BERT Question-Answering at Google

BERT Question Answering

BERT Question-Answering A Patent granted to Google on May 11, 2021, involves performing Natural language processing (“NLP”) tasks such as question answering. It relies on a language model pre-trained using world knowledge. Recent advances in language-model pre-training have resulted in language models such as Bidirectional Encoder Representations from Transformers (“BERT”). This has been discussed within … Read more

Extracting Entities with Automated Data Wrappers

automated data wrapper

Extracting Entity Information From Web Pages with Data Wrappers One area of SEO worth exploring involves Semantic SEO, which I wrote about in What is Semantic SEO?. One of the important patents I wrote about involved Entity Extraction for knowledge graphs and which I covered in more detail in the post Answering Questions Using Knowledge … Read more

Adjusting Featured Snippet Answers by Context

context scoring adjustments for featured snippet answers

How Are Featured Snippet Answers Decided Upon? I recently wrote about Featured Snippet Answer Scores Ranking Signals. I described how Google was likely using query-dependent and query-independent ranking signals to create answer scores for queries looking like they wanted answers. One of the inventors of that patent from that post was Steven Baker. I looked … Read more