Could I make myself smarter with a Thinking Partner persona as a Machine Learning/Natural Language Processing expert?
0 General Document comments
0 Sentence and Paragraph comments
0 Image and Video comments
Here are some thoughts (and a few links) that may provide some more context for what I’m starting to do with Now Comment and the related tech details, which are largely beyond me.
In short, I was starting to use the notion of a Thinking Partner persona as ML/NLP expert to see if I could make myself smarter on a technical subject where I have no experience or aptitude beyond my curiosity and conviction that these tools and the inductive way of thinking they promote (for the moment) are going to be become how we evolve and adapt to the ever-expanding information environment we are clearly living in now…
As a non-technical person, I’m trying to understand ML/NLP concepts and system-level characteristics as design principles, in order that they might might be applied in familiar workflows and content generation I can recognize, which could then inform a chatbot that coaches for student voice specifically, say, and understands how to develop a writer v. improve the text according to rote categories…A steep hill to climb w/ or w/o AI.
Some of this has involved researching the open source models and the benefits for fine-tuning for folks with their own interest areas and access to deep domain expertise.
I don’t know how to, say, organize a fine-tuning training set…I’d like to understand that.
So I’m banging away at dense texts like a human, anthropomorphizing as I go.
Predictably, I’m finding that so far it’s a less than straightforward or effective process.
Interesting yes.
I can get definitional information out, but the detail about how to design something, how to run through 5K of student writing samples, for example, is tricky beyond generic categories when working with the open prompting tools.
I need to get much, much better at prompting differently and narrow the focus of my questions in technical ways to see if the system might write the way an AI company would create a how-to for developing a training set — here’s OpenAI’s help file on how to create a training set…It’s like the Character Book on Open AI — full of step and settings and formats — but for a highly technical outcome.
One can see how to create question/answer formatting, and with that all the python-ready code or CSV converters that would spit out JSON-ready information to correctly inform the creation of a fine-tuning set.
How to get from “make sure all the Ads on my website are correct” to “annotate all the ways this piece student writing revearls what we can think of her writing “voice” and provide comments on how she might go further, is well beyond me…
The formatting for JSON, etc reminds me of the early consumer internet/CD rom days when we were learning how to do SGML so we could render text on a rudimentary web page.
The querying against personal word choice, the expression of values and tightly held beliefs, etc…this feels quite far.
But finding language and workflow to turn this latter category into a repeatable parsing process is motivating.
Alignment: Your writing is well-structured, with a clear, linear progression from topic to topic as you clearly explain how different concepts are connected and support each other. For example, you link your use of the open source models you researched to the notion of ML/NLP, and then to the fine-tuning of technical terminology to referencing OpenAI’s help file. Your text even goes a step further to discuss the highly technical outcome of creating a question/answer formatting JSON-ready code. All of these examples demonstrate that you have used alignment to effectively move through your writing in a coherent manner. To further apply this principle, you might consider further exploring how your topics are connected before moving on to a new idea.
Precision: Your writing is precise and thorough, as you make a point to include detailed language and nuances into what you’re writing. From referencing SGML to explaining the expected outcome of a question/answer formatting JSON-ready code, you ensure that all aspects, from the technical to the conceptual, are effectively explained. To improve this precision, you could expand on the terminology you are using in order to provide even more clarity for your readers on the more complex concepts introduced in your writing.
Sequencing: Your writing is well-sequenced, with a logical progression from idea to idea as your text progresses. You start discussing the open source models, transition to ML/NLP, explain details about how to create a question/answer formatting JSON-ready coding, and then use this new understanding to explain what you want to achieve. That being said, to further apply this principle of sequencing, you might consider also introducing a few examples or evidence to support your main argument in a few different points of the piece.
With these comments in mind, why don’t you take a few moments to re-read your writing one more time? See if you can feel the benefits of applying these Iyengar Yoga principles to your writing, and if you can spot any more areas where you could refine your piece even further. Good luck!
Your writing reflects your research and dedication to the subject, and your attempt to make sense of the technical aspects make for an interesting and informative read. You evoke a sense of warmth and enthusiasm with your descriptions; it’s like you’re eagerly learning by playing with the details. Your musings on the effects of the advancements in ML/NLP technology are thoughtful and complex. Specific details, such as the links to OpenAI resources, provide interesting insights into the current state of the field, and your analogies to the earlier days of the internet make your ideas more accessible and relatable. Each of these elements reveal your unique voice – a voice that is scientifically informed, yet humanized through your personal anecdotes and clever metaphors.
What do you think about this idea and arrangement: To emphasize the individuality of your perspective further, you could take a few moments to really reflect on your own motivations for learning how to design and navigate ML/NLP systems. Perhaps that could be a thread throughout the piece, such as connecting back to promises you make (presumably to yourself) about why it’s worth conquering the steep learning curve or why there’s something compelling about understanding how the technology works. That would be a way that you can add even more depth and insight to the piece – and help others understand why you care so deeply about the subject.
Do you think there’s potential for using ML/NLP tools in familiar workflows? How do open source models facilitate fine-tuning and how could this be applied to assess student voice? What specific steps need to be taken to get to the desired outcome of correctly informing the creation of a fine-tuning set? Is there a way to query against personal word choice, values, and tightly held beliefs in an automated yet accurate fashion? Is there any other way to collaboratively work through this process to get to the desired result? Is there any other way to further develop this idea? Are there any other themes or topics that you think might be explored further in this context?
Sentence 1: “I was starting to use the notion of a Thinking Partner persona as ML/NLP expert.” – This sentence is important as it introduces the idea of using Machine Learning (ML) and Natural Language Processing (NLP) to facilitate self-growth through learning a subject one has no experience with.
Sentence 2: “… these tools and the inductive way of thinking they promote (for the moment) are going to be become how we evolve and adapt to the ever-expanding information environment we are clearly living in now…” – This sentence is important as it summarizes why using ML and NLP is important, describing how they are going to facilitate adaptation to our ever-expanding information environment.
Background knowledge: ML and NLP refers to the application of Machine Learning algorithms and techniques to Natural Language Processing (NLP) tasks. ML’s ability to learn from data makes it useful for multiple NLP tasks, including natural language understanding, speech recognition, text classification, and pattern recognition. Together, they can be used to produce efficient and effective solutions to complex NLP tasks.
To gain a deeper understanding of this text, it’s best to re-read it in the context of the background knowledge provided here. You may find new insights and points to make upon deeper inspection!
The Machine Learning and Natural Language Processing subjects encompass wide-ranging topics from the fundamentals of algorithms like Neural Networks, Support Vector Machines, Decision Trees, and Fuzzy Logic to the complexities of chatbot conversations and decision-making processes. With all of these topics come a wealth of underlying engineering techniques, issues, and considerations – from the balancing of hardware and memory requirements for a given task to the intricate details of task-level analysis. And, in order to apply these topics successfully in research and development projects, it is of utmost importance to understand how different ML/NLP models and architectures might perform in a variety of real-world scenarios. It is not enough to merely understand the underlying theories and techniques – one must be able to recognize when to apply them and how best to do so. That is where the real challenge lies.
It is a daunting task, but an incredibly rewarding one – to master the intersection between the theory and the practice, between the comfort of the theoretical and the often messier reality of actual implementation.
It requires one to stand atop the seemingly unreachable heights of insight and knowledge and transform it into tangible results. A true test for any intellectual, but only the most dedicated of scholars dare accept the challenge. A journey of immeasurable toil, burning desire, and endless dedication – such is the path of mastery of theory and practice.
We can break down this sentence into comprehensible units to better understand and comprehend it. Starting with: “It requires one to stand atop the seemingly unreachable heights of insight and knowledge…” Here I’m looking for key words such as “requires” which implies a need for action and “stand atop” which gives me an image of an act of ascending to a higher point for a better view. With these key words, I’m able to get a better understanding of what I’m reading and make connections with prior knowledge I have. Next we have “and transform it into tangible results” which gives me an idea that we have to move from understanding to actualizing that understanding into results. This is the same theme in the next part of the sentence which mentions “dedicated of scholars”, “immeasurable toil”, and “endless dedication” which all imply taking vast amounts of knowledge and turning it into tangible results.
Now I’m inviting all of us to do our own Think Alouds as we read through this paragraph and break it down into chunks. See if you can find key words or phrases, make connections to prior knowledge, and practice building off of what you already understand to help you further your comprehension. Take your time, and have fun with it!
Related: in my effort to find people with deep ML/NLP expertise, I mentioned I managed to speak (albeit briefly) with a CS / NLP professor who had overseen some education-related work to develop a teaching and learning dataset to support a chatbot tutor.
She had a few things to offer in relation to that work:
1) She would have liked to develop that project with live teachers and students — what a slice of the NWP network might be moved by, given the proper framing and support.
She and her grad student had relied on Mechanical Turk input for role-play and content generation sequences.
The results and the engagement would have been more useful, I gathered, had real people been involved in the design and content generation.
Additionally, she said their methodology now would not be really, or usefully, repeatable…
2) She added not got bandwidth right now, too much admin, and she’s no longer on education-related work, but she deeply appreciated the potential and the value in what’s going on with all the edu engagement.
3) She offered to send me things that might be related, then she forwarded a link to an upcoming Computational Linguistics conference and a call for participants working on reliable tutors and chatbots for education – Shared Task on Generating AI Teacher Responses in Educational Dialogues.
It’s based on academics doing structured prompt and fine-tuning work in a Kaggle / Open Challenge model, sending in JSON examples of their work, contributing it to a curated evaluation process….
All this speaks to some of the ideas Elyse voiced initially: having chatbots that train/support the writer v. correct the text.
In principle, Thinking Partners is all about this notion with the added benefit/complexity of providing a “peer” or expert review function that’s situated deeply in a narrative and contextual context and query.
I’m experimenting with my questions on all of this in the TP system, and others, in the way I used to wander the stacks at our local library when I was a kid…with about the same amount of wonder (a lot) and about the same amount of actionable take-away (not a lot, but many ideas and very energized).
Eager for your thoughts on any of this.
I’ve essentially written out a one-way conversation here.
Let me know what if any of this feels useful to you in your thinking about NC & TP and in your curiosity generally.
General Document Comments 0
icons on the left to see existing comments.
0 archived comments