Skip to content

Commit fa51d2e

Browse files
committed
change words
1 parent 9a608c2 commit fa51d2e

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -31,9 +31,9 @@ python setup.py install
3131

3232
- [AWS g4dn 2xlarge instance](https://aws.amazon.com/ec2/instance-types/g4/) is used to the experiment. (One NVIDIA T4 GPU with 8 vcpus, Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz)
3333
- results can be reproduced by simply running `examples/example_w2v.py` and `examples/example_lda.py`
34-
- To evaluate w2v model, we used `evaluate_word_pairs` function ([ref link](https://radimrehurek.com/gensim/auto_examples/tutorials/run_word2vec.html#evaluating)) in gensim, note that better performance on WS-353 test set does not necessarily mean that the model will workbetter in application as desribed on the link. However, it is good to be measured quantitively and fast training time will be at least very objective measure of the performaance.
34+
- To evaluate w2v model, I used `evaluate_word_pairs` function ([ref link](https://radimrehurek.com/gensim/auto_examples/tutorials/run_word2vec.html#evaluating)) in gensim, note that better performance on WS-353 test set does not necessarily mean that the model will workbetter in application as desribed on the link. However, it is good to be measured quantitively and fast training time will be at least very objective measure of the performaance.
3535
- I trained W2V model on `quora-duplicat-questions` dataset from gensim downloader api on GPU with cusim and compare the performance (both speed and model quality) with gensim.
36-
- To evaluate LDA model, I think there is no good way to measure the quality of traing results quantitatively. But we can check the model by looking at the top words of each topic. Also, we can compare the training time here.
36+
- To evaluate LDA model, I found there is no good way to measure the quality of traing results quantitatively. But we can check the model by looking at the top words of each topic. Also, we can compare the training time quantitatively.
3737
- W2V (CBOW, negative sampling)
3838

3939
| attr | 1 workers | 2 workers | 4 workers | 8 workers | GPU |

0 commit comments

Comments
 (0)