Crossover: 2014

Chapter 253 Quietly Changing the World

The purpose of this step is to complete the preliminary analysis of the preprocessed original text through this series of calculations.

Content selection is to select the corresponding subset of text units from the weighted text units (that is, the text that has been analyzed by the weight of step Ⅱ) to form a summary candidate set. According to the required summary length, linear programming, submodular function, and heuristic Algorithms, etc. to select text units;

Content organization refers to organizing the content of the candidate set to form a final abstract, which can be output in order according to the word count requirements. Some researchers also propose to use methods based on semantic information, templates, and neural network learning to generate abstracts that meet the requirements.

Judging from the corresponding descriptions of these levels of the technical framework, it can be seen that all three are very important, whether it is weight calculation, content selection, or content organization.

If you can't figure out the weight calculation and content selection, you can't figure out where to summarize the text when summarizing.

If you can't handle the content organization, it will directly affect the user experience.

In this case, people in this time and space do pay more attention to the three aspects of weight calculation, content selection and content organization of automatic text summarization when conducting research on automatic text summarization.

In the past, according to Eve Carly's thinking, she didn't understand why Lin Hui was very interested in a patent that focused on content representation like "A New Method for Text Judgment, Screening and Comparison".

Even at one time, both Eve Carly and Ewald Cherry believed that Lin Hui was simply showing favor to Eve Carly by purchasing some tasteless patents that were related to Eve Carly but were actually irrelevant. .

But looking at it now, it's clear that's not the case.

If Eve Carly's academic habits about Lin Hui are presumed to hold.

That is, "if a scientific research project involves multiple links, each link has room for action,
Then Lin Hui will definitely focus on the initial link or open up a new track in the place before the initial link." If it is established.

Then, if Lin Hui works in the framework of automatic text summarization, it is most likely to start with the "content representation" link that other researchers are indifferent to.

After all, content representation is the initial link under the framework of automatic text summarization.

If Lin Hui does something under the existing framework, there is a high probability that he will make a fuss about the link of content presentation.

In this way, a patent such as "A New Method for Text Judgment, Screening and Comparison" is not a tasteless patent to Lin Hui.

On the contrary, it may be a very important patent.

And think about Lin Hui's habit of almost never doing meaningless things.

Eve Carly felt that it was absolutely impossible for Lin Hui to spend hundreds of thousands of dollars to acquire patents but only to curry favor with a stranger.

Since Lin Hui acquired "A New Method of Text Judgment, Screening and Comparison", he must have taken a fancy to the value of this patent.

And the value that Lin Hui fancy is likely to be as Eve Carly guessed.

Eve Carly felt more and more that this judgment was correct.

The patent "A New Method for Text Judgment, Screening and Comparison" was the first patent Eve Carly applied for when she was 18 years old.

This patent was held by Eve Carly for six or seven years before it was officially transferred to Lin Hui.

However, Rao has held the patent for this algorithm for several years, and before that, Eve Carly had not discovered the potential value of the patent.

In her eyes, this patent is almost worthless except for its commemorative value (it is the first patent after all).

The patents I once owned are not only valuable, but also very likely to be of great value.

For such an inference, Eve Carly couldn't laugh or cry.

A patent that I have been engaged in for a long time has not exerted its real value in my own hands.

But it has greater value in others?
It's not just as simple as having greater value.

Indeed, as he guessed, it will mean that such a patent that has almost no use in the eyes of Eve Carly has the possibility of a great new life in the hands of LIN HUI.

Eve Carly once thought that she could accept all this very calmly.

But when she really came to a corresponding judgment, Eve Carly's mood still had some ripples involuntarily.

After all, because the core content of the patent "A New Method for Text Judgment, Screening and Comparison" is mainly responsible for the initial task of content representation in automatic text summarization.

This patent was once regarded as a low-level patent by Eve Carly.

But Lin Hui proved to her that there are no low-level patents, only low-level vision.

This is simply a slap in the face, and it would be difficult for anyone to be completely indifferent.

Of course, Eve Carly just had some ripples and emotions in her heart, and she didn't care too much about it.

Besides, the so-called Di Linhui proved to her that there are no low-level patents, only low-level vision.

It was only proved by Lin Hui unintentionally, not by Lin Hui deliberately.

Anyway, since coming into contact with Lin Hui, Eve Carly felt that people with Lin Hui's personality rarely do things just to slap others in the face or to show off for a while.

From Eve Carly's point of view, Lin Hui always does things according to his own unique rhythm, step by step.

The small movements that seem to be slow, only after careful attention will you find that everything is extremely carefully arranged, and it is quite a posture of being surrounded by layers of joint strikes.

As an opponent, you will know the horror of Lin Hui, but every time you take a step, you will find that your opponent has set up several obstacles for you. How can this feeling not be scary?

Eve Carly was a little lucky that she didn't continue to be Lin Hui's enemy, but became Lin Hui's same camp.

Of course, Lin Hui never seemed to have the idea of ​​simply being an enemy to others.

Lin Hui is always serious about being himself, but what Lin Hui doesn't know is that in the process of trying to become a better person, he quietly changed the world unconsciously.

Since arriving in China and being able to officially meet Lin Hui.

Recently, Eve Carly's e-mails are almost full of e-mails sent to her by colleagues in American academia.

The question most asked by these people is not whether she has figured out the mystery of the generative text summarization algorithm after she came into contact with LIN HUI.

The most curious question for these people is what kind of person Lin Hui is.

What kind of person is Lin Hui?
It is also difficult for Eve Carly to describe it in specific words.

Before contacting Lin Hui, the deepest impression Lin Hui gave Eve Carly was Lin Hui's talent.

(End of this chapter)