Note CoreNLP tokenizer correction on website

This commit is contained in:
Matthew Honnibal 2018-07-02 11:35:31 +02:00
parent 06c6dc6fbc
commit a85620a731
1 changed files with 9 additions and 3 deletions

View File

@ -157,7 +157,13 @@ p
+infobox("Important note", "⚠️") +infobox("Important note", "⚠️")
| This evaluation was conducted in 2015. We're working on benchmarks on | This evaluation was conducted in 2015. We're working on benchmarks on
| current CPU and GPU hardware. | current CPU and GPU hardware. In the meantime, we're grateful to the
| Stanford folks for drawing our attention to what seems
| to be #[+a("https://nlp.stanford.edu/software/tokenizer.html#Speed") a long-standing error]
| in our CoreNLP benchmarks, especially for their
| tokenizer. Until we run corrected experiments, we have updated the table
| using their figures.
+aside("Methodology") +aside("Methodology")
| #[strong Set up:] 100,000 plain-text documents were streamed from an | #[strong Set up:] 100,000 plain-text documents were streamed from an
@ -183,14 +189,14 @@ p
+row +row
+cell #[strong spaCy] +cell #[strong spaCy]
each data in [ "0.2ms", "1ms", "19ms"] each data in [ "0.2ms", "1ms", "19ms"]
+cell("num") #[strong=data] +cell("num")=data
each data in ["1x", "1x", "1x"] each data in ["1x", "1x", "1x"]
+cell("num")=data +cell("num")=data
+row +row
+cell CoreNLP +cell CoreNLP
each data in ["2ms", "10ms", "49ms", "10x", "10x", "2.6x"] each data in ["0.18ms", "10ms", "49ms", "0.9x", "10x", "2.6x"]
+cell("num")=data +cell("num")=data
+row +row
+cell ZPar +cell ZPar