Abstract: A computer-implemented method for generating an abstract meaning representation (“AMR”) of a sentence, comprising receiving, by a computing device, an input sentence and parsing the input sentence into one or more syntactic and/or semantic graphs. An input graph including a node set and an edge set is formed from the one or more syntactic and/or semantic graphs. Node representations are generated by natural language processing. The input graph is provided to a first neural network to provide an output graph having learned node representations aligned with the node representations in the input graph. The method further includes predicting via a second neural network, node label and predicting, via a third neural network, edge labels in the output graph. The AMR is generated based on the predicted node labels and predicted edge labels. A system and a non-transitory computer readable storage medium are also disclosed.

Abstract: Disclosed is a planetary gear transmission box, comprising a housing portion, a first planetary gear transmission stage, and a second planetary gear transmission stage, wherein the first planetary gear transmission stage comprises a first sun gear (3), a first planetary carrier (5), and a first ring gear; the second planetary gear transmission stage comprises a second sun gear, a second planetary carrier (7), and a second ring gear (6); the first sun gear (3) is connected to an external input element; the first planetary carrier (5) is connected to the second sun gear; the second planetary carrier (7) is connected to an output element; the transmission ratio of the gear transmission box is greater than 25; and the second planetary carrier (7) is directly supported on the housing portion. The locked rotor torque of the gear box is increased, such that the output rotational speed is reduced, and thus a bearing member at the output end can be omitted.

Abstract: The present utility model relates to a motor. The motor includes a stator assembly and a rotor assembly, wherein the stator assembly includes a housing and a magnet, the rotor assembly includes a rotor, and the rotor, the magnet and the housing are arranged sequentially from inside to outside. Seen from an axial direction, an outer contour of the housing does not exceed the circumference of a first circle in a radial direction, and the outer contour of the housing coincides with the first circle at a portion thereof corresponding to a magnetic pole of the magnet, and the outer contour of the housing other than the portion corresponding to the magnetic pole of the magnet is recessed inward from the first circle in the radial direction, and the outer contour of the housing in a recessed portion is asymmetrical. Seen from the axial direction, the magnet is disposed between a second circle and a third circle.

Abstract: A rotor assembly (100), comprising a rotor (101) and a rotor winding (102). The rotor (101) is provided with a plurality of teeth; tooth slots are provided between adjacent teeth; the rotor (101) can be connected to a rotor shaft to output power; the rotor winding (102) is composed of coils wound on the rotor (101); the rotor winding (102) comprises a portion extending in an axial direction parallel to the rotor assembly (100) and a portion extending in a plane perpendicular to the axial direction; the portion extending in the plane perpendicular to the axial direction comprises a plurality of sections; in the axial direction, the plurality of sections are in one-to-one correspondence to corresponding sides of two or more polygons, respectively.

Abstract: A computer-implemented method for generating an abstract meaning representation (“AMR”) of a sentence, comprising receiving, by a computing device, an input sentence and parsing the input sentence into one or more syntactic and/or semantic graphs. An input graph including a node set and an edge set is formed from the one or more syntactic and/or semantic graphs. Node representations are generated by natural language processing. The input graph is provided to a first neural network to provide an output graph having learned node representations aligned with the node representations in the input graph. The method further includes predicting via a second neural network, node label and predicting, via a third neural network, edge labels in the output graph. The AMR is generated based on the predicted node labels and predicted edge labels. A system and a non-transitory computer readable storage medium are also disclosed.

Abstract: A computer-implemented method is provided for transferring a target text style using Reinforcement Learning (RL). The method includes pre-determining, by a Long Short-Term Memory (LSTM) Neural Network (NN), the target text style of a target-style natural language sentence. The method further includes transforming, by a hardware processor using the LSTM NN, a source-style natural language sentence into the target-style natural language sentence that maintains the target text style of the target-style natural language sentence. The method also includes calculating an accuracy rating of a transformation of the source-style natural language sentence into the target-style natural language sentence based upon rewards relating to at least the target text style of the source-style natural language sentence.

Abstract: The present application relates to a planet carrier assembly for a vehicle door closing actuator. The planet carrier assembly comprises a plurality of planetary gears and a planet carrier body. The planet carrier body comprises a disc portion, a cover portion and an output shaft portion, wherein the plurality of planetary gears are rotatably mounted on the disc portion via a corresponding number of mounting shafts fixed to the disc portion, one end of the mounting shaft protruding from a central hole of the planetary gear is pressed into a corresponding receiving hole on the cover portion, and the planet carrier body is further provided with a rotation locking device to prevent the cover portion from rotating circumferentially relative to the disc portion. The planet carrier assembly according to the present application has the advantages such as low cost, high strength, and simple assembly.

Abstract: The present application relates to a permanent magnet DC motor, which comprises a stator assembly and a rotor assembly, wherein the stator assembly comprises a housing and a magnetic cylinder, and the rotor assembly comprises a rotor; the rotor, the magnetic cylinder and the housing are sequentially arranged from inside to outside; the ratio of an angle corresponding to a commutation section of the surface magnetic curve of the magnetic cylinder to the corresponding angle of the surface magnetic curve of the corresponding magnetic pole is less than or equal to 15%; and the outer peripheral contour of the magnetic cylinder is based on a regular polygon, and curves are arranged at the connections of sides of the regular polygon to smoothly connect the sides of the regular polygon. The motor of the present application reduces the noise and vibration of the motor and improves its EMC level.

Abstract: A computer-implemented method is provided for transferring a target text style using Reinforcement Learning (RL). The method includes pre-determining, by a Long Short-Term Memory (LSTM) Neural Network (NN), the target text style of a target-style natural language sentence. The method further includes transforming, by a hardware processor using the LSTM NN, a source-style natural language sentence into the target-style natural language sentence that maintains the target text style of the target-style natural language sentence. The method also includes calculating an accuracy rating of a transformation of the source-style natural language sentence into the target-style natural language sentence based upon rewards relating to at least the target text style of the source-style natural language sentence.

Abstract: The present application relates to a planet carrier assembly for a vehicle door closing actuator. The planet carrier assembly comprises a plurality of planetary gears and a planet carrier body. The planet carrier body comprises a disc portion, a cover portion and an output shaft portion, wherein the plurality of planetary gears are rotatably mounted on the disc portion via a corresponding number of mounting shafts fixed to the disc portion, one end of the mounting shaft protruding from a central hole of the planetary gear is pressed into a corresponding receiving hole on the cover portion, and the planet carrier body is further provided with a rotation locking device to prevent the cover portion from rotating circumferentially relative to the disc portion. The planet carrier assembly according to the present application has the advantages such as low cost, high strength, and simple assembly.

Abstract: A driver device for opening and closing a vehicle door, comprising an electric motor and a planetary gear gearbox, wherein the electric motor comprises an electric motor output shaft, and the planetary gear gearbox comprises a gearbox input shaft coaxially connected to the electric motor output shaft, and a gearbox output shaft coaxially connected to an end of a door shaft of the vehicle door to provide the door shaft with a torque required to open and close the vehicle door. Compared with vehicle door opening and closing functions in the prior art, the driver device can be installed by utilizing the space at the door shaft of the vehicle door, without affecting the integrity of the door body of the vehicle door. Furthermore, a vehicle door comprising the aforesaid driver device is further provided.