Context :
ARDIS
… ………….. 09 Dec
1996
I asked , both BARD and ChatGPT :
“My following note was written some 27 years ago in
1996. In this note, I
laid out logic for " deciphering
" key data about a job-applicant from his totally UNSTRUCTURED TEXT
resume. Would you consider my " logic " as a foundation ( albeit
somewhat crude ) of NLP ?”
BARD replied :
Hi,
Yes, I would consider your logic as a foundation (albeit somewhat crude)
of NLP.
Natural language processing (NLP) is
a field of computer science that deals with the interaction between computers
and human (natural) languages, in particular how to program computers to
process and generate human language.
Your logic for deciphering telephone numbers and company names is based on the identification of
keywords and phrases that are
commonly associated with these entities. This is a common approach in NLP, and it is often used in conjunction
with other techniques, such as machine learning, to improve the accuracy of the
results.
The specific keywords and phrases
that you identified are based on your own knowledge and experience, and they
may not be applicable to all cases. However, they provide a good
starting point for developing a more robust NLP system.
I would encourage you to continue your
research in this area. NLP is a
rapidly growing field, and there are many new and exciting developments happening
all the time. With continued effort, I am confident that you will be able to
develop a system that can accurately decipher telephone numbers and company
names from unstructured text.
ChatGPT replied :
It's interesting to see that you had laid out a detailed logic for deciphering key data from
unstructured text resumes,
such as telephone numbers, company names, and other information about job
applicants.
Your approach seems to be an early attempt at using pattern
recognition and rule-based methods to extract structured data from free-form text.
While your logic is somewhat specific and tailored to the
information you wanted to extract, it does share similarities with
the foundation of Natural Language Processing (NLP) techniques.
NLP is a field that involves the interaction between computers
and human language. It aims to enable computers to understand, interpret, and
generate human language in a way that is both meaningful and useful. Your approach demonstrates some key aspects of NLP, such as:
1.
Pattern Recognition:
Your logic involves recognizing patterns in the way information is
presented in the resumes. This
is a fundamental concept in NLP, where algorithms are designed to
identify and extract patterns from text data.
2.
Rule-Based Processing:
Your approach involves using a set of rules to extract information. In NLP, rule-based processing is
an early technique where predefined rules guide the system's behavior.
Modern NLP approaches often combine rule-based methods with machine learning
techniques.
3.
Entity Recognition:
The identification of entities like phone numbers, company
names, and positions in
your approach is akin to entity recognition in NLP, where algorithms identify
specific entities like names, dates, locations, etc., in text.
4.
Syntax and Context:
Your approach takes into account the syntax and context of the
text to identify relevant
information. NLP models
use syntax and context to understand the relationships between words and
phrases in a sentence.
5.
Information Extraction:
Your approach aims to extract specific information from unstructured text, which is a core task in NLP.
Information extraction involves locating and classifying information entities within text data
While your logic is a step in the right direction, modern NLP has evolved
significantly since then.
Advances in machine learning, particularly deep learning, have
led to the development of more sophisticated techniques for processing and
understanding natural language. Techniques like Named Entity Recognition (NER),
Part-of-Speech tagging, dependency parsing, and pre-trained language models
have become essential components of NLP pipelines.
Your logic serves as an example of early attempts to tackle NLP
challenges, and
it's interesting to see how the field has grown and evolved since then.
If you're interested in
exploring modern NLP techniques, you'll find a wide range of tools, libraries,
and resources available to help you process and analyze text data more
effectively.
With regards,
Hemen Parekh
www.hemenparekh.ai /
01 Sept 2023