-
Hello,
I am running MOVERScore on summarization outputs, with both `n_gram=1` and `n_gram=2`. Surprisingly, I am getting the exactly same score in both cases. Shouldn't there be a difference, even …
-
I tried to reproduce the training of the fr-en simultaneous model. I follows the instruction to prepare the dataset and run the script train.simul-s2st.sh
The model training seems to go fine but the …
-
To calculate WordsPerMillion, we need access to all the occurrences of the query in all the documents of the corpus.
This is possible for a single term (`TermsEnum.totalTermFreq()`), but as far as I …
-
**Describe the bug**
Unigram 9.5 crashes on Windows on ARM, although I reinstall it.
**To Reproduce**
Steps to reproduce the behavior:
1. Install Unigram in Microsoft Store
2. Open it
**Expe…
-
We have 5 (or more?) different binary formats for the tagger that are supported. At least:
* Unigram model 1
* Unigram model 2
* Unigram model 3
* 2-gram HMM
* Perceptron
And additionally t…
-
Recently in Unigram to autocomplete an emoji for example :love left/right arrows have taken up bottom and up arrows, but the media sender still has the old arrows for scrolling. I think they should be…
-
Thanks for your Briliiant work !!!
However, I'm trying to use it on Orchestra, which means I have to get the hidden features from a multi-inst, if the work get the way to get the hidden features? It …
-
使用
```
seg = pkuseg.pkuseg(model_name='pre_model/pkuseg/default_v2.zip',postag=True)
```
导入下载的预训练模型“default_v2”时,导入失败,显示没有“unigram_word.txt”文件
```
File "......\Python38\lib\site-packages\pkus…
-
## Motivation
There are multiple libraries that implement subword models within the compression-based space. There is fastBPE, SentencePiece, YouTokenToMe, etc.
As far as I can tell there are f…
-
ann22 updated
3 years ago