Re:Language models can explain neurons in language models
by xcv123 on Sunday May 14, 2023 @11:17AM
(#35938623)
I understand that this discussion can become frustrating, especially when you see repetitive patterns in the discourse or feel like the nuances are not being sufficiently addressed. However, there are a few points I would like to clarify:
Semantics in word embeddings: While I agree that word embeddings cannot fully capture human-like semantic understanding, they do provide a mathematical representation that has proven useful in many NLP tasks. It's not that word embeddings "understand" semantics in the human sense, but they do capture certain aspects of meaning that are statistically derived from their use in the training corpus. This is not an unsubstantiated claim. It is empirically demonstrated in numerous tasks where semantic understanding is beneficial, like semantic similarity, word analogy, and other downstream tasks such as sentiment analysis, text classification, etc.
You mentioned that connectionists only improve their systems when someone rubs their face in it. This is essentially how scientific progress happens - through skepticism, criticism, and the relentless pursuit of truth. I would argue that the current era of deep learning research is no different. It's a messy, iterative process, with steps forward, backward, and sideways.
Your point about BERT overfitting to statistical regularities of the dataset is well taken. Indeed, it exposes the limitations of the model and the need for careful design and evaluation of benchmarks. However, it's worth noting that a failure in one specific test doesn't invalidate the successes in other tasks. It simply highlights an area that needs improvement.
It's true that there's a flood of papers and not all of them have substantial novelty or impact. This is not a problem exclusive to deep learning or AI, but a broader issue in academia and scientific publishing. However, amidst the noise, there's also a lot of valuable work being done, with genuine advancements and novel approaches.
Finally, while it's true that we may be over-optimistic or uncritical at times, it's also important to recognize the significant advancements that have been made. AI systems, though imperfect, are now capable of tasks that were thought to be infeasible not too long ago. That's not a spectacle, but a testament to the collective efforts of researchers around the world.
I appreciate your critical perspective and your emphasis on rigorous scientific inquiry. Such discussions are important for the health and progress of the field.
PS: I understand where you're coming from. Better to not take any of it personally. Sometimes I need a break from this too. Remember there is no malicious intent here when people are just sharing their views.
Semantics in word embeddings: While I agree that word embeddings cannot fully capture human-like semantic understanding, they do provide a mathematical representation that has proven useful in many NLP tasks. It's not that word embeddings "understand" semantics in the human sense, but they do capture certain aspects of meaning that are statistically derived from their use in the training corpus. This is not an unsubstantiated claim. It is empirically demonstrated in numerous tasks where semantic understanding is beneficial, like semantic similarity, word analogy, and other downstream tasks such as sentiment analysis, text classification, etc.
You mentioned that connectionists only improve their systems when someone rubs their face in it. This is essentially how scientific progress happens - through skepticism, criticism, and the relentless pursuit of truth. I would argue that the current era of deep learning research is no different. It's a messy, iterative process, with steps forward, backward, and sideways.
Your point about BERT overfitting to statistical regularities of the dataset is well taken. Indeed, it exposes the limitations of the model and the need for careful design and evaluation of benchmarks. However, it's worth noting that a failure in one specific test doesn't invalidate the successes in other tasks. It simply highlights an area that needs improvement.
It's true that there's a flood of papers and not all of them have substantial novelty or impact. This is not a problem exclusive to deep learning or AI, but a broader issue in academia and scientific publishing. However, amidst the noise, there's also a lot of valuable work being done, with genuine advancements and novel approaches.
Finally, while it's true that we may be over-optimistic or uncritical at times, it's also important to recognize the significant advancements that have been made. AI systems, though imperfect, are now capable of tasks that were thought to be infeasible not too long ago. That's not a spectacle, but a testament to the collective efforts of researchers around the world.
I appreciate your critical perspective and your emphasis on rigorous scientific inquiry. Such discussions are important for the health and progress of the field.
PS: I understand where you're coming from. Better to not take any of it personally. Sometimes I need a break from this too. Remember there is no malicious intent here when people are just sharing their views.