hankcs
hankcs
Yes, radical embedding. Unigram inside character is radical.
radical.txt is a voluminous dictionary. What exists in a dictionary doesn't necessarily to appear in your text. character.vec is embedding of char pre-trained without subword information (i.e. word2vec). character-bi.vec is...
Hi, thanks for the suggestion. I think when stdin reaches an EOF (either the end of file or a CTRL+D), the loop will break.
Hi @zhijing-jin , thanks for reporting this bug. It's probably due to the famous "text degeneration" problem of many seq2seq models. After https://github.com/emorynlp/elit/commit/0dad49e587ce415e867f1c6aaf39a5261ebde9c4 is released, you can set `beam_size=4, no_repeat_ngram_size=4`...
Hi, seems that you have an legacy elit installed. The latest version doesn't print commands you gave. What you called is not what you installed just now. To confirm, run...
Well, then the `pip` on your system is of Python2. ELIT2.x only supports Python3 so pip downloaded the legacy version. To install 2.x, you need to run pip3 install instead....
Hi, the new error is due to your network failed to reach files.pythonhosted.org, which is a public site not maintained by us. I'd recommend you to either retry, or to...
1. This is raised by pytorch. Maybe your hardware is just too old. You can build from source to get rid of it: https://discuss.pytorch.org/t/bug-w-nnpack-cpp-80-could-not-initialize-nnpack-reason-unsupported-hardware/107518 2. Format per each annotation can...
Thanks for your prompt rely. I'm using `MRP2020_Train_Dev-2020CoNLL_CFMRP_LDC2020E05.tgz` from LDC, which might not be exactly the same with the one used in MRP2020 competion. Maybe `split_dataset.sh` creates random split too?...
@tuzhucheng Access Denied when `ls` your S3, could you confirm? BTW, the raw web pages can be downloaded from [Zenodo](https://zenodo.org/record/5115890#.YaeD7C8RppR) (passages.zip).