I am trying to design a terminology extractor with GPT-3 and I am following the template in the documentation for a tweet classifier at the moment. That means the engine is davinci, the response length 64, the temperature 0.2, the Top P 1, the stop sequence “two enter keys”, and a highly structured prompt which involves a natural language instruction and about 9 examples with 5 sentences for completion.
This is my prompt, which copies the tweet template completely:
This is a terminology extractor.
Sentence: “The rocketship is fueled with Alpha-Omega Jet Fuel.”
Keywords: Alpha-Omega Jet Fuel
Sentence: Barack Obama will visit Japan on Memorial Day.
Keywords: Memorial Day
Sentence: The metatarsals are attached to the cuneiform bones at a diagonal angle.
Keywords: metatarsal, cuneiform
Sentence: The HTTP protocol is used for sending and receiving HTML requests over the internet.
Keywords: HTTP protocol, HTML request
- Happy Birthday John! I got you this memory-foam mattress for the occasion.
- The band Green Day usually uses Vox foot pedals with heavy reverb and oscillatory delay.
- The Amazon rainforest has been heavily damaged by ammonium acetate in the form of acid rain.
- The young boy’s occlusion was malaligned and he was in dire need of a surgical implant.
- It was the happiest day in the world, except for a V1 Tesla Roadster which had crashed into an embankment.
- Vox foot pedals, oscillatory delay
- ammonium acetate
- V1 Tesla Roadster
- After all the Shizuku Miyatsu that he had practiced, he had become serene.
- The left tetrometer was fully engaged at the time of the incident.
- She underwent a tetralogy of fallot surgery early in life.
- The corneal gland is inflamed due to lack of lipids.
- A gristmill mills grain with the assistance of vanes which are called blades.
Unfortunately, GPT-3 returned the stop sequence in the playground, so it will need at least a little adjusting.
I can think of a few adjustments.
I can increase the temperature.
I can eliminate the stop sequence.
I can provide higher-quality data. These examples are made up, but I can provide real-world sentences with actual terminology to be extracted.
I can provide even more examples.
I will continue to tinker with this, but in case anybody wants to collaborate, I’d be interested in hearing your suggestions.
Thanks very much.