "get into language models" with pay-per-character pricing, as opposed to something more open.

Do you advocate for the disclaimer only because 1) the sample uses their product or 2) just because they sell a product correlated to the topic?

I see a lot of articles that fall into #2 being published here without a disclaimer. And I think a disclaimer isn't necessary for #2. Even for #1 I wouldn't bother, but I understand the expectation.

Many advocate a lot against ads, targeting, etc. If we also advocate against promotional content, what would companies do to get attention and traffic?

Re: Show HN: Analyzing top HN posts with language models

#20

Post by notatoad »

rmbyrro wrote: post #19
wpietri wrote: post #16

The conflict of interest here concerns me. I don't object to content marketing, but I'd rather a) you were clear from the start that you work for this company and are promoting its product, and b) that this "revolves around [...] using Cohere’s Embed endpoint", so that people can judge how much they want to "get into language models" with pay-per-character pricing, as opposed to something more open.

Do you advocate for the disclaimer only because 1) the sample uses their product or 2) just because they sell a product correlated to the topic? I see a lot of articles that fall into #2 being published here without a disclaimer. And I think a disclaimer isn't necessary for #2. Even for #1 I wouldn't bother, but I understand the expectation. Many advocate a lot against ads, targeting, etc. If we also advocate against…

most content marketing goes to a post on the company's own website, which is a sort of inherent disclosure.

i don't think asking people to disclose that they work for the company whose product they're promoting is "advocating against promotional content".

Post reply on HN