Simple Text Summarizer API via @21 is the most cost effective option

Submit a text file of up to 500 KB and receive a simple text summary via the marketplace for 3000 satoshis (about $0.02). For current 21 users, it’s as simple as a 21 quick buy:

21 buy "pagekicker/simple-text-summarizer/buy" --data-file /path/to/local/file.txt

Note the file must have a .txt or .md extension and the double quotes around the resource path (shortened URL) are necessary.

You will receive the ten most statistically significant sentences via stdout.  For example, the summarizer produced the following from the original bitcoin white paper:

fred@fred-XPS-L322X:~/pk-21/simplePKsum$ 21 –debug buy “pagekicker/simple-text-summarizer/buy” –data-file test/
* Messages are broadcast on a best effort basis, and nodes can leave and rejoin the network at will, accepting the longest proof-of-work chain as proof of what happened while they were gone.
* Each owner transfers the coin to the next by digitally signing a hash of the previous transaction and the public key of the next owner and adding these to the end of the coin.
* The problem of course is the payee can’t verify that one of the owners did not double-spend the coin.
* The payee needs proof that at the time of each transaction, the majority of nodes agreed it was the first received.
* For our timestamp network, we implement the proof-of-work by incrementing a nonce in the block until a value is found that gives the block’s hash the required zero bits.
* To modify a past block, an attacker would have to redo the proof-of-work of the block and all blocks after it and then catch up with and surpass the work of the honest nodes.
* When a node finds a proof-of-work, it broadcasts the block to all nodes.
* Nodes express their acceptance of the block by working on creating the next block in the chain, using the hash of the accepted block as the previous hash.
* A user only needs to keep a copy of the block headers of the longest proof-of-work chain, which he can get by querying network nodes until he’s convinced he has the longest chain, and obtain the Merkle branch linking the transaction to the block it’s timestamped in.
* We can calculate the probability he ever reaches breakeven, or that an attacker ever catches up with the honest chain, as follows [8]: p = probability an honest node finds the next block q = probability the attacker finds the next block qz = probability the attacker will ever catch up from z blocks behind eq1 Given our assumption that p > q, the probability drops exponentially as the number of blocks the attacker has to catch up with increases.

A more fully featured version of the summarizer will be available soon with support for positive and negative seed terms and weightings as well as stop word lists and improved control over output.

Once you’re on the 21 network, all you need to do to use the  summarizer is issue the 21 buy command described above. This means that bulk summarization suddenly becomes very easy via shell script. There’s no issue with the trivial cost: when you join you get an initial supply of bitcoin and can replenish it by carrying out various tasks such as joining social networks, etc. Considering that signing up for a text analytics service generally requires at least 30 minutes of filling out forms, requesting tokens, and fielding annoying emails or phone calls from sales people, and comparing the dollar value of your time, the Simple Text Summarizer  becomes the most cost-effective option for light to medium weight projects summarizing many documents.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s