from Hacker News

What a crossword AI reveals about humans' way with words

by gsjbjt on 9/30/21, 8:35 AM with 49 comments

  • by bvm on 9/30/21, 10:28 AM

    I 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".

  • by weeblewobble on 9/30/21, 4:33 PM

    A few years back I wrote a program that, given a blank or partially-filled in (NYT-style) crossword grid (with black squares already inserted), could fill out the rest of the grid with valid words/phrases both across and down. It had no relation to clues though, you had to write the clues yourself after the grid was filled out.

    I wrote it because I wanted to make my dad (a huge nyt crossword fan) a custom crossword for his birthday. I put in a bunch of phrases related to him and our family and let the program fill in the rest. It was a huge hit, never really went back to it though. Anyone know if anything else like this exists?

  • by bvm on 9/30/21, 10:34 AM

    > 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.

  • by dom111 on 9/30/21, 9:30 AM

  • by isolli on 9/30/21, 9:52 AM

    "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?

  • by wirthjason on 9/30/21, 1:28 PM

    For some reason only the first paragraph was shown. I had to view it in privacy mode to see the whole article. I wonder if the ad blocker on my iPhone triggered something.

  • by wirthjason on 9/30/21, 1:33 PM

    This makes me curious, how are crossword puzzles made? Clues -> words? Or working backwards from words to clues? Some blend of the two?

  • by eutectic on 9/30/21, 1:03 PM

    I wonder how well gpt-3 + search would perform as a crossword-solving agent. I guess the tokenization might be tricky to deal with.