AlvisNLP

corpus processing engine

I2B2Reader

Synopsis

I2B2Reader reads files in the format of the I2B2 challenge.

Description

I2B2Reader reads documents in I2B2 challenge including the text of documents, tokenization as annotations, concepts as annotations, assertions as annotation features and relations as tuples.

Snippet

<i2b2reader class="I2B2Reader">
    <textDir></textDir>
</i2b2reader>

Mandatory parameters

textDir

Mandatory

Path to the directory containing I2B2 text files.

Optional parameters

assertionsDir

Optional

Path to the directory where assertion files can be found.

conceptsDir

Optional

Path to the directory that contains concept annotations.

constantAnnotationFeatures

Optional
Type: Mapping

Constant features to add to each annotation created by this module.

constantDocumentFeatures

Optional
Type: Mapping

Constant features to add to each document created by this module.

constantRelationFeatures

Optional
Type: Mapping

Constant features to add to each relation created by this module.

constantSectionFeatures

Optional
Type: Mapping

Constant features to add to each section created by this module.

constantTupleFeatures

Optional
Type: Mapping

Constant features to add to each tuple created by this module.

relationsDir

Optional

Path to the directory where relation files can be found.

assertionFeature

Default value: `assertion`
Type: String

conceptTypeFeature

Default value: `type`
Type: String

Feature where to store the concept type.

conceptsLayer

Default value: `concepts`
Type: String

Name of the layer where to store concepts annotations.

leftRole

Default value: `left`
Type: String

Name of the left argument of relations.

linenoFeature

Default value: `lineno`
Type: String

Name of the feature where to store the line number.

linesLayer

Default value: `lines`
Type: String

Name of the layer where to store lines.

rightRole

Default value: `right`
Type: String

section

Default value: `text`
Type: String

Name of the unique section of each document.

tokenNumberFeature

Default value: `tokenno`
Type: String

Feature where to store the token index.

tokensLayer

Default value: `tokens`
Type: String

Name of the layer where to store tokens.

Deprecated parameters

conceptsLayerName

Deprecated
Type: String

Deprecated alias for conceptsLayer .

linesLayerName

Deprecated
Type: String

Deprecated alias for linesLayer .

sectionName

Deprecated
Type: String

Deprecated alias for section .

tokensLayerName

Deprecated
Type: String

Deprecated alias for tokensLayer .