emnlp2017-bilstm-cnn-crf icon indicating copy to clipboard operation
emnlp2017-bilstm-cnn-crf copied to clipboard

CoNLL.py Getting an Error in Train_Chunking.py

Open prometheusloong opened this issue 5 years ago • 2 comments

Using TensorFlow backend. Generate new embeddings files for a dataset Read file: komninos_english_embeddings.gz Added words: 3 :: Transform agac_chunking dataset :: Traceback (most recent call last): File "Train_Chunking.py", line 47, in pickleFile = perpareDataset(embeddingsPath, datasets) File "/public/home/zcyu/ref/NLP/emnlp2017-bilstm-cnn-crf/util/preprocessing.py", line 57, in perpareDataset pklObjects['data'][datasetName] = createPklFiles(paths, mappings, datasetColumns, commentSymbol, valTransformations, padOneTokenSentence) File "/public/home/zcyu/ref/NLP/emnlp2017-bilstm-cnn-crf/util/preprocessing.py", line 318, in createPklFiles trainSentences = readCoNLL(datasetFiles[0], cols, commentSymbol, valTransformation) File "/public/home/zcyu/ref/NLP/emnlp2017-bilstm-cnn-crf/util/CoNLL.py", line 48, in readCoNLL val = splits[colIdx] IndexError: list index out of range

prometheusloong avatar May 06 '19 08:05 prometheusloong

my data have some special character. it caused the error.

prometheusloong avatar May 06 '19 13:05 prometheusloong

maybe your data is not BIO format?

tao2021 avatar Jul 31 '22 08:07 tao2021