Scribd
Upload
111 views4 pages

Assessment 5 - Natural Language Processing

The document summarizes an article about natural language processing. It discusses how natural language processing is mostly accomplished through machine learning and neural networks. Some key applications of natural language processing mentioned include automatic summarization, presenting information in a human-friendly format, and reducing work for tasks like reporting. However, the author notes that they have not found many resources that explain how to use natural language processing libraries at a beginner level.

Uploaded by

api-483095692
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
111 views4 pages

Assessment 5 - Natural Language Processing

The document summarizes an article about natural language processing. It discusses how natural language processing is mostly accomplished through machine learning and neural networks. Some key applications of natural language processing mentioned include automatic summarization, presenting information in a human-friendly format, and reducing work for tasks like reporting. However, the author notes that they have not found many resources that explain how to use natural language processing libraries at a beginner level.

Uploaded by

api-483095692
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Park 1

Jeff Park

Mr. Speice

Independent Study and Mentorship

11 October 2019

Natural Language Processing

Research Assessment 3

Date: 11 October 2019

Subject: Natural Language Processing

Works Cited:

Heller, Martin. "Natural language processing explained." ​InfoWorld.com,​ 29 May 2019. ​Gale

General OneFile​,

https://link.gale.com/apps/doc/A587036144/ITOF?u=j043905010&sid=ITOF&xid=b5bc

37cf. Accessed 11 Oct. 2019.

Natural language processing has become increasingly relevant in the technology sector as

a result of increased computing capabilities and the general growth in the utilization of machine

learning techniques. Natural language processing is now mostly accomplished through the use of

machine learning and neural networks. However, for it to work effectively, a lot of data

preparation must be made, and sufficient processing power is required.

There are specific functions that can be accomplished through the use of natural language

processing. One of the most common functions is automatic summarization. This function has

many applications regardless of the career involved as summarization would cut out irrelevant
Park 2

information and save time on anyone using the summarization program. Therefore, some aspects

of natural language processing can be applied essentially anywhere to reduce the load on

employees. In addition, natural language processing allows for information to be presented in a

human-friendly format. For example, information regarding a press conference can be outputted

into paragraph text using natural language processing. This would allow for the automation of

low-end journalism tasks and also save time when creating reports. For software developers, it

could reduce work spent on project management tasks such as reports. Especially for scrum

software development models which require frequent communication between team members,

natural language processing serves to make the process easier.

The article also referenced many Python libraries and educators that should continue to

guide my path for my machine learning projects. However, based on the lexile measure of this

article, it might assume a more advanced understanding of machine learning from its readers.

However, I now have more leads on where I can go to learn more about machine learning in

general. One of those people is DJ Sarkar, who apparently posts excellent tutorials on natural

language processing. The Python libraries mentioned were Beautiful Soup, Natural Language

Toolkit, and SpaCy. Combined with Google’s TensorFlow, I should have a relatively smooth

experience learning machine learning with a Python frontend. There were some other products

and tools that were discussed, but they seem to have limited relevance to my experience level

and goals. For now, my goal is probably to gain a foothold in the world of python machine

learning. However, I have still yet to encounter many resources that explain how to use these

libraries at a complete beginner level. Therefore, for my next assessment, I need to figure out

where complete beginner resources can be found.


Park 3

Overall, this article named a lot of new resources that I can look further into, and I can

see their connection to some of the other concepts I have learned from past research assessments.

It appears that Python is very much a favorite among developers for machine learning purposes

due to its easy to use nature. There are many resources that teach data analysis and machine

learning for those who already have a good understanding of computer science concepts and

other Python libraries. However, I have trouble finding resources that teach machine learning

concepts and usage of Python library at an absolute beginner level. Most of the understanding of

computer science I have gained is mostly through hands-on experience, so I do not have much

academic understanding of computer science.


Park 4

Annotated Works

Annotations

You might also like