Show HN: Language games – simple games made with word vectors

Re:Show HN: Language games – simple games made with word vec... by SamBam on Monday January 06, 2020 @03:53PM (#21973184)

I'm failing to understand game 4:

    Player 0 it is your turn!
    The word you are trying to match in meaning is:
    antepenultimate
    Your char list is:
    ['i', 'g', 'j', 'u', 'b']
    Please input a valid word made from some or all of the provided characters

What's the right answer?

[ Parent | on HN ]

Re:Show HN: Language games – simple games made with word vec... by ggggtez on Monday January 06, 2020 @04:32PM (#21973577)

Importantly: there was no "right answer" in mind when it created the question. The letters were random, as was the word.

It calculates the distance in vector space from your word to the given word.

I think it helps if you understand what Word2Vec is, as then it becomes clear what is going on.

[ Parent | on HN ]

Re:Show HN: Language games – simple games made with word vec... by dcsan on Monday January 06, 2020 @05:49PM (#21974370)

so you didn't have a word near penultimate and then pick some letters from it? It's really just open-ended what the users should choose? That does make it a lot harder...

[ Parent | on HN ]

Re:Show HN: Language games – simple games made with word vec... by chosenPixel on Monday January 06, 2020 @03:55PM (#21973205)

'bug' would be one i'd assume

[ Parent | on HN ]

Re:Show HN: Language games – simple games made with word vec... by SamBam on Monday January 06, 2020 @04:14PM (#21973388)

But how does "bug" match the meaning of "antepenultimate" in any way? I must be missing the point of the game.

Is it just "words that vaguely, extremely distantly, have some relation, as determined by the neural net"? And your job is to work out which extremely-distant word is slightly closer? (I noticed "gubi" scored very, very slightly more points than "bug" in the demo.

[ Parent | on HN ]

Re:Show HN: Language games – simple games made with word vec... by ggggtez on Monday January 06, 2020 @04:35PM (#21973601)

You are basically correct. https://en.wikipedia.org/wiki/Word2vec

Essentially, all words are embedded in an N-dimentional space. Then you can simply measure the distance between words in the word-cloud. The exact method of how it decided what coordinates to assign to each word in the cloud isn't important to the game.

[ Parent | on HN ]