# CS6320 Final (Fall 2022) — Data

来源：https://www.kaggle.com/competitions/cs6320final/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

**Login eLearning to get data**

The dataset consists of two json files: train.json and test.json. These files are different from the original release of the CoNNL-2003 since we have already processed and tokenized them for you. Hence, the documents are represented as a list of strings. The dataset is not split into separate training and development/validation sets. You will need to do this yourself as needed using train set.

The train file contain the following 4 fields (each is a nested list):

'text' - actual input tokens
'NER' - the entity tag (LOC/MISC/O/ORG/PER)
'POS' - the parts of speech tag (will be handy for feature engineering of the MEMM model)
'index' - index of the token in the dataset
The test data only has 'text', 'POS' and 'index' fields. You will need to submit your prediction of 'NER' tag to the Kaggle.