Microsoft Technology Licensing, Llc Patent Portfolio Statistics

Publication number: US20220107864A1
Application number: 17/553,785

Abstract:
Embodiments of the present disclosure include an error recovery method comprising detecting a computing error, restarting a first artificial intelligence processor of a plurality of artificial intelligence processors processing a data set, and loading a model in the artificial intelligence processor, wherein the model corresponds to a same model processed by the plurality of artificial intelligence processors during a previous processing iteration by the plurality of artificial intelligence processors on data from the data set.

Publication date: 2022-04-07
Applicant: Microsoft Technology Licensing, Llc
Inventors: Bharadwaj Pudipeddi

---

Publication number: US20220108078A1
Application number: 17/552,742

Abstract:
A system for extracting a key phrase from a document includes a neural key phrase extraction model (“BLING-KPE”) having a first layer to extract a word sequence from the document, a second layer to represent each word in the word sequence by ELMo embedding, position embedding, and visual features, and a third layer to concatenate the ELMo embedding, the position embedding, and the visual features to produce hybrid word embeddings. A convolutional transformer models the hybrid word embeddings to n-gram embeddings, and a feedforward layer converts the n-gram embeddings into a probability distribution over a set of n-grams and calculates a key phrase score of each n-gram. The neural key phrase extraction model is trained on annotated data based on a labeled loss function to compute cross entropy loss of the key phrase score of each n-gram as compared with a label from the annotated dataset.

Publication date: 2022-04-07
Applicant: Microsoft Technology Licensing, Llc
Inventors: Chuan Hu

---

Publication number: US20220137942A1
Application number: 17/550,452

Abstract:
A function is compiled against a first application binary interface (ABI) and a second ABI of a native first instruction set architecture (ISA). The second ABI defines context data not exceeding a size expected by a third ABI of a foreign second ISA, and uses a subset of registers of the first ISA that are mapped to registers of the second ISA. Use of the subset of registers by the second ABI results in some functions being foldable when compiled using both the first and second ABIs. First and second compiled versions of the function are identified as foldable, or not, based on whether the compiled versions match. Both the first and second compiled versions are emitted into a binary file when they are not foldable, and only one of the first or second compiled versions is emitted into the binary file when they are foldable.

Publication date: 2022-05-05
Applicant: Microsoft Technology Licensing, Llc
Inventors: Clarence Dang Siu Yeen

---