Yiran Wang comments

Results 16 comments of


                                            Yiran Wang

How to generate my own distillation dataset for Levenshtien Transformer

Hi, have you solved that? I am facing the same problem.

The equal sign in double quotation marks is not parsed correctly

So, should I close the issue on [SublimeREPL page](https://github.com/wuub/SublimeREPL/issues/480)?

Why not outputs += inputs ?

if you re-run your program, could you please let me know the new results? thx

Bert Embedding Extraction

Hi, thank you for sharing the source code. I am also curious about the influence of the document-level BERT, could you please share me with your document-level BERT embedding files?...

Bert Embedding Extraction

@juntaoy Thanks for your reply. I found there is a `doc_key` in your `jsonlines` format example, but what is that? Should I just group all the sentences in the document...

Bert Embedding Extraction

@juntaoy But for OntoNotes 5.0, there is not `-DOCSTART-` as document indicator, how do you handle this?

Questions about the experiments details

Wow, thanks for your quick response. I got two more questions. 1. If I understand correctly, in table 2, the numbers of `BitFit` were taken from the [original paper](https://aclanthology.org/2022.acl-short.1). But...

Questions about the experiments details

Thanks~

可以用pip安装吗

只要是提供了 setup.py 的 GitHub repository 一般来说都可以用 pip 安装. `pip install git+https://github.com/howl-anderson/hanzi_chaizi.git`