Unfortunately, using spacy-stanfordnlp gives slightly less control over pretokenisation and dis/enabling sentence segmentation in a mutually exclusive manner.
-
-
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Nice work! I think there's a spacy-udpipe package as well? I haven't used it, but the UDPipe models are pretty good. It's possible the wrapper will be better. I never solved the batching thing in the spacy-stanfordnlp wrapper, so the speed is much worse than it should be.
-
Thanks! Spacy-udpipe seems like a good trade-off in quality v. speed. I'll see if I can support it, too. Even if spacy-stanfordnlp's batching worked perfectly, I think spaCy's speed is hard to beat. I'm still surprised how you pull it off, it's astonishing!
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.