bionlp2017

KO | EN

gitlite — search

#hacktoberfest #ai #typescript #go #golang #android #deep-learning #linux #java #windows #kubernetes #pytorch #ios #openai

(★ 13)

Extract annotated misspellings from MIMIC-III.

bionlp2017 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

This repository contains source code for the paper 'Unsupervised Context-Sensitive Spelling Correction for Clinical Free-Text with Word and Character N-Gram Embeddings', which will be presented at the [BioNLP Workshop at ACL 2017](http://www.aclweb.org/aclwiki/index.php?title=BioNLP_Workshop). The source code offered here contains a script to extract our manually annotated MIMIC-III data.

# Requirements

* Python 2.7

To extract our manually annotated MIMIC-III test data, you should have access to the [MIMIC-III v1.3 database](https://mimic.physionet.org). This should be v1.3 of the database, since the extraction script doesn't work anymore with later versions.

# Extracting the annotated test data

To extract the annotated test data, git clone this repository and run

```python2.7 extract_test.py [path to NOTEEVENTS.csv file from the MIMIC-III v1.3 database]```

from inside the directory. This script preprocesses the **NOTEEVENTS.csv** data and stores the preprocessed data in the file **mimic_preprocessed.txt**. It then extracts the annotated 
test data, which is stored to the file **testcorpus.json** in four lists: correct replacements, misspellings, misspelling contexts, and line indices.

bionlp2017

bionlp2017 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

bionlp2017

bionlp2017 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README