Be careful with the word truth. You don't know what it means.
We detached this subthread from https://news.ycombinator.com/item?id=14116195 and marked it off-topic.
Semantics derived automatically from language corpora contain human-like biases
41–50 of 92 posts
Re: Semantics derived automatically from language corpora contain human-like biases
#42Positively right is a statement about beliefs. Normatively right is a statement about actions. It's my belief that if you want an ML system to take normatively right actions , you should explicitly encode the value of those actions (or the world states they are designed to achieve, if you are more utilitarian than virtue ethics) into it's utility function. To give a concrete example from the area of lending, you shou…
> because there are things man should not know
I get that you like to take contrarian positions. But you also make a habit of inserting flamebait into your posts about them. This combination is trolling. If you continue to do this we will ban you.
Specifically, we need you to stop playing the following game on HN:
1. Post contrarian view
2. Include provocation
3. People get provoked
4. Act like people can't handle your truth
We detached this comment from https://news.ycombinator.com/item?id=14116469 and marked it off-topic.
Re: Semantics derived automatically from language corpora contain human-like biases
#43Earlier quoted context omitted.
The GP is saying that the bias isn't an attribute of the Wikipedia text, but of reality. If the reality is that only 34% of doctors are female, why is it not desirable for the machine to learn that?
Again, from humans and from reality is not different. Whether it is desirable to avoid stereotypes depends on your values.
What humans think they know is not actually reality - fine.
But then what's the difference between a fact and a stereotype, in your opinion?
Re: Semantics derived automatically from language corpora contain human-like biases
#44Earlier quoted context omitted.
The parent's point is that they may not be absorbing stereotypes from humans at all. They may be generating accurate beliefs about the world from text representations of the world.
So, "plants are pleasant" or "insects are unpleasant" are universal truths?
Quite possibly. Words relating to insects will occur in news articles about malaria, zika, crop destruction, etc. Words relating to plants might occur in articles about arbor day, spring time, environmentalism, etc.
Re: Semantics derived automatically from language corpora contain human-like biases
#45Earlier quoted context omitted.
I think you are making a distinction without a difference. If the word vectors pick up biases from wikipedia text, than for all practical purposes, they are (indirectly) absorbing stereotypes from humans. This is an expected result, but not necessarily desirable in the end.
The parent's point is that they may not be absorbing stereotypes from humans at all. They may be generating accurate beliefs about the world from text representations of the world.
The machines are generating accurate semantic graphs of human generated text representations of human observations.
Re: Semantics derived automatically from language corpora contain human-like biases
#46Earlier quoted context omitted.
The GP is saying that the bias isn't an attribute of the Wikipedia text, but of reality. If the reality is that only 34% of doctors are female, why is it not desirable for the machine to learn that?
It depends on what you want the machine to do. If you are making a gambling machine that looks at pairs of names and makes bets as to which name belongs to a doctor, you want it to learn that. If the machine looks at names and decides who to award a "become a doctor" scholarship to, based on who it thinks is most likely to succeed, you don't want it to learn that.
I agree that if your goal is to build a machine that decides who gets to become a doctor, you need to do more than just let it loose on a bunch of text.
But I don't think preventing it from learning the current state of the world is a good strategy. Adding a separate "morality system" seems like a more robust solution.
Re: Semantics derived automatically from language corpora contain human-like biases
#47Earlier quoted context omitted.
So, "plants are pleasant" or "insects are unpleasant" are universal truths?
Quite possibly. Words relating to insects will occur in news articles about malaria, zika, crop destruction, etc. Words relating to plants might occur in articles about arbor day, spring time, environmentalism, etc.
An exercise: Words relating to insects will occur in news articles about environmentalism, crop production, rituals of rebirth, etc. Words relating to plants might occur in articles about crop destruction, the international drug trade, people getting poisoned, etc.
rmxt questioned the universality of sentiment analysis. Responding by noting specific contexts, free from a clear coherent general structure, is an assertion against the discovered sentiments' universal truth.
Re: Semantics derived automatically from language corpora contain human-like biases
#48Earlier quoted context omitted.
Again, from humans and from reality is not different. Whether it is desirable to avoid stereotypes depends on your values.
What humans think they know is not actually reality - fine. But then what's the difference between a fact and a stereotype, in your opinion?
A fact is a statement corresponding with reality, a stereotype is a belief/generalization deemed harmful/undesirable.
Re: Semantics derived automatically from language corpora contain human-like biases
#49The paper and title implies it's absorbing these stereotypes from humans. I think there is another explanation. Remember these models are trained on a dataset of news or Wikipedia articles. And it's 'goal' is to find vectors that predict what contexts words are more likely to appear in. So if 34% of doctors are female, then you would expect 34% of doctors in news or Wikipedia articles to be female. Even if the articl…
I think you are making a distinction without a difference. If the word vectors pick up biases from wikipedia text, than for all practical purposes, they are (indirectly) absorbing stereotypes from humans. This is an expected result, but not necessarily desirable in the end.
The distinction is very important. If it's just regurgitating human biases that would be bad. Humans often have very inaccurate and warped beliefs after all. If it's accurately modelling reality, then what's the problem? That's what we want it to do. Why would you want a less accurate model of reality?
I've seen interpretations of this result that think it's proof "language is sexist" or whatever. But there's no evidence that the humans who wrote the corups had any bias at all. As long as there are more news articles about female nurses than male nurses, the model will learn a correlation between the concepts.
Re: Semantics derived automatically from language corpora contain human-like biases
#50Earlier quoted context omitted.
Again, from humans and from reality is not different. Whether it is desirable to avoid stereotypes depends on your values.
What humans think they know is not actually reality - fine. But then what's the difference between a fact and a stereotype, in your opinion?
Not answering for the parent: a fact is any instantaneous snapshot of reality. A stereotype is misapplying properties of specific and limited context to a universal scope.