DBpedia Member

Diffbot Technologies Corp.

Diffbot (https://www.diffbot.com/) is a Menlo-Park, California-based company whose mission is to “extract knowledge in an automated way from documents.” Diffbot Technologies Corp. started as a years-long private pilot program and launched the AI-powered Knowledge Graph in mid of 2018. A few months later they joint the DBpedia Association. Since then Diffbot Technologies Corp. supports the DBpedia Association and its goals.


Diffbot’s mission is to enable the age of intelligent systems by building the first comprehensive database of human knowledge. We envision a future where man is free from the cognitive shackles of data gathering; where we are all surrounded in our daily work and leisure by intelligent systems, infused with knowledge, that serve and empower mankind.

Research Areas:

  • Record Linking
  • Named Entity Recognition
  • Coreference Resolution
  • Entity Linking
  • Relation Extraction
  • Sentiment Analysis
  • Knowledge Inference
  • Knowledge Fusion
  • Computer Vision

Software Engineering Areas:

  • Web Data Extraction/API’s
  • Distributed Systems
  • Highly Scalable Systems
  • Machine Learning

Diffbot Natural Language API

Most of the world’s knowledge is encoded in natural language (e.g., news articles, books, emails, academic papers). It is estimated that 80 percent of business-relevant information originates in unstructured form, primarily text. However, the ambiguous nature of human communication makes it difficult for software engineers and data scientists to leverage this information in their applications.

After years of research, we are proud to announce the Diffbot Natural Language API (https://www.diffbot.com/products/natural-language/), a new product to help businesses convert their text documents into knowledge graphs. Knowledge graphs represent information about real-world entities (e.g., people, organizations, products, articles) via their relationships with other entities (e.g., founded by, educated at, was mentioned in). This is the same production-grade technology that we use to build the world’s largest knowledge graph from the web, and we are making it available to all.

Filipe Mesquita presentetd the Natural Lange API at the Knowledge Graphs in Action event on October 6, 2020.


Contact Person

Filipe Mesquita