Contextual embeddings, such as ELMo and BERT [21], [49], assign each word a representation based on its context [44]. This research builds on an observation that the context for structured data can be encoded very differently from the traditional sentence and text-based context. This means that embeddings for the structured data can be constructed on different principles, and if properly optimized, they can be used to improve performance ML and AI-based tasks related to the structured data. Here we present several new types of tabular embeddings taking into consideration structure of columns, rows, and presence of metadata. We demonstrated that properly optimized embeddings in combination with ML and DL models show significant improvement on such important tasks as tabular column and tuple recognition.

Anecdotal evidence suggests that Web-search engines, together with the Knowledge Graphs and Bases, such as YAGO [46], DBPedia [13], Freebase [16], Google Knowledge Graph [52] provide rapid access to most structured information on the Web. However, taking a closer look reveals a so called "knowledge gap" [18] that is largely in the dark. For example, a person searching for a relevant job opening has to spend at least 3 hours per week for several months [2] just searching job postings on numerous online job-search engines and the employer websites. The reason why this seemingly simple task cannot be completed by typing in a few keyword queries into a search-engine and getting all relevant results in seconds instead of hours is because access to structured data on the Web is still rudimentary. While searching for a job we have many parameters in mind, not just the job title, but also, usually location, salary range, remote work option, given a recent shift to hybrid work places, and many others. Ideally, we would like to write a SQL-style query, selecting all job postings satisfying our requirements, but it is currently impossible, because job postings (and all other) Web tables are structured in many different ways and scattered all over the Web. There is neither a Web-scale generalizable algorithm nor a system to locate and normalize all relevant tables in a category of interest from millions of sources.Here we describe and evaluate on a corpus having hundreds of millions of Web tables [39], a new scalable iterative training data generation algorithm, producing high quality training data required to train Deep- and Machine-learning models, capable of generalizing to Web scale. The models, trained on such en-riched training data efficiently deal with Web scale heterogeneity compared to poor generalization performance of models, trained without enrichment [20], [25], [38]. Such models are instrumental in bridging the knowledge gap for structured data on the Web.