INFORMS Open Forum

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

Hi Carrie:
Semantic role labeling (SRL) should be useful for your first task. AllenNLP has an off-the-shelf model demo: 
https://demo.allennlp.org/semantic-role-labeling/semantic-role-labeling
You may have to fine-tune it using in-domain data.

--
Feng Mai, Ph.D.
Associate Professor of Information Systems & Analytics
School of Business
Stevens Institute of Technology

------------------------------
Feng Mai
Stevens Institute of Technology
Hoboken NJ

Original Message:
Sent: 04-04-2023 13:25
From: Carrie Beam
Subject: Text/language parsing help plus front-end developer referral?

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

------------------------------
Carrie Beam, Ph.D.
Director, MSBA Analytics Projects
University of California, Davis
Walnut Creek, CA
cbeam@ucdavis.edu
------------------------------

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

Hi Carrie,

For the referral, you could email Deji - a former colleague who does freelance development on the side of his current role at MS . I know he does a lot of work using React, JavaScript and the likes - ejiadedeji@gmail.com.

--
Izuwa, Ahanor
Ph.D. Candidate,
Industrial and Systems Engineering,
University of Tennessee.

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie

Hi all - asking for help on language/text parsing here. 

I have a consulting project in which they want to take in a paragraph or so of free-form text, such as a human's dictation of an event or an email describing a situation.  We want the computer to be able to extract out meaningful bits from this text, such as who the main agent is, what happened next, and what the final outcome was.  The challenge I'm running into is that NTLK/SpacY etc look like they will parse into subject and object, and even do dependent clauses, but 'Bobby checked the book out of the library' and 'The book was checked out of the library by Bobby' and 'The librarian handed Bobby the book' are three examples of three different text cases, all of which we would want to end up as Main Actor = Bobby, the item = book, librarian = helper, and checked out of the library = the action. 

Does anybody have any expertise in this that they would be willing to share, or know of a way you might point me? 

(We have tried ChatGPT and it's good but not good enough.  It tends to make up stuff, or get it slightly wrong.)  If it helps, this is a very narrow situation: the business process is much the same day in and day out, just described differently in different words.  We don't need to encompass the whole ocean here.

And on a slightly different note, I am also looking for referrals to a freelance computer programmer good with front-end things (think bubble.io, Angular, JavaScript, those sorts of things), to go on top of a client's back-end thing (SQL mostly.)  Any referrals would be most appreciated.

-- Carrie