As you might have seen here, I am currently working on Artificial Intelligence, to be more precise, in Machine Learning.
The main is to use Machine Learning in order to answer Biomedical and Healthcare issues, in order to have a department working on Life Sciences (which, in general, is still quite new).
But Machine Learning is a wide, broad thing and one might do many kind of analysis as well as answer to many questions throught it.
In my case, I am working on NLP processes.
- What is NLP?
NLP states for Natural Language Processing.
We call Natural Languages those languages that have not been created by humans in an artificial way ( as for example, programming languages ! ) but those that have been developped themselves organically during centuries along human history .
NLP is therefore a subfield of linguistics, computer sciences, artificial intelligence.
It is mainly concerned by the interactions with computer and human language.
Particularly, it focus on how computers can process and analyze large amounts of natural language data.
- What are the challenges?
We can identify mainly three bigs fields that are a challenge nowadays in NLP:
* Speech Recognition :
Speech recognition is a technology that enables a machine or program to identify and understand words or phrases from spoken language and convert them into machine readable format. It is a subfield of computational linguistics that deals with technologies to allow spoken input into systems.
* Natural Language understanding :
Natural language understanding interprets the meaning that the user communicates and classifies it into proper intents. For example, it is relatively easy for humans who speak the same language to understand each other, although mispronunciations, choice of vocabulary or phrasings may complicate this. NLU is responsible for this task of distinguishing what is meant by applying a range of processes such as text categorization, content analysis and sentiment analysis, which enables the machine to handle different inputs.
* Natural-language generation :
It often works closely with Natural Language Understanding (NLU), another sub-field of NLP. Where input is unstructured text, NLU helps in producing a structured representation that can be consumed by NLG. Generating language uses more of our brain than understanding it. Likewise, computers might find NLG a more difficult task than NLU.
A mature NLG system can free humans from mundane writing, create narratives quickly, enable almost real-time reporting, and streamline operations.
(you can consult the complete definitions here)
- What can be NLP used for?
NLP has many applications. The deep understanding of how humans talk and their communication can help in many fields from linguistic understanding to cybersecurity, personal assistance, translation tools and automatic responders.
- What about NLP in healthcare?
This is the field where, as a bioengineer, i will be using NLP. You can read all about that here (w.i.p)