rsennrich/subword-nmt
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
PythonMIT
Issues
- 1
- 3
How to find all valid BPEs for a word?
#119 opened by hlthu - 2
- 3
BrokenPipeError: [Errno 32] Broken pipe
#117 opened by whher - 1
learn_bpe.py code question
#116 opened by lzp-man - 1
- 1
Readme update please
#109 opened by youyinnn - 1
applying BPE(Byte Pair Encoding) fails for large Chinese data tokenized with THULAC
#113 opened by caesardai - 1
- 3
- 2
Unknown word and vocabulary filter
#111 opened by Hannibal046 - 2
Question about vocabulary filter
#110 opened by Hannibal046 - 1
Recover back code file
#105 opened by Hannibal046 - 2
About the vocabulary size
#108 opened by TomasAndersonFang - 4
No module named apply_bpe
#107 opened by RamoramaInteractive - 2
DeprecationWarning and ResourceWarning: Enable tracemalloc to get the object allocation traceback
#106 opened by RamoramaInteractive - 1
Expected format of input
#99 opened by hlncrg - 2
Facebook ParlAI Blender subword-nmt fails
#89 opened by gibmaxn - 3
subword-nmt
#101 opened by jh072535 - 1
learn_joint_bpe_and_vocab.py for Japanese
#103 opened by lovodkin93 - 1
BPE-Dropout question
#104 opened by oaarnikoivu - 1
learn_bpe.py error
#102 opened by unwritten - 1
Add tokens after pretraining
#97 opened by Bachstelze - 2
About how to use BPE in NMT.
#98 opened by TomasAndersonFang - 1
Intra-word boundary marker
#83 opened by Darenar - 2
BUG : Generating a vocab.bpe file "Killed"
#96 opened by Skylixia - 1
BPE vocabulary config
#95 opened by anrizal - 1
Restoring BPE
#93 opened by Oxi84 - 1
Seed for --dropout
#90 opened by noe - 3
Use Subword NMT inline in my python code
#88 opened by ajesujoba - 1
- 2
UnicodeDecodeError: fairseq-interactive example
#86 opened by isVoid - 9
About Programmatically usage
#76 opened by loretoparisi - 2
Meaning of the output file of learn_bpe.py
#84 opened by Gromy1211 - 1
BPE is language dependent or not?
#82 opened by umeshpant - 4
For languages that not share an alphabet, like chinese and english, should I train the shared bpe model or train their own bpe model separately?
#75 opened by luckysofia - 0
how to restore the original encoding from BPE encoding after translation?
#68 opened by shshen-closer - 2
How to recover the BPE
#80 opened by QAQ-v - 3
Trouble with a JavaScript Corpus
#78 opened by shamoons - 1
question about joint bpe vocab size
#79 opened by zrlhk - 2
Problem with a large corpus
#77 opened by nguyenvulebinh - 7
too many @ in the result
#71 opened by kFoodie - 4
- 1
- 4
- 1
Vocabulary size / convention
#67 opened by Kyubyong - 1
Post Processing
#64 opened by jigyasa06 - 1
- 2
Skip special tokens
#65 opened by voidmagic - 2
encoding issue?
#63 opened by kmario23