Abstract: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.

Abstract: A method may include: forming a base layer on a substrate; forming a waveguide assembly on the base layer, where the waveguide assembly is surrounded by a cladding layer; forming a trench opening through the cladding layer and the base layer; forming an undercut void by etching the substrate through the trench opening, where the undercut void extends under the waveguide assembly and the base layer; and filling the trench opening with a filler to seal off the undercut void. Other embodiments are described and claimed.