Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Sample of challenging sequences.

More »

Table 1 Expand

Fig 1.

Complete process of dataset preparation.

More »

Fig 1 Expand

Table 2.

Article statistics.

More »

Table 2 Expand

Table 3.

Sentence structure conversion by separating punctuation.

More »

Table 3 Expand

Table 4.

Sentence after tokenization and set up sentence indicator.

More »

Table 4 Expand

Table 5.

Tagging scheme.

More »

Table 5 Expand

Table 6.

Sample of NER dataset.

More »

Table 6 Expand

Fig 2.

Named entity vs. non-named entity ratio.

More »

Fig 2 Expand

Fig 3.

Ratio of named entities.

More »

Fig 3 Expand

Fig 4.

Frequency of named entities.

More »

Fig 4 Expand

Table 7.

Dataset statistics.

More »

Table 7 Expand

Table 8.

Train and test data distribution.

More »

Table 8 Expand

Fig 5.

Workflow diagram.

More »

Fig 5 Expand

Fig 6.

Type-1 model architecture.

More »

Fig 6 Expand

Fig 7.

Type-2 model architecture.

More »

Fig 7 Expand

Table 9.

Statistics of matched words in each word embedding.

More »

Table 9 Expand

Table 10.

Changing nature of the root words with the addition of suffixes and prefixes.

More »

Table 10 Expand

Fig 8.

Character level feature extraction with CNN.

More »

Fig 8 Expand

Table 11.

Example sequence for prediction.

More »

Table 11 Expand

Table 12.

Sample evaluation.

More »

Table 12 Expand

Table 13.

Exact and partial precision scores.

More »

Table 13 Expand

Table 14.

Exact and partial recall scores.

More »

Table 14 Expand

Table 15.

Exact and partial F1 scores.

More »

Table 15 Expand

Table 16.

Micro F1 scores.

More »

Table 16 Expand

Table 17.

Comparison of hybrid and non-hybrid models’ F1 scores.

More »

Table 17 Expand

Table 18.

Comparison of results between four word embeddings.

More »

Table 18 Expand

Table 19.

Comparison of results on integrating CNN layer.

More »

Table 19 Expand

Table 20.

Comparison of results on integrating CRF layer.

More »

Table 20 Expand

Table 21.

Comparison of results between BGRU and BLSTM based models.

More »

Table 21 Expand

Fig 9.

Dropout effect.

More »

Fig 9 Expand

Table 22.

Count of correctly predicted NE classes.

More »

Table 22 Expand

Table 23.

Test sample-1.

More »

Table 23 Expand

Table 24.

Test sample-2.

More »

Table 24 Expand

Fig 10.

Comparison of results between four models.

More »

Fig 10 Expand

Table 25.

Macro and micro F1 scores of the best model.

More »

Table 25 Expand

Fig 11.

The graphical representation of confusion matrix of the best performing model.

More »

Fig 11 Expand

Table 26.

Results on different challenges for BGRU+CNN+CRF (word2vec(cbow)).

More »

Table 26 Expand

Table 27.

Results of other existing model along with our proposed model for Bengali NER.

More »

Table 27 Expand

Table 28.

Dataset details of other existing models along with our proposed model for Bengali NER.

More »

Table 28 Expand