09-12-2023, 09:27 PM
(This post was last modified: 09-12-2023, 09:30 PM by Macdaddy4sure.)
_AugmentedIntelligence Tackling NLU
NLP or Natural Language Processing or Computational Linguistics has been around since the 1980s and has roared back in the past few years with the NLP moniker. LLMs known as Large Language Models have appeared on the scene from companies like Google and OpenAI leading to NLP. The idea is to train a neural network and a model to simply generate and understand user inputs from a text prompt. Here are a few examples of what they can do. The examples are of generating text. This model can also produce C++ code from instructions as a text prompt! This development is extreme leap forward in Computer Science and is a game changer in schools.
The goal of natural language processing (NLP) is to design and build computer systems that are able to analyze natural languages like German or English, and that generate their outputs in a natural language, too. Typical applications of NLP are information retrieval, language understanding, and text classification.
I started from my ability as a child to read and write as my skills evolved I was confident in a decade or so this would be possible to write and find the next word in the sentence or paragraph and my completed papers. Regardless, I was presented with a task and have found solutions to NLP problems but the understanding eludes me. First we have lots and lots of data that is accessible on the internet like Wikipedia and Wiktionary. This task is not as simple as pairing word vectors to their labeled word counterparts, the words must be disambiguated. This processes is called Word-Sense Disambiguation. Without labeled data from Wikipedia I created a piece of software called a ManualPOSTagger or a Manual Part of Speech Tagger. This software is simple. The users enters an article from Wikipedia and prompts the user for labels like the word type, special word type. if a word is part of a grammatical object and what type of sentence it is in.
The document you are writing must also make sense as in, is it formatted correctly, reads well, and semantically correct.
In order for one to understand any word one comes across there are a few things to take note of. First the word must work in a brain. Meaning pictures, diagrams and other words with grammar trees. The computer will work entirely with word vectors and the words will be matched in the database.
NLP or Natural Language Processing or Computational Linguistics has been around since the 1980s and has roared back in the past few years with the NLP moniker. LLMs known as Large Language Models have appeared on the scene from companies like Google and OpenAI leading to NLP. The idea is to train a neural network and a model to simply generate and understand user inputs from a text prompt. Here are a few examples of what they can do. The examples are of generating text. This model can also produce C++ code from instructions as a text prompt! This development is extreme leap forward in Computer Science and is a game changer in schools.
The goal of natural language processing (NLP) is to design and build computer systems that are able to analyze natural languages like German or English, and that generate their outputs in a natural language, too. Typical applications of NLP are information retrieval, language understanding, and text classification.
I started from my ability as a child to read and write as my skills evolved I was confident in a decade or so this would be possible to write and find the next word in the sentence or paragraph and my completed papers. Regardless, I was presented with a task and have found solutions to NLP problems but the understanding eludes me. First we have lots and lots of data that is accessible on the internet like Wikipedia and Wiktionary. This task is not as simple as pairing word vectors to their labeled word counterparts, the words must be disambiguated. This processes is called Word-Sense Disambiguation. Without labeled data from Wikipedia I created a piece of software called a ManualPOSTagger or a Manual Part of Speech Tagger. This software is simple. The users enters an article from Wikipedia and prompts the user for labels like the word type, special word type. if a word is part of a grammatical object and what type of sentence it is in.
The document you are writing must also make sense as in, is it formatted correctly, reads well, and semantically correct.
In order for one to understand any word one comes across there are a few things to take note of. First the word must work in a brain. Meaning pictures, diagrams and other words with grammar trees. The computer will work entirely with word vectors and the words will be matched in the database.