Sap Se

General Electric Company

Tarun Sharma

Jayananda Appanna Kotri

Yashwanth Dasari

Sharad Kejriwal

Abinaya S

Jeffrey Douglas Rambo

Kudum Shinde

John David Bibler

Paul Alexander Intemann

Ajit Kumar Verma

Ravinder Hamilpur

Sridhara Rao Venkata Mittapalli

In an example embodiment, factual question generation from freeform content is achieved through semantic role labeling and recurrent neural networks (RNNs). Specifically, semantic role labeling is used to identify an answer phrase so that it can be replaced with an appropriate question word. RNNs are then used to extract triples (Subject-Object-Predicate) from the sentence, and each of these triples can be used as an answer phrase/word. An RNN is then fed with training data to generate the questions more efficiently.

Automated question generation using semantics and deep learning

A stator temperature control system for a gas turbine engine is provided. The stator temperature control system includes a casing circumferentially surrounding a stator assembly, the casing having a top portion and a bottom portion; an air source having an inlet and an outlet; and a supply line in fluid communication with the outlet of the air source and the bottom portion of the casing, wherein the bottom portion of the casing receives a flow of air from the air source via the supply line to increase a temperature of the bottom portion of the casing.

Stator temperature control system for a gas turbine engine

An ejector is presented. The ejector includes a primary fluid inlet to receive a primary fluid. The ejector further includes a secondary fluid inlet to receive a secondary fluid. Furthermore, the ejector includes a nozzle fluidly coupled to the primary fluid inlet and the secondary fluid inlet. The nozzle includes a secondary pilot inlet to receive at least a portion of the secondary fluid from the secondary fluid inlet, and a nozzle outlet including a plurality of primary openings for discharging the primary fluid and a secondary opening for discharging the secondary fluid. A turbo-machine having the ejector is also presented.

Ejector and a turbo-machine having an ejector

A recurrent neural network (RNN) is trained to identify split positions in long content, wherein each split position is a position at which the theme of the long content changes. Each sentence in the long content is converted to a vector that corresponds to the meaning of the sentence. The sentence vectors are used as inputs to the RNN. The high-probability split points determined by the RNN may be combined with contextual cues to determine the actual split point to use. The split points are used to generate thematic segments of the long content. The multiple thematic segments may be presented to a user along with a topic label for each thematic segment. Each topic label may be generated based on the words contained in the corresponding thematic segment.

Thematic segmentation of long content using deep learning and contextual cues

Growing community of inventors

Bengaluru, India

Tarun Sharma