Closed 2020zyc closed 5 years ago
I didn't evaluate the parsing speed precisely like the paper, so it may not be able to compare with it correctly. The time for training an epoch is about 4m50s, and it takes about 1m12s to evaluate the three datasets (43948 sents). I didn't estimate the time of decoding individually.
ok, thx and nice code.
Thanks :)
Recently I implemented the bucket mechanism adopted in tensorflow, which has made the speed twice as fast as I said before, but may result in a slightly loss of performance (95.79 & 94.08, still better than the official code). The implementation is still not perfect, but may give you some inspiration.
hi, how is the decode speed? Any evaluation? Thx.