What a crossword AI reveals about humans' way with words
1–10 of 50 posts
Re: What a crossword AI reveals about humans' way with words
#2Re: What a crossword AI reveals about humans' way with words
#3"But, unlike more than 200 human solvers, it wasn’t perfect on all of the puzzles: It got waylaid on two of them and finished with errors."
I'm curious, what kind of error are we talking about? Words that don't exist, or another solution to a problem that may not have a unique solution?
Re: What a crossword AI reveals about humans' way with words
#4"But, unlike more than 200 human solvers, it wasn’t perfect on all of the puzzles: It got waylaid on two of them and finished with errors." I'm curious, what kind of error are we talking about? Words that don't exist, or another solution to a problem that may not have a unique solution?
Also, as a novice to crosswords, how do puzzle makers ensure that they have a unique solution?
Re: What a crossword AI reveals about humans' way with words
#5"But, unlike more than 200 human solvers, it wasn’t perfect on all of the puzzles: It got waylaid on two of them and finished with errors." I'm curious, what kind of error are we talking about? Words that don't exist, or another solution to a problem that may not have a unique solution?
Also, as a novice to crosswords, how do puzzle makers ensure that they have a unique solution?
Related, this crossword designed to have two solutions: https://imgur.com/Atd5Dry
Re: What a crossword AI reveals about humans' way with words
#6"But, unlike more than 200 human solvers, it wasn’t perfect on all of the puzzles: It got waylaid on two of them and finished with errors." I'm curious, what kind of error are we talking about? Words that don't exist, or another solution to a problem that may not have a unique solution?
Non-existent words should be easy to check for. My guess is answers not (quite) matching the clues. Analogies and cultural references are probably hard for AI to get: is an "empire fighting knight" historical figure or Jedi? One level of such referencing is doable, 2-3 likely very hard.
Re: What a crossword AI reveals about humans' way with words
#7I would be interested to see how they perform on UK-style cryptic crosswords (https://en.wikipedia.org/wiki/Cryptic_crossword) where there's much more play/subversion/meta-approach to the "rules".
Re: What a crossword AI reveals about humans' way with words
#8"But, unlike more than 200 human solvers, it wasn’t perfect on all of the puzzles: It got waylaid on two of them and finished with errors." I'm curious, what kind of error are we talking about? Words that don't exist, or another solution to a problem that may not have a unique solution?
Also, as a novice to crosswords, how do puzzle makers ensure that they have a unique solution?
In a traditional cryptic crossword each individual word has at least two independent things in the clue referring to it, for example, in an unrealistically simple case, "it means X" and "it's an anagram of Y", so each individual answer is very likely to be unique. In addition, alternate letters of each answer are part of another word, so the whole thing is extremely likely to have a unique solution.
However, with a combination of a bad clue and a bit of bad luck it does sometimes happen that an experienced crossword solver has to take a guess before sending in their solution. I'm not an experienced crossword solver, but I've seen them at work, and I would guess that finding a good alternative solution happens less than one time in 50. That's just a guess, though. For a better estimate one should systematically compare the solutions produced by competent crossword solvers with the official solutions.
Re: What a crossword AI reveals about humans' way with words
#9> The crossword solver is a closed system—it can’t just Google the answers.
yet from the wiki:
> Probabilities for individual words or phrases in the puzzle are computed using relatively simple statistical techniques based on features such as previous appearances of the clue, number of Google hits for the fill. https://en.wikipedia.org/wiki/Dr.Fill
I don't think it's fair to describe it as a closed-system if it's Googling stuff, even for pruning.
Re: What a crossword AI reveals about humans' way with words
#10I would be interested to see how they perform on UK-style cryptic crosswords ( https://en.wikipedia.org/wiki/Cryptic_crossword ) where there's much more play/subversion/meta-approach to the "rules".
Yes, and fewer crossing letters, so there are usually many more words that will "fit".