Natural Language Processing and Real Estate Documents

Each real estate document you see is unique in its own way. Though the forms are often similar, the change of one small word can make a big impact on the overall meaning of a real estate document. Historically, these documents have been reviewed by abstractors, attorneys, and landmen to determine their relevance to a particular tract of land and/or their impact on the ownership of that tract of land. Parse began with our team dreaming of a more efficient way to run title. A method that went beyond excel spreadsheets and hand-drawn flowcharts and instead utilized the latest in technology, such as natural language processing, to speed up the title research process.

According to Wikipedia, Natural language processing (NLP) is a subfield of linguistics, computer science, and artificial intelligence concerned with the interactions between computers and human language, in particular how to program computers to process and analyze large amounts of natural language data. The result is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them. The technology can then accurately extract information and insights contained in the documents as well as categorize and organize the documents themselves.

We recently developed a custom named entity recognizer that labels the Grantor, Grantee, and several other import details about a document. Named entity recognition is a natural language processing process that automatically identifies named entities within a text and classifies them into predefined categories. Categories can be things such as names of people, locations, dates, quantities, monetary values, percentages, and more. Using our custom named entity recognizer, we searched thru the full text of documents and highlighted the text found a specific color based upon what it believes the text to be.

Color Key

Red = Grantor

Yellow = Grantee

Green = Section

Blue = Block

Utilizing this named entity recognizer and highlight method, we were able to gain a 20% speed efficiency in annotating real estate documents. If you are interested in having a custom named entity recognizer developed for you, contact us today.