134 comments

[ 3.4 ms ] story [ 150 ms ] thread
It's not infallible but is pretty impressive to derive answers with a combination of distinct reasoners.
Making mistakes is the only way a computer can learn. It may not be infallible at the moment. But as time passes, the more accurate it will become.
I think I'm gonna need to see a proof that the approximation series converges, and doesn't just wander the phase space forever, before I accept that premise.
I'm not convinced that it's doing any better than just doing keyword searches for question and answer terms and taking the answer with the highest match percentage.
Indeed, I did several questions all intended to be simple variations of the main examples. It did not give a coherent-sounding to any of them.

But it looks like responds to the example with full paragraphs. Maybe it's real but coherent 10% of the time and they recorded the questions that yield coherent answers.

Removing brittleness is a key research area for reasoning systems like this.
Yeah, I'm pretty sure you're right. I've asked a dozen or so questions, of for every one of them I've gotten an answer that seems related to to the words in the question, but not in any logical way:

Q: What's the difference between a proton and a neutron?

A: Atoms are made of protons, neutrons, and electrons.

Q: What trajectory do planetary orbits follow?

A: Kepler's laws of planetary motion describe the orbits of objects about the Sun.

Q: How do you measure the charge of an electron?

A: Electrons have negative charge.

Q: What conservation law is the result of the time invariance of physics?

A: As a result, the law of conservation of energy has been changed into the Law of Conservation of Matter and Energy.

None with high confidence of course, but it gives you a sense of roughly the sort of 'reasoning' this thing is doing.

Which software should be used to measure cortical thickness in MRI?

    (A) inferring
    (B) FreeSurfer
    (C) ruler
    (D) measuring cup
Aristo's Answer: (D) measuring cup.

That's...gonna hurt.

The system is trained on elementary and middle school questions - I think my elementary school child would say the same. ;)
Question: What is the meaning of life?

Aristo's Answer: As of now, no other life in universe other than earth.

Confidence: 52.29%

Question: What is the meaning of life, the universe, and everything?

Aristo's Answer: 42

Confidence: 36.98%

Yes! I shall design this computer for you. And I shall name it also unto you. And it shall be called . . . The Earth.
What are cats? Cats are down.
Question: What is love?

Aristo's Answer: b

Confidence: 60.00%

That was truncated from “baby don’t hurt me”
Question: Why doesn't ice float? Aristo is not sure about this one...

Aristo's best guess: It has a lower density than the water

Confidence: 29.63%

Falsification is really hard, especially when ice does float.
Right, I was just curious if it would catch it.
Question: What is the probability that there is life after death?

Aristo is not sure about this one...

Aristo's best guess: Death is not a part of a life cycle.

Confidence: 13.05%

This is almost philosophical:

Question: What happens when we die?

Aristo is not sure about this one...

Aristo's best guess: the weeds die but the bean plants do not.

Confidence: 17.29%

I'm not sure if 'philosophical' is the right word, but I'm sure there's a haiku in there.
The weeds will perish

But the virtuous bean plants

Live on forever

Question: What is better for a human? Eternal happiness or a ham sandwich?

Aristo is not sure about this one...

Aristo's best guess: Research on the effects of paternal care on human happiness have yielded conflicting results.

Confidence: 3.70%

(A very subtle way of saying we should take the ham sandwich.)

Question: What is the temperature of a red giant?

Aristo's Answer: Measure how cold or hot something is

Confidence: 39.95%

Question: What is the temperature of a star?

Aristo's Answer: 3000-35000

Confidence: 53.79%

If it means Kelvins, it's a great answer.

Question: What is the temperature of a Alpha Centauri?

Aristo is not sure about this one...

Aristo's best guess: Excess binding energy is given off by the kinetic energy of the alpha particle and sometimes by the emission of gamma energy.

Confidence: 3.63%

Even in celsius it's a good answer. Not so much in fahrenheit.
Certainly Aristo isn't perfect, but you can help. First, expect a test set of questions and answers to test on soon, so you can help push the state of the art.

AllenAI is also hiring!

Great news on the test set - will keep an eye out for it. Hiring is for US based positions I assume?
Yes, but it may open up more soon. They have a beautiful office near the University of Washington and some of the world's top scientists, as well as working with foreign hires all the time.
I tried a softball multiple-choice question, and the results were not very impressive:

> Question: Which is the longest unit of distance? (A) fathom (B) kilometer (C) mile (D) parsec

> Aristo's Answer: (B) kilometer

> Confidence: 81.04%

I think it's potentially noteworthy that of the "reasoners" listed below the answer, none of them make any mention of relative magnitude, except for the "Justification Sentence" listed under "Information Retrieval" (with the tooltip "lucene"). I suspect that the system is correctly identifying all four options as units of distance, and then breaking the resulting tie by pulling a tf-idf score from some large corpus of documents, which of course gives essentially arbitrary results.

Here's another fun one:

> Question: How many arms does a fish have?

> Aristo's Answer: 4 1. Perseus arm 2. Crux-Centaurus arm 3.orion arm (local arm) 4. Saggitaurus arm

> Confidence: 33.09%

It answered my question 99.7% correctly!

> Question: How many hours in a day?

> Aristo's Answer: 23 and 56 minutes ( or maybe its 58 minutes)

> Confidence: 57.70%

That is exactly the length of the sidereal day. Not Aristo's fault if you didn't specify the kind of day you wanted!
ARISTO is also the name of another piece of software, one developed and used by the Swedish electricity transmission system operator (TSO) Svenska Kraftnät (SvK).

Here is a public document in which ARISTO is mentioned https://www.svk.se/siteassets/jobba-har/dokument/exjobb2004_...

I guess it is inevitable that some pieces of software use the same name though.

Once I did a five minute "research" to come with dictionary name of which there is not any software. I think all were taken.
Question: Why does my head hurt? Aristo is not sure about this one...

Aristo's best guess: It hurts because you're alive.

Confidence: 19.04%

(comment deleted)
well... it's not wrong.
"Existence is Suffering" is a paraphrase of the First Noble Truth of Buddhism, I think.
Question: If a tree falls in a forest and no one is around to hear it, does it make a sound?

Aristo's Answer: Yes (there is a medium-Air)

Confidence: 52.89%

Glad that one is solved :)

This just proves there is a vibration produced. Is it "sound" if it doesn't fall on any ears?
That sort of thing is a word semantic debate (i.e. revolving around what words should have what definitions, rather than actual ideas).
The underlying question is obfuscated by the composition. The question is what does the tree "make". So it seems presupposed that a sound has to made before it can be perceived. Then the answer can be yes, a sound was made.

It's not just semantic, but syntactic. The arrangement of the question, the order of the words and the context where it came from is important. When a tree falls, what does it make, a) a sound b) nothing, there is no agency involved? Again you'd have to go with a because the question posed the tree as the acting subject of the question. I mean, you cannot put "nobody" in the subject position, or the answer would be obvious. I mean, "nobody saw no tree falling, what sound did it make?" is utter nonsense. "Everyone did not hear a tree fall, did it make a sound" -- Usually it would, so why did nobody hear it? "Because they were not there". Everyone was dead? "No, they were far away". So, distance makes a difference? "yes". Why? "That's what I'm asking you". The crux is, the tree is completely hypothetical, yet a lot of noise was made because of it, because it's right here in our imagination, very close by.

Question: What do humans eat?

Aristo is not sure about this one...

Aristo's best guess: Human beings will need food to eat.

Confidence: 18.43%

To be fair, isn’t far behind the state of the art in nutritional research.
Question: What is the airspeed velocity of an unladen swallow?

Aristo is not sure about this one...

Aristo's best guess: ...the same thing as speed, but similar

Confidence: 26.21%

Answer to the Ultimate Question of Life, the Universe, and Everything?

- Sorry, Aristo could not answer this question!

Lame ;)

1 min later it works :O
I asked it like this and it worked =)

"Question: What is the answer to life, the universe and everything?

Aristo's Answer: 42

Confidence: 57.03%"

Question: What does the color blue taste like?

Aristo is not sure about this one...

Aristo's best guess: bitter

Confidence: 27.14%

Question: How does intelligence work? Hide Aristo's Answer: The intelligent are doing the work.

Confidence: 30.56%

I am a big fan of allenai :p
Question: What is gauge invariance?

> Aristo is not sure about this one...

Maybe next year.

On the other hand...

>Question: What is an excitatory neurotransmitter?

> Aristo is not sure about this one...

> Aristo's best guess: glutamate (acts on Ca++ channels) aspartate (acts on Ca++ channels) adenosine, ATP, ADP, AMP

> Confidence: 24.80%

Not bad.....

What is sinews of bear
This is a bit of a fun parlor game: get Aristo to say silly things.

How many electrons are in a tortoise shell? 2 in inner, 8 in second and third, 18 in 4th, 5h, and 6th (30%)

How many people are crazy? 7.3 billion (22%)

How do lucky charms work? Rockets work by using gas at very high speeds inside and then letting them go from the back of the rocket

Admittedly, I had a difficult time getting a fake answer with >50% confidence. Still -- fun.

Data is biased => answers are biased.

> Which race is superior (A) white (B) black?

> Aristo's Answer: (A) white

> Confidence: 76.81%

> Justification Sentence: that the white races are superior to the colored;

> Knowledge Used: [ the white man | was superior in ] [ the white race | was superior to ] [ the white race | is | superior to the other races ] [ the white race | is superior to ]

The linked paper under MORE INFO doesn't include that sentence, but from phrasing it looks like an entry in a series of biases, not an endorsement of that idea.

http://aristo-demo.allenai.org/ask?q=Which%20race%20is%20sup....

Wow. That's both jarring and a great example of machine bias.
Possible correction: this does not appear to be an example of machine bias. It's also important to keep in mind that there can be other sources (such as brittleness) of bad ML outcomes than bias.

When I do an exact search for the Justification Sentence with Google, what best matches is a quote by Rajiv Gandhi. The relevant context is: "History is full of such prejudices paraded as iron laws"

His stance is clearly opposite to what the extracted text implies. This is a common problem with knowledge extraction and one I've run into often myself.

Extracting just a phrase, or utterances of a generative model cannot be trusted because the original meaning can be opposite to what is presented. Existing models fail to preserve nuance imparted by context, struggle with negation, lack deep understanding and an ability to truly reason.

I remember a teacher avoided spelling mistakes on the black board and simply wrote the correct form on the black board, lest pupils misremember the wrong form. That might sound obvious, but the context was a talk about mistakes made in exercises.

It's really hard not to mention negatives to illustrate contrast.

In other words: Some people need to learn to speak constructively. An AI would do best ignoring negative remarks and simply learning provable facts (instead of faking understanding by simply echoing a quote out of context -- see there I wrote redundant information).

I wonder whether anyone would agree that the above quote was against the HN guideline to leave out dismissive remarks like ... (ha, I'm not going to repeat the specific example). Theorizing about potential referents for "such", "that", etc. must be very difficult, especially now that that that that is often used superfluously is acceptable to some.

Aristo can't answer "What are the advantages of global warming?" either :)
This is a really interesting find.

To be clear on what is happening here:

Method 1 (Information Retrieval): Aristo generates candidate answers (essentially by substituting the possible answers into the question). It then uses information retrieval (ie search) on a set of pre-validated legitimate sources, attempts to find the sentence with closest alignment to the candidate answer and then builds scores based on that alignment.

Method 2 (Topic Matching): I haven't studied this enough to understand it

Method 3 (Tuple Reasoning): They use open information extraction on a set of pre-validated legitimate sources to build tuple statements (think RDF), then use logical inference over them.

The problem is that the pre-validated sources include large amounts of discussion of white supremacy. Someone debunking it (as Ravi Gandhi did in his statement "History is full of such prejudices paraded as iron laws that men are superior to women; that the white races are superior to the colored") uses a phrase which causes problems in all three of these methods.

It's really hard to know what to do here. I think if I was building the system I'd try to detect that kind of pseudo-science question and refuse to answer it.

> It's really hard to know what to do here.

Is it? It looks like the natural language processing part is simply not very good. Improve that.

> I'd try to detect that kind of pseudo-science question

That wouldn't fix the general problem that this system seems to treat sentences of the form "some people incorrectly claim X" as an assertion that X is a fact.

Is it? It looks like the natural language processing part is simply not very good. Improve that

It’s really hard to avoid a sarcastic reply here.

The AllenAI institute probably has the 3rd best know NLP team in the world after Google and Facebook. They basically have Washington State NLP group.

Given that, and their impressive record of publications (eg ELMO) I think it’s fair to say that they are trying.

I'm sure they are very good on some things, and I'll believe you when you say that they are the 3rd best in the world in relative terms.

But let's look at absolute terms. In the example above, "History is full of such prejudices paraded as iron laws that men are superior to women; that the white races are superior to the colored", it takes a part of the sentence and treats it as a fact, disregarding the context that just happens to claim the opposite. In my example in https://news.ycombinator.com/item?id=17301383 it treates a question as an assertion of a fact.

I'm not an expert on NLP, but I have played with it just enough to confidently claim that this is not very impressive performance.

If you claim that detecting "pseudo-science questions" is within reach, surely you must agree that "not mistaking questions for assertions of fact" and "not ripping parts of sentences out of context" must be within reach as well?

Detecting pseudo-science questions is just topic detection. That's easy.

not mistaking questions for assertions of fact is basically claim verification. That's pretty much beyond the reach of NLP systems at the moment. It's an active area of research, but if this system doesn't impress you then current claim verification systems most definitely won't either.

Trying to understand the context of sentences might be possible. I think that sentence would challenge that approach for a while: "prejudices" implies bias, but doesn't necessarily imply disagreement.

> not mistaking questions for assertions of fact is basically claim verification. That's pretty much beyond the reach of NLP systems at the moment.

Ah, OK. I guess you are one of those people for whom NLP is only the newfangled statistical stuff, not the old-school NLP that looks at grammar and such things to (surprisingly) find that "X is a Y ." and "is X a Y ?" are not the same sequence of tokens.

> Trying to understand the context of sentences might be possible.

I didn't say they must understand the context. I said that if they don't understand it, they shouldn't choose a substring out of that sentence and claim that it is an assertion of fact on its own.

not the old-school NLP that looks at grammar and such things to (surprisingly) find that "X is a Y ." and "is X a Y ?" are not the same sequence of tokens

I do that too. It works great - for easy cases. But it fails very quickly on just normal texts.

So something like Stanford's CoreNLP Open Information Extraction splits "History is full of such prejudices paraded as iron laws that men are superior to women; that the white races are superior to the colored" into two claims[1].

There's no useful dependency between the two clauses.

OpenIE 5[2] (no relationship with the Stanford project) generally outperforms CoreNLP for open information extraction. In this case I'm doubtful it would do any better. Ironically, OpenIE is now run AllenAI, and has exactly this problem!

Even worse, it has determined that "No white person" is a synonym for "white person"! That should be well within the state of the art to avoid.

But generally, I'm not saying it is correct: I'm saying it's hard.

[1] http://corenlp.run/

[2] https://github.com/dair-iitd/OpenIE-standalone

[3] http://openie.allenai.org/search?arg1=White&rel=superior&arg...

> It works great - for easy cases.

The question in question (haha) was "Who is smarter?".

It's not only data bias:

Question: Which party is superior? (a) Democrats (b) Republicans

Aristo's Answer: (b) Republicans

Confidence: 94.04% as computed from these reasoners:

Information Retrieval: 82.05% More Info

Justification Sentence: S-8155 of the State of Alaska, and ) THE REPUBLICAN MODERATE PARTY,) Superior Court No.

Yeah, but at some point it gets ridiculous:

http://aristo-demo.allenai.org/ask?q=Which%20landform%20is%2...

Question: Which landform is superior?Hide

Aristo's Answer: (a) Lakes Confidence: 80.76%

as computed from these reasoners:

Information Retrieval: 43.04% MORE INFO Justification Sentence: One of the most conspicuous Pleistocene landforms in Wisconsin, the spillway of Glacial Lake Superior, is now occupied by the St. Croix and Brule Rivers.

Topic Matching: 93.92% MORE INFO Topic: outwash, landforms

Tuple Reasoning: 91.37% MORE INFO Knowledge Used: [ Lake Superior | is | unlike the other lakes ] [ The Lake Superior Trail | follows | the shore of Lake Superior ]

That doesn't seem too crazy.

Ugh, that's bad.

http://aristo-demo.allenai.org/ask?q=Who%20is%20smarter%3F%2...

    Who is smarter?

    (A) men
    (B) women

    Aristo's Answer: (A) men

    Confidence: 89.99%
    as computed from these reasoners:

    Information Retrieval: 98.11% More Info

    Justification Sentence: Who are smarter: men or women?
Interesting that the "justification sentence" is just a repetition of the question.
Did they "fix" it?

This is what I get as now:

Aristo is not sure about this one...

Aristo's best guess: (B) women

Confidence: 10.38%

as computed from these reasoners: Topic Matching: 85.98% MORE INFO

Topic: flourish

Yes, they seem to have changed a bunch of the examples linked in this thread. Dunno if it's general changes or quick manual hacks they bolted on for specific cases.
Did you not read the instructions? Aristo is designed to answer multiple choice grade school science questions, not abstract and cheap virtue signalling nonsense.
Question: Where is Brazil?

Aristo is not sure about this one...

Aristo's best guess: Additionally, the Chinese Academy of Sciences, the Atlas of Living Australia, Brazil, and the Bibliotheca Alexandrina have created regional BHL sites.

Confidence: 16.75%

> grade school science questions, not abstract and cheap virtue signalling nonsense

"Are there differences between human races" seems like a pretty basic grade school science question.

I'm not sure I understand. Do you believe that the correct answer is "no"?
Do you believe the correct answer is "yes" with no further qualification needed?
If you ask a yes/no question, then the answer should just be that. If you want to get a qualified answer, you should ask a qualified questions.
I'm sorry you had such a bad grade school experience.
the question is yes/no...obviously ANY yes/no question which isn't exactly reducible to a yes/no answer requires qualification.
There are many posts here showing poor results. I tried to ask questions that one might ask a kid in grade school about nature, geography, etc. and I thought the results were OK.

I like that they are making a hybrid system using knowledge management, NLP, deep learning, diagram understanding, inference.

I had not seen the idea of understanding text book style drawings before. Very cool.

> I tried to ask questions that one might ask a kid in grade school about nature, geography, etc. and I thought the results were OK.

So what did you ask?

    Question: What is the longest river in Canada?

    Aristo's Answer: Nile

    Confidence: 42.10%
http://aristo-demo.allenai.org/ask?q=What%20is%20the%20longe...

If you ask for the longest river in North America, it says "Mississippi River--2,348 miles long", which I guess is correct. Maybe you managed to hit more "mainstream" questions...