All geek questions in one place

Turkish syntax dataset

I am new to Syntaxnet and I tried using a pre-prepared model of the Turkish language through the instructions here

Point-1: . Although I set the environment variable MODEL_DIRECTORY, tokenize.sh did not find the associated path, and it gives an error, as shown below:

root@4562a2ee0202:/opt/tensorflow/models/syntaxnet# echo "Eray eve geldi." | syntaxnet/models/parsey_universal/tokenize.sh
F syntaxnet/term_frequency_map.cc:62] Check failed: ::tensorflow::Status::OK() == (tensorflow::Env::Default()->NewRandomAccessFile(filename, &file)) (OK vs. **Not found: label-map**)

Point-2: So, I changed tokenize.sh by commenting on MODEL_DIR = $ 1 and setting the path for my Turkish model, as shown below:

PARSER_EVAL=bazel-bin/syntaxnet/parser_eval
CONTEXT=syntaxnet/models/parsey_universal/context.pbtxt
INPUT_FORMAT=stdin-untoken
MODEL_DIR=$1
MODEL_DIR=syntaxnet/models/etiya-smart-tr

Point-3: After that, when I run it, as said, it gives an error, as shown below:

root@4562a2ee0202:/opt/tensorflow/models/syntaxnet# echo "Eray eve geldi" | syntaxnet/models/parsey_universal/tokenize.sh
I syntaxnet/term_frequency_map.cc:101] Loaded 29 terms from syntaxnet/models/etiya-smart-tr/label-map.
I syntaxnet/embedding_feature_extractor.cc:35] Features: input.char input(-1).char input(1).char; input.digit input(-1).digit input(1).digit; input.punctuation-amount input(-1).punctuation-amount input(1).punctuation-amount 
I syntaxnet/embedding_feature_extractor.cc:36] Embedding names: chars;digits;puncts
I syntaxnet/embedding_feature_extractor.cc:37] Embedding dims: 16;16;16
F syntaxnet/term_frequency_map.cc:62] Check failed: ::tensorflow::Status::OK() == (tensorflow::Env::Default()->NewRandomAccessFile(filename, &file)) (OK vs. **Not found: syntaxnet/models/etiya-smart-tr/char-map**)

I downloaded the Turkish package by following the link template specified as download.tensorflow.org/models/parsey_universal/.zip and a list of language mapping files, as shown below:

  • -rw-r ----- 1 root 50646 Sep 22 07:24 char -ngram-map

    -rw-r ----- 1 root 329 Sep 22 07:24 label-map

    -rw-r ----- 1 root 133477 Sep 22 07:24 set-label-set

    -rw-r ----- 1 root 5553526 Sep 22 07:24 morpher-params

    -rw-r ----- 1 root 1810 Sep 22 07:24 -

    -rw-r ----- 1 root 10921546 Sep 22 07:24 parser-params

    -rw-r ----- 1 root 39990 Sep 22 07:24 prefix-table

    -rw-r ----- 1 root 28958 22 07:24 -

    -rw-r ----- 1 root 561 22 07:24 tag-map

    -rw-r ----- 1 root 5234212 Sep 22 07:24 tagger-params

    -rw-r ----- 1 root 172869 Sep 22 07:24 word-map

-1: , char -map, , @Point-3 . , - , , , , % 93,363 ?

-2: char -map ?

-3: char -map, , SyntaxNet ?

-4: , char -map... ..? word2vec, , wt. ?

+4

Source: https://habr.com/ru/post/1655461/

More articles:


All Articles