Refer Answer to Table Column

In Row Labeling projects, you can accelerate the annotation process by pre-filling answers based on the data present in your uploaded file (CSV, Excel, etc.).

You can achieve this by configuring ‘Refer answer to table column’ for each question and mapping it to a specific column header in your dataset. Once set, the system automatically creates pre-labeled answers based on the values in that column.

To configure this, navigate to Step 3 of the Project Creation Wizard. While adding or editing questions, open the Advanced Settings section, then choose the column header you want the question to refer to.

After completing the setup, open the project. You will see that the question has been pre-filled with answers parsed directly from the referenced column.

Configuring for nested questions

Datasaur also supports Refer answer to table column for nested questions, which are child questions under a Grouped attributes question. The parent Grouped attributes question cannot refer to a column directly, so the reference must be set on its child question(s) instead.

You can configure this using the same steps as regular flat-structured questions, as described in the previous section.

The parsing behavior may differ depending on whether the parent or child questions allow multiple answers, since nested questions may need to split values into multiple groups, multiple items, or both. The next section explains how this parsing works.

Data parsing and separators

To maximize the utility of pre-labeling, specific characters in your tabular data are parsed to determine how answers should be split and grouped.

Multiple answers separator (;)

If a question is configured to allow multiple answers, you can use a semicolon ; to split the data in a single cell into separate answers.

If the question does not allow multiple answers, the semicolon will be ignored, and the entire cell value will be treated as a single pre-labeled answer.

Example

• Question: "Fruit" (Type: Text)

• Referred column cell data: Apple;Banana;Pear

• Result: The system creates three pre-labeled answers: Apple, Banana, and Pear.

86B

Datasaur sample - Multiple answers separator.csv

Open

Answer group separator (|||)

This separator is exclusive to nested questions in Grouped attributes question.

The ||| separator controls how values from a single cell are split into multiple answer groups. Because it is used to create groups, it only takes effect when the parent Grouped Attributes question is configured to allow multiple answers.

To create multiple answer groups from a single cell, insert the triple pipe ||| between groups. This separator can also be used alongside the multiple answers separator (;) within each group.

Requirements for group parsing

1. The Grouped attributes (parent) question must be configured to allow multiple answers.

   • Otherwise, the system ignores all ||| separators and treats the cell as a single group.

2. The nested question (child) must refer to the column that contains the separators.

   • The child question may optionally allow multiple answers, enabling the parsing of the semicolon (;) within each group.

The following view outlines how the system parses data depending on how your nested questions are configured:

Case 1

Parent question: Allow multiple answers? ❌

Nested question: Allow multiple answers? ✅

Column data: A1;A2|||B1;B2

The resulting pre-labeled answer: Group 1: A1, A2|||B1, B2

Case 2

Parent question: Allow multiple answers? ✅

Nested question: Allow multiple answers? ❌

Column data: A1;A2|||B1;B2

The resulting pre-labeled answer: Group 1: A1;A2 Group 2: B1;B2

Case 3

Parent question: Allow multiple answers? ✅

Nested question: Allow multiple answers? ✅

Column data: A1;A2|||B1;B2

The resulting pre-labeled answer: Group 1: A1, A2 Group 2: B1, B2

Test data example

1. Upload the file below during project setup:

197B

Datasaur sample - Refer answer to column.csv

Open

1. In the Preview step of the Project Creation Wizard, make sure to enable Convert first row as header.

1. In the Labelers’ tasks step, configure the questions as follows:

   • Question 1: Colors (Type: Text)

     • Enable Allow multiple answers

     • Set Refer to column: colors_available

       
   • Question 2: Vehicle parts (Type: Grouped attributes)

     • Enable Allow multiple answers

       • Question 2.1: Part name (Type: Text)

         • Enable Allow multiple answers

         • Set Refer to column: part_names_and_tags

       

Result

After the project is created, labelers will see the questions automatically pre-filled according to the values in the CSV file.