Hacker News new | ask | show | jobs
by philh 2529 days ago
In one model I found online[1], the closest word to "king" was "kings" (0.71) and the second closest was "queen" (0.65).

[1] http://bionlp-www.utu.fi/wv_demo/ (making sure to select the English model)

1 comments

If we eliminate king from the result list I would assume it's plural is removed as well. Bummer, that would mean the latent space algebra in this example has no effect whatsoever..
> If we eliminate king from the result list I would assume it's plural is removed as well.

In fact, the plural isn't removed. You can see the effect by analogizing A:B :: A:?.

For man:king :: man:?, you get [kings, queen, monarch, crown_prince] as the top 4. For man:king :: woman:?, the results are [queen, monarch, princess, crown_prince], with 'kings' as #6.

Of course, your model may vary.