Time Travel: 2014
Chapter 92 The admiration of the top algorithm team (Part 2)
Eve Carly fell into deep thought for a while.
No matter how this 270% is derived, it probably doesn’t come out of nowhere.
Eve doesn't know what the rules are for software promotion in other countries, but in the United States, if you rashly carry out such unfounded quantitative promotion without a logical and self-consistent measurement model as a theoretical support, you will easily be fined. Leftover.
That is to say, the so-called "270%" high probability of Nanfeng APP is based on a sufficiently powerful and logically self-consistent accuracy measurement model.
But it’s hard to say. Every year there are many developers who ignore publicity rules in order to gain attention.
Out of a rigorous scientific research attitude, Eve Carly conducted a search using the keyword "text summary accuracy measurement model".
In the search results, Eve Carly saw at a glance that there was a new accuracy measurement model mixed in among the models.
No way, it's hard not to notice that Eve Carly is an expert on the more than ten models that have been used to measure the accuracy of text summarization.
Now called "LH Text Summarization Accuracy Measurement Model" Eve Carly has never seen it before.
Let’s take a rough look at the accuracy measurement method used by this model.
Eve unexpectedly discovered that through this new accuracy measurement model, evaluators do not need to introduce any subjective factors into the process of evaluating summary accuracy.
Because there are no subjective factors involved, this accuracy evaluation method can completely quantitatively analyze the summary accuracy of all existing text summary algorithms.
This measurement model also demonstrates several usage examples.
After the algorithm in the Nick Yahoo news digest software was measured by this model, the accuracy score was only 1 point.
Nanfeng APP received a score of 3.7 points.
Seeing this result, Eve understood why Nanfeng APP’s so-called summary accuracy was 270% ahead.
It seems that this LH text summary accuracy measurement model must have been developed by the developers of Nanfeng APP.
Even if it was not done by the developers of Nanfeng APP, there should be some connection between the two.
Otherwise, how could the measurement results of this model be highly homogeneous with the data promoted by Nanfeng APP's software.
I have to say that this new method of measuring accuracy called LH gave Eve Carly a feeling of enlightenment.
By utilizing this measurement model, their future research will also be smoother.
However, what surprised Eve Carly was that the "LH Text Summary Accuracy Measurement Model" did not appear alone in the form of a paper.
Instead, it appears in a patent titled "Generative Text Summarization Algorithm."
Measurement model appearing in patent? This undoubtedly means that even if this model is very efficient, its actual use still theoretically requires authorization from the patent owner.
Isn’t this too doggy? There is no reason to put this model in a patent.
And is it necessary to apply for a patent for just an algorithm?
Although Eve Carley's previous algorithm was very powerful, they did not apply for a patent.
But Eve had nothing to say about this.
The reason why they don't apply for algorithm patents is not because they are selfless.
It's because their previous algorithms were only improvements based on predecessors and did not have complete originality.
In addition, applying for a patent will involve a certain degree of technology disclosure.
Although the patent applicant does not need to publish all the details, even if the details are not published, the technical route still needs to be explained.
When they know the technical route, the world's top R\u0026D teams are not vegetarians.
Although it is impossible to develop an identical algorithm according to the technical route described in the patent, it is obviously infringement.
However, the thinking inspired by the technical route disclosed in the patent can easily overtake other similar technologies in corners.
In fact, it is precisely because of concerns about the leakage of technical routes that few specialized algorithm patents have appeared in the United States in recent years.
Um, or is it that this patent owner is so confident that he is not afraid of others catching up?
Eve saw that the owner of the patent for "Generative Text Summarization Algorithm" is Lin Hui
From the spelling, it seems to be a Chinese name, but Eve is at a loss about this name.
However, by searching Lin Hui on Google, Eve could easily find a lot of relevant information.
However, none of this information is good news for Eve.
Eve saw that Lin Hui proposed the "LH text summary accuracy measurement model" in the patent.
But he appears to have no plans to keep the model private.
Instead, it took the initiative to submit this model to the U.S. National Standards Committee and the International Organization for Standardization for review.
That is to say, Lin Hui not only does not mind making this evaluation method public, but is committed to using this measurement system as the standard for measuring summary accuracy in the news summary industry.
It’s also understandable, who doesn’t want a frame he or she makes to become a standard for the whole world?
At present, in the news summary industry, except for the LH model, there is almost no model that does not require the introduction of subjective factors to measure accuracy.
In this case, this "LH text summary accuracy measurement model" will most likely become the only objective standard for text summary accuracy measurement.
What is this concept? As the saying goes, first-rate teams make standards, and second-rate teams make technology.
When Eve and her team were still conducting algorithm research on a technical level.
Lin Hui, a truly ambitious developer, not only set out to develop a more efficient text summarization algorithm.
At the same time, we also seek to unify industry standards.
So they lost from the beginning?
Although she had always been calm, Eve Carly couldn't help but feel a little sad at this time.
She silently remembered the name of Lin Hui, an extremely confident and farsighted Chinese, in her heart.
Happy New Year, book friends! I wish all my book friends may all their wishes come true and all the best in the new year.
You'll Also Like
-
Disabled Mr. Zhan is the Child’s Father, It Can’t Be Hidden Anymore!
Chapter 672 3 hours ago -
From a family fisherman to a water immortal
Chapter 205 6 hours ago -
Lord of Plenty
Chapter 327 6 hours ago -
Evergreen Immortal
Chapter 228 6 hours ago -
Crossing the wilderness to survive, starting with a broken kitchen knife
Chapter 216 7 hours ago -
I was a tycoon in World War I: Starting to save France
Chapter 580 7 hours ago -
With the power of AI, you become a giant in the magic world!
Chapter 365 8 hours ago -
Depressed writers, the whole network begs you to stop writing
Chapter 241 9 hours ago -
I can identify everything, but the entries are crooked?
Chapter 182 9 hours ago -
Type-Moon, I heard that after death, you can ascend to the Throne of Heroes?
Chapter 274 9 hours ago