Primer Selected for Intelligent Applications Top 40 Award

10

Synthetic Text Detection

Classify text as likely to have been written by a human or a machine.

Documentation

Example

Bitcoin will hit $100,000 in the next year. It will be one of the most difficult investments you have ever seen. In a couple of years we will be able to pay for our education and our schooling and we will get a chance to retire as well…

Output[RESULTS]

class:

synthetic text

confidence:

0.81

Example

Output[RESULTS]

class:

synthetic text

confidence:

0.81

Request A Demo Request A Demo _

Back

Try Engines for Free

01

Get Started for Free

02

Test Our Engines

Test our API on your data.

03

Integrate at Scale

Once you've seen the power of engines, build your own scalable engine pipelines.

Get Started For Free Get Started For Free _

Named Entity Recognition

Identify people, locations, and organizations within a body of text.

Explore

Coreference Resolution

Identify who the words “he,” “she,” and “they” are referring to.

Explore

Relation Extraction

Identify relationships between entities.

Explore

Classifiers

Categorize any kind of text.

Explore

Sentiment Analysis

Classify text as positive, negative, or neutral, returned as a classifier.

Explore

Topic Modeling

Identify the topic that the text is talking about without the need for training or ontology.

Explore

Summarization

Summarize a document to meet your needs and identify the key information.

Explore

Key Phrase Extraction

Automatically identify and extract the key information within a document.

Explore

Explainability

See what parts of the text the models are using for your predictions.

Explore