├── .gitignore ├── AmazonTextractExample ├── SampleInvoice_Adobe Scan 24_10_2020_1 (1).jpg └── SampleInvoice_Adobe Scan 24_10_2020_2 (1).jpg ├── Final_Report ├── Dissertation_COMPSCI791_Spencer_Han.pdf ├── SpencerHan_Poster.jpg └── SpencerHan_Poster.pdf ├── Preprocessing ├── Initial_Notebook.ipynb ├── checking_confidence.py ├── handLabelMatching.py ├── labelChecking.py ├── spacyLabeling.py ├── spacyTokenTest.py ├── test.py └── textractProcessing.py ├── Presentation └── A Deep Learning Based Approach for Name Entity.pptx ├── README.md ├── nlp_processing ├── BiLSTM-CNN-CRF.ipynb ├── RetrainBetterData.ipynb ├── ReuseModel.ipynb ├── biLSTM-CRF.ipynb ├── confidence.ipynb ├── elmo.ipynb ├── elmoModel ├── elmo_train.py ├── model.png ├── preprocessing.py └── temp.py └── spacy_text ├── deepLearn_Preprocessing.py ├── ner ├── cfg ├── model └── moves ├── parser ├── cfg ├── model └── moves ├── tagger ├── cfg ├── model └── tag_map ├── tokenizer └── vocab ├── key2row ├── lookups.bin └── lookups_extra.bin /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/.gitignore -------------------------------------------------------------------------------- /AmazonTextractExample/SampleInvoice_Adobe Scan 24_10_2020_1 (1).jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/AmazonTextractExample/SampleInvoice_Adobe Scan 24_10_2020_1 (1).jpg -------------------------------------------------------------------------------- /AmazonTextractExample/SampleInvoice_Adobe Scan 24_10_2020_2 (1).jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/AmazonTextractExample/SampleInvoice_Adobe Scan 24_10_2020_2 (1).jpg -------------------------------------------------------------------------------- /Final_Report/Dissertation_COMPSCI791_Spencer_Han.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Final_Report/Dissertation_COMPSCI791_Spencer_Han.pdf -------------------------------------------------------------------------------- /Final_Report/SpencerHan_Poster.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Final_Report/SpencerHan_Poster.jpg -------------------------------------------------------------------------------- /Final_Report/SpencerHan_Poster.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Final_Report/SpencerHan_Poster.pdf -------------------------------------------------------------------------------- /Preprocessing/Initial_Notebook.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/Initial_Notebook.ipynb -------------------------------------------------------------------------------- /Preprocessing/checking_confidence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/checking_confidence.py -------------------------------------------------------------------------------- /Preprocessing/handLabelMatching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/handLabelMatching.py -------------------------------------------------------------------------------- /Preprocessing/labelChecking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/labelChecking.py -------------------------------------------------------------------------------- /Preprocessing/spacyLabeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/spacyLabeling.py -------------------------------------------------------------------------------- /Preprocessing/spacyTokenTest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/spacyTokenTest.py -------------------------------------------------------------------------------- /Preprocessing/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/test.py -------------------------------------------------------------------------------- /Preprocessing/textractProcessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Preprocessing/textractProcessing.py -------------------------------------------------------------------------------- /Presentation/A Deep Learning Based Approach for Name Entity.pptx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/Presentation/A Deep Learning Based Approach for Name Entity.pptx -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/README.md -------------------------------------------------------------------------------- /nlp_processing/BiLSTM-CNN-CRF.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/BiLSTM-CNN-CRF.ipynb -------------------------------------------------------------------------------- /nlp_processing/RetrainBetterData.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/RetrainBetterData.ipynb -------------------------------------------------------------------------------- /nlp_processing/ReuseModel.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/ReuseModel.ipynb -------------------------------------------------------------------------------- /nlp_processing/biLSTM-CRF.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/biLSTM-CRF.ipynb -------------------------------------------------------------------------------- /nlp_processing/confidence.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/confidence.ipynb -------------------------------------------------------------------------------- /nlp_processing/elmo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/elmo.ipynb -------------------------------------------------------------------------------- /nlp_processing/elmoModel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/elmoModel -------------------------------------------------------------------------------- /nlp_processing/elmo_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/elmo_train.py -------------------------------------------------------------------------------- /nlp_processing/model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/model.png -------------------------------------------------------------------------------- /nlp_processing/preprocessing.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /nlp_processing/temp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/nlp_processing/temp.py -------------------------------------------------------------------------------- /spacy_text/deepLearn_Preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/deepLearn_Preprocessing.py -------------------------------------------------------------------------------- /spacy_text/ner/cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/ner/cfg -------------------------------------------------------------------------------- /spacy_text/ner/model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/ner/model -------------------------------------------------------------------------------- /spacy_text/ner/moves: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/ner/moves -------------------------------------------------------------------------------- /spacy_text/parser/cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/parser/cfg -------------------------------------------------------------------------------- /spacy_text/parser/model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/parser/model -------------------------------------------------------------------------------- /spacy_text/parser/moves: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/parser/moves -------------------------------------------------------------------------------- /spacy_text/tagger/cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/tagger/cfg -------------------------------------------------------------------------------- /spacy_text/tagger/model: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/tagger/model -------------------------------------------------------------------------------- /spacy_text/tagger/tag_map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/tagger/tag_map -------------------------------------------------------------------------------- /spacy_text/tokenizer: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/tokenizer -------------------------------------------------------------------------------- /spacy_text/vocab/key2row: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/vocab/key2row -------------------------------------------------------------------------------- /spacy_text/vocab/lookups.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/vocab/lookups.bin -------------------------------------------------------------------------------- /spacy_text/vocab/lookups_extra.bin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spencerhan/InvoiceNamedEntityRecognition/HEAD/spacy_text/vocab/lookups_extra.bin --------------------------------------------------------------------------------