Segmentation tool

The Segmentation tool splits a block's text into sentence-level segments. Segmentation determines the unit of translation and of content-memory matching, so consistent segmentation is important for leverage and review. By default the tool segments source text using built-in SRX-style rules that handle common sentence boundaries and abbreviations; rules can also be loaded from an SRX file.

The number of segments produced is recorded on each block. Already-segmented text is left alone unless re-segmentation is requested. Target text can be segmented independently, with its own rules file.

IDsegmentation

SourceBuilt-in

CategoryText processing

Cardinalitymonolingual

Tagstext-processing

Parameters

Parameter	Type	Default	Description
`engine`	string	srx	Hvilken segmenterer som skal brukes; standardvalget krever ingen konfigurasjon
`layer`	string		Navn på segmenteringsoverleggslag; tomt bruker motorens naturlige lag
`overwriteSegmentation`	boolean	false	Segmenter allerede segmenterte blokker på nytt og erstatt tidligere segmentering
`provider`	string		AI-leverandør-ID (anthropic
`rulesPath`	string		Bane til en egendefinert SRX 2.0-regelfil (overstyrer det innebygde regelsettet)
`model`	string		Modellnavn
`segmentSource`	boolean	true	Segmenter kildeteksten
`treatIsolatedCodesAsWhitespace`	boolean	false	Behandle isolerte innebygde koder som mellomrom under segmentering
`credential`	string		Navn på lagret legitimasjon
`segmentTarget`	boolean	false	Segmenter eksisterende måltekst
`trimLeadingWhitespace`	boolean	true	Ekskluder innledende mellomrom fra hvert segmentspenn
`instruction`	string		Valgfri veiledning for hvordan du deler opp
`trimTrailingWhitespace`	boolean	true	Utelat etterfølgende mellomrom fra hvert segmentspenn
`maxChunkRunes`	integer		Myk øvre grense for del-størrelse i tegn (0 = modellstandard)
`renumberCodes`	boolean	false	Omnummerer innebygde kode-ID-er ved materialisering av segmenter til et tospråklig format

Configure it live

Configuration

Loading form…

Examples

Segment source text with default rules

Split source into sentences using the built-in rules.

segmentSource: true

Re-segment with a custom SRX file

Replace existing segmentation using project-specific rules.

segmentSource: true
overwriteSegmentation: true
sourceSrxPath: ./rules/segmentation.srx

Processing notes

Operates on translatable blocks only; non-translatable blocks pass through unchanged.
The resulting segment count is written to a block property.

Limitations

The built-in rule set targets common Latin-script sentence boundaries; non-Latin scripts may need a custom SRX file.

← Back to the Tool Reference