> ## Documentation Index
> Fetch the complete documentation index at: https://docs.abbyy.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Process unstructured documents in Advanced Designer
> Use Advanced Designer NLP activities — Segmentation, NER, Address Parsing, Deep Learning for NLP — to extract data from contracts, emails, and freeform text.
Skills for processing [unstructured documents](/vantage/documentation/advanced-designer/use-cases/extracting-from-docs#unstructured-documents) can only be built in Advanced Designer; the cloud-based [Skill Designer](/vantage/documentation/skill-designer/skill-designer) does not support these scenarios. They use four core NLP activities to identify entities, segment text, and extract fields from freeform content like contracts, letters, and emails:
* [Segmentation activity](/vantage/documentation/advanced-designer/activities/segmentation/segmentation-activity)
* [Deep Learning for NLP activity](/vantage/documentation/advanced-designer/activities/deep-learning-nlp)
* [Named Entities (NER) activity](/vantage/documentation/advanced-designer/activities/ner)
* [Address Parsing activity](/vantage/documentation/advanced-designer/activities/address-parsing)
Each of these activities supports a limited set of languages. See the activity's reference page for the language list.
## Pick a scenario
| Scenario | When to use | Key activities |
| :----------------------------------------------- | :---------------------------------------------------------------- | :-------------------------------------- |
| Pre-trained named entities (whole document) | Entities can appear anywhere — minimal configuration needed | NER (+ Address Parsing) |
| Pre-trained named entities (specific paragraphs) | The entity always sits in a known paragraph | Segmentation + NER (or Address Parsing) |
| Custom named entities (Deep Learning for NLP) | Pre-trained can't disambiguate, or your entity type isn't covered | Segmentation + Deep Learning for NLP |
Each scenario below shares a common pattern; only the activities you add to the processing flow differ.
## Common workflow
Open Advanced Designer and click **Create Document Skill** on the start page.
On the **Documents** tab, upload the documents you'll use to set up the skill.
On the **Fields** tab, create and configure the fields the skill will extract. Label documents in the **Reference** section.
On the **Activities** tab, add the activities for your scenario (described below). Open each activity in the **Activity Editor** to configure and train it.
Click **Test Skill Using Selected Documents** to evaluate [results](/vantage/documentation/advanced-designer/document-skills/results). When the results are good enough, [publish the skill](/vantage/documentation/advanced-designer/document-skills/publish).
## Pre-trained named entities (whole document)
Use this scenario when the entities you need can appear anywhere in the document — for example, company names and addresses in a letter. Add a [Named Entities (NER) activity](/vantage/documentation/advanced-designer/activities/ner) and map each named entity to a field. If you also need to break an address into components (street, city, state, country, postal code), add an [Address Parsing activity](/vantage/documentation/advanced-designer/activities/address-parsing) and map the components to fields.
## Pre-trained named entities (specific paragraphs)
Use this scenario when the entity always sits in the same paragraph — for example, a purchase amount in the price clause of a sales agreement. First isolate the paragraph with a [Segmentation activity](/vantage/documentation/advanced-designer/activities/segmentation/segmentation-activity), then run a [Named Entities (NER)](/vantage/documentation/advanced-designer/activities/ner) or [Address Parsing](/vantage/documentation/advanced-designer/activities/address-parsing) activity on the segmented field.
You can also isolate the paragraph with a [Fast Learning](/vantage/documentation/advanced-designer/activities/fast-learning) or [NLP Extraction Rules](/vantage/documentation/advanced-designer/activities/nlp-extraction-rules/extraction-rules) activity instead of Segmentation, then run NER or Address Parsing on the result.
Pre-trained activities are easy to configure and need no training, but a neural network trained on your documents may extract more accurately. If you have a large document set, also try the [custom named entities](#custom-named-entities-deep-learning-for-nlp) scenario below and pick whichever performs better.
## Custom named entities (Deep Learning for NLP)
Use this scenario when pre-trained activities can't disambiguate the entities you need — for example, extracting only one organization's name from a paragraph that lists both parties to an agreement, or extracting an entity type that NER doesn't cover (such as an email address). Pair a [Segmentation activity](/vantage/documentation/advanced-designer/activities/segmentation/segmentation-activity) with a [Deep Learning for NLP activity](/vantage/documentation/advanced-designer/activities/deep-learning-nlp): Segmentation isolates the paragraph and Deep Learning extracts the targeted fields.
Training a Deep Learning for NLP activity requires at least 50 documents (150 recommended). For best results, also try the pre-trained [Named Entities (NER)](/vantage/documentation/advanced-designer/activities/ner) activity and pick whichever extracts more accurately on your documents.
## Related activities
Extract pre-trained entities like names, organizations, and dates from freeform text.
Split addresses into street, city, state, country, and postal code.
Isolate the paragraph that contains the data you want to extract.
Train a neural network to extract custom or hard-to-disambiguate entities.