Automated Essay Scoring

Automated Essay Scoring related modeling class

class pororo.tasks.automated_essay_scoring.PororoAesFactory(task: str, lang: str, model: Optional[str])

Bases: pororo.tasks.utils.base.PororoFactoryBase

Regression based Automated Essay Scoring

English (roberta.base.en.aes)

• dataset: The Hewlett Foundation: Automated Essay Scoring

• metric: Spearman (80.25)

• ref: https://www.kaggle.com/c/asap-aes/data

Examples

>>> aes = Pororo(task="aes", lang="en")
>>> aes("To me, leadership does not necessarily mean accumulating as many titles as possible...")
23.56

static get_available_langs()

static get_available_models()

load(device)

Load user-selected task-specific model

Parameters

device (str) – device information

Returns

User-selected task-specific model

Return type

object

class pororo.tasks.automated_essay_scoring.PororoBertAes(model, config)

Bases: pororo.tasks.utils.base.PororoSimpleBase

predict(sent: str, **kwargs)

Conduct Automated Essay Scoring

Parameters

sent – (str) sentence to be encoded

Returns

predicted essay score

Return type

float