Autographer
The work of a mediocre writer can, and therefore, should be automated.
For people far from seteratura , it may not be obvious how many works of art have already been written, or will be written soon. Sites such as Samizdat or Proza.ru contain text volumes that have not been forgotten by programmers of even the most complex and heavily loaded systems. Even the seediest literary competition in the network collects tens to hundreds of participants, and it should be noted that the uniqueness of the texts is a condition for participation in most of them. That is, the production of a new one is spurred on by life, but the quality of this new and relatively low and unclaimed: it’s possible to publish a book for money for almost every hundredth person writing, to win the competition is similar.
This is due to the limited resources (consumer ability and demand among the readers, production capacity of the printing house and design - publishing houses, prize money, time of jury members), and, to a large extent, the quality of the works. If we reject frankly illiterate and inadequate texts - and this is, according to modest estimates, at least a quarter of any stream for publication or victory - all the same, there will be too many standard, hackneyed, boring, secondary texts of writers of the past and each other. Increasingly, there are suggestions that even a robot would be able to write such a - literate, but absolutely inexpressive, work that differs from similar names only by proper names. So why doesn't the robot really do it?
')
The theory of literature has accumulated enough information about the structure of a literary work, so that you can compile an algorithm for generating text from blocks of large and medium size: parts and chapters.
The simplest is name generation . Leonid Kaganov, a well-known writer who is familiar with programming, at one time wrote an article entitled “ How to call your book ”, containing an exhaustive list of possible schemes. In the simplest version, “The noun in the nominative case + the noun in the genitive case” (“Dragon Sword”, “Game of Thrones”, “King of the Ring”) is implemented in half an hour. For example, on the Kohana framework with its QueryBuilder:
It is enough to have a base of the first and second parts with the following structure:
Next, you should think about the plot . It is well known that Borges said that there are only 4 plots in literature :
But in the modern reader this causes some confusion. Much closer to life is the theory of Thirty-six dramatic situations by Georges Polti, with which, with some assumptions, it is possible to classify any literary work.
That is, having created only 36 plotting schemes, we can already - in draft form - compose absolutely any work in the world that is not inferior to either proven classics or modern creations.
But what does the text itself consist of, regardless of the plot? Many people even remember from the school literature course that in every real work one can distinguish the exposition, the outset, the development of the action, the climax, the denouement and the postposition , therefore, the work should have at least 5 parts, each of which will represent one of the classical stages of the plot development. .
Each part, in turn, may consist of some semantic blocks: narratives, descriptions and arguments :
If in each of the 36 plots to write an algorithm for the sequential construction of narrations, descriptions and arguments, then we get. almost the entire "skeleton" and the main "muscles" of the work.
In turn, inside a block there can be several paragraphs with a certain order of sentences inside them, which - sentences - in turn consist of words in a certain order and forms. Although it is believed that the Russian grammar is less enslaved than, for example, English, the standard literary style implies the direct construction of sentences - almost like in English - and any change in the places of the "components" of a sentence already implies emotional coloring or individual features of speech that we are now not interested.
And then, finally, we got the full text, having a randomly generated name, assembled according to the scheme of one randomly selected from 36 plot, with one of the random patterns, the location of paragraphs and sentences. Plain mediocre text. It remains to add to it what distinguishes the work of this author from the robot. Proper Names
Parsing lines is not such a difficult task. It is enough to place a marker like "# Main_Char #", "# Main_Enemy #", etc. into the original text instead of specific names and titles. The situation is somewhat complicated by the need to change the endings of words in different cases in Russian, but I think it’s not difficult to add another flag clearly indicating the use of a certain case ending.
Thus, several months of a competent programmer can replace hundreds of years and thousands of units of human labor. I dare to notice, absolutely useless and sad.
The web writer platform, obviously, should be the web:
But one question remains: why is it really necessary? Well, I believe that if you save humanity from the need to write a lot and badly to set off rare talents, you will get more of them.
For people far from seteratura , it may not be obvious how many works of art have already been written, or will be written soon. Sites such as Samizdat or Proza.ru contain text volumes that have not been forgotten by programmers of even the most complex and heavily loaded systems. Even the seediest literary competition in the network collects tens to hundreds of participants, and it should be noted that the uniqueness of the texts is a condition for participation in most of them. That is, the production of a new one is spurred on by life, but the quality of this new and relatively low and unclaimed: it’s possible to publish a book for money for almost every hundredth person writing, to win the competition is similar.
This is due to the limited resources (consumer ability and demand among the readers, production capacity of the printing house and design - publishing houses, prize money, time of jury members), and, to a large extent, the quality of the works. If we reject frankly illiterate and inadequate texts - and this is, according to modest estimates, at least a quarter of any stream for publication or victory - all the same, there will be too many standard, hackneyed, boring, secondary texts of writers of the past and each other. Increasingly, there are suggestions that even a robot would be able to write such a - literate, but absolutely inexpressive, work that differs from similar names only by proper names. So why doesn't the robot really do it?
')
The theory of literature has accumulated enough information about the structure of a literary work, so that you can compile an algorithm for generating text from blocks of large and medium size: parts and chapters.
The simplest is name generation . Leonid Kaganov, a well-known writer who is familiar with programming, at one time wrote an article entitled “ How to call your book ”, containing an exhaustive list of possible schemes. In the simplest version, “The noun in the nominative case + the noun in the genitive case” (“Dragon Sword”, “Game of Thrones”, “King of the Ring”) is implemented in half an hour. For example, on the Kohana framework with its QueryBuilder:
public function random_textname () { // Get random text name part 1 $offset = DB::select(DB::expr('MIN( `id` ) AS min, MAX( `id` ) AS max'))->from('story_names')->where('part', '=', 1)->execute()->as_array(); $RID = mt_rand($offset[0]['min'],$offset[0]['max']); $random_name = DB::select('story')->from('story_names')->where('id', '>=', $RID)->and_where('part', '=', 1)->limit(1)->execute()->get('story'); // Get random text name part 2 $offset = DB::select(DB::expr('MIN( `id` ) AS min, MAX( `id` ) AS max'))->from('story_names')->where('part', '=', 2)->execute()->as_array(); $RID = mt_rand($offset[0]['min'],$offset[0]['max']); $result = DB::select('story')->from('story_names')->where('id', '>=', $RID)->and_where('part', '=', 2)->limit(1)->execute()->get('story'); $random_name .= ' '.$result; return $random_name; } It is enough to have a base of the first and second parts with the following structure:
id | part | storyNext, you should think about the plot . It is well known that Borges said that there are only 4 plots in literature :
- On the storming and defense of the fortified city (Troy)
- About the long return (Odyssey)
- About search (Jason)
- On the suicide of God (Odin, Atis)
But in the modern reader this causes some confusion. Much closer to life is the theory of Thirty-six dramatic situations by Georges Polti, with which, with some assumptions, it is possible to classify any literary work.
That is, having created only 36 plotting schemes, we can already - in draft form - compose absolutely any work in the world that is not inferior to either proven classics or modern creations.
But what does the text itself consist of, regardless of the plot? Many people even remember from the school literature course that in every real work one can distinguish the exposition, the outset, the development of the action, the climax, the denouement and the postposition , therefore, the work should have at least 5 parts, each of which will represent one of the classical stages of the plot development. .
Each part, in turn, may consist of some semantic blocks: narratives, descriptions and arguments :
SCHEME OF TEXT-PAPULATION
- The beginning of the event.
- His development.
- The end of the event.
Note. In the artistic texts there is also the culmination preceding the end of the event.
TEXT DESCRIPTION SCHEME
- The general impression about the subject (phenomenon).
- Signs of the subject (phenomenon).
- Attitude to the subject (phenomenon).
TEXT DISCUSSION SCHEME
- Introduction.
- Thesis.
- Evidence (explanation).
- Conclusion.
Note. In the text-reasoning, sometimes the introduction and the thesis may coincide. In addition, in the text of this type of output in some cases may be absent.
If in each of the 36 plots to write an algorithm for the sequential construction of narrations, descriptions and arguments, then we get. almost the entire "skeleton" and the main "muscles" of the work.
In turn, inside a block there can be several paragraphs with a certain order of sentences inside them, which - sentences - in turn consist of words in a certain order and forms. Although it is believed that the Russian grammar is less enslaved than, for example, English, the standard literary style implies the direct construction of sentences - almost like in English - and any change in the places of the "components" of a sentence already implies emotional coloring or individual features of speech that we are now not interested.
And then, finally, we got the full text, having a randomly generated name, assembled according to the scheme of one randomly selected from 36 plot, with one of the random patterns, the location of paragraphs and sentences. Plain mediocre text. It remains to add to it what distinguishes the work of this author from the robot. Proper Names
Parsing lines is not such a difficult task. It is enough to place a marker like "# Main_Char #", "# Main_Enemy #", etc. into the original text instead of specific names and titles. The situation is somewhat complicated by the need to change the endings of words in different cases in Russian, but I think it’s not difficult to add another flag clearly indicating the use of a certain case ending.
Thus, several months of a competent programmer can replace hundreds of years and thousands of units of human labor. I dare to notice, absolutely useless and sad.
The web writer platform, obviously, should be the web:
- It has a low entry threshold for both the user and the developer.
- Good potential for modifications.
- Highest availability in the modern world
- Relatively high reliability due to the storage of information in the clouds
But one question remains: why is it really necessary? Well, I believe that if you save humanity from the need to write a lot and badly to set off rare talents, you will get more of them.
Source: https://habr.com/ru/post/161311/
All Articles