Hacker News Reader

Comment by elpachuco | Hacker News Reader

>>Another example of a good language problem is question answering, like “What’s the second-biggest city in California that is not near a river?” If I typed that sentence into Google currently, I’m not likely to get a useful response.

So I typed that in google just to see and indeed I got nothing. I guess their [1]knowledge graph still has a long way to go.

[1http://www.google.com/insidesearch/features/search/knowledge...]

View on HN

Resolving these kind of queries is same as asking system to write a Turing complete program. A generalized query essentially sets a goal and the resolver is expected to create a program on the fly to build an answer.

For example, you can set a query "what's the 2nd biggest city in CA not near the river that has weather same as Seattle and is not among the top 500 cities in US".

As you can see generalized query would literally require system to create a program on its own. If we can do this, we would not need programmers and very likely it would be same breakthrough as practically unlimited supply of energy.

http://www.quora.com/What%E2%80%99s-the-second-biggest-city-...

Wolfram can handle it: http://www.wolframalpha.com/input/?i=2nd+biggest+city+in+Cal...

That misses the key qualifier: "near a river". The challenge there is what is "near", and what is a "river"?

You are right of course.

I was playing with it, had to go to a meeting and forgot I'd modified the question.

Uh, no, that's just "the second biggest city" Wolfram can't even handle "What is the second biggest city in California near a river" - IE, can't do something one step beyond the trivial.

http://www.wolframalpha.com/input/?i=What+is+the+second+bigg...

Can't even handle "What is the second biggest city in northern California" http://www.wolframalpha.com/input/?i=What+is+the+second+bigg...

Reply on news.ycombinator.com