Add a short description here!
Project description
Implement some keyphrase generation algorithm
Description
Implemented Paper
CopyRNN
Deep Keyphrase Generation (Meng et al., 2017)
CopyCNN
CopyTransformer
Usage
required files (4 files in total)
vocab_file: word line by line (don’t with index!!!!)
training, valid and test file
data format for training, valid and test
json line format, every line is a dict
Notes
- compared with the original
seq2seq-keyphrase-pytorch
- fix the implementation error:
copy mechanism
train and inference are not correspond (training doesn't have input feeding and inference has input feeding)
easy data preparing
tensorboard support
- compared with the original
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
deep-keyphrase-0.0.5.tar.gz
(30.9 kB
view details)
File details
Details for the file deep-keyphrase-0.0.5.tar.gz
.
File metadata
- Download URL: deep-keyphrase-0.0.5.tar.gz
- Upload date:
- Size: 30.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/42.0.2 requests-toolbelt/0.9.1 tqdm/4.41.0 CPython/3.7.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d53739d5c322dc64f8a2ec4bfceecfc111bff005c1502fbc18c5aa3c949db603 |
|
MD5 | 4934e5cc5032a86a526c40d8cc03c9bf |
|
BLAKE2b-256 | b42abdd249bb513d48ad653dd767e7b8b08fd9795e28c0b78006dabc1d19d3dc |