---
id: "sato"
category: "detector"
url: "http://registry.apicrafter.io/tool/sato"
---

# Sato (`sato`)

Sato is a research model from Megagon Labs, published at VLDB 2020, that predicts the semantic type of every column of a table. It extends the Sherlock column network with a topic model of the whole table and adds a conditional random field that predicts the types of all columns together, so the other columns of a table help to choose the type of each one. The published model predicts the same 78 semantic types as Sherlock, written in camelCase, such as birthDate or fileSize. The registry maps these types through mappings.sherlock, so this list is the same as the one of the sherlock tool. The code and the pretrained model are released under the Apache 2.0 license.

Website: <https://github.com/megagonlabs/sato>

## Supported datatypes (30)

- `address`
- `age`
- `birthday`
- `birthplace`
- `brand`
- `category`
- `city`
- `comment`
- `continent`
- `country`
- `currency`
- `dc_creator`
- `dc_publisher`
- `description`
- `duration`
- `elevation`
- `filesize`
- `gender`
- `genre`
- `industry`
- `isbn`
- `language`
- `name`
- `nationality`
- `orgname`
- `person_fullname`
- `religion`
- `species`
- `weight`
- `year`