Abstract: A design method for an inerter with adaptively adjusted inertia ratio is based on a lead screw-flywheel inerter, which is to change the positions of mass blocks on a flywheel along the radial direction of the flywheel, so as to change of the moment of inertia of the flywheel, and thus to realize adaptive adjustment of the inertia ratio of the inerter. Specifically, the change of angular velocity of the flywheel is caused by the change of an external force load on a lead screw, a centrifugal force on the mass blocks in spring-mass block structures is changed by the angular velocity, and the positions of the mass blocks in the radial direction of the flywheel is determined by the balanced relation of the centrifugal force and a spring restore force, so that the design purpose is achieved.

Abstract: A training system produces a resource-efficient machine-trained model via a training architecture that employs plural processing paths. Some of the processing paths incorporate the use of auxiliary information that imparts external knowledge about source items being processed. The training architecture also employs contrastive learning that operates at different respective levels within the training architecture. For instance, the training architecture uses encoder-level contrastive learning to compare output information generated by different encoders within the training architecture. The training architecture uses decoder-level contrastive learning to compare output information produced by different decoders within the training architecture. An inference-stage system performs an application task using the model produced by the training system.

Abstract: In embodiments of the present disclosure, there is provided an approach for fact checking based on semantic graphs. According to embodiments of the present disclosure, after obtaining a text to be fact checked, a plurality of evidence sentences related to the text are retrieved from an evidence database. Then, semantic graphs of the text and the evidence sentences are constructed based on the semantic analysis, and a veracity of a statement in the text can be determined based on the semantic graphs. Embodiments of the present disclosure propose a graph-based reasoning approach for fact checking, and use the constructed semantic graphs to facilitate verification of the truthfulness of the text, thereby improving the accuracy for fact checking.

Abstract: This disclosure relates to a chip, an electronic device, a transportation vehicle, and a method for generating a control signal. The chip includes a mesh bus and a ring bus. The mesh bus is coupled to each sensor to receive and transmit perception data. The ring bus is coupled to a processor and the mesh bus. The processor receives different types of perception data from different sensors such as a camera and a lidar, and fuses the data to generate a control signal for controlling an execution apparatus.

Abstract: The present disclosure provides a technical solution of multi-modal chatting, which may provide response to user query by using multi-modal response in the interaction between chatbot and human beings, so that the expressing ways and the expressed content by the chatbot could be richer by using such response in a multi-modal way.

Abstract: Systems and methods are provided for training a data model based on training data. The training includes pre-training and fine-tuning the data model based on a combination of an autoregressive (AR) model and a non-autoregressive (NAR) model. Training data may be received and encoded into streams of tokens. A pre-trainer during decoding generates a continuum of data structures of the AR and NAR combined model including a main stream and a series of predicting streams. Masked tokens in predicting streams reference or attend to one or more preceding tokens in the main stream or the preceding predicting streams. A fine-tuner selects streams to generate a trained model according to a target data model. The target data model is determined based on balancing an accuracy constraint and an efficiency constraint for predicting tokens. The decoder acts as abridge between the AR and NAR models in generating a trained data model.

Abstract: A knowledge injection model for generative commonsense reasoning. In examples, an encoder-decoder model is used to generate a model output (204) a plausible description for a set of concepts. A prototype (218) is generated from an in-domain or out-of-domain knowledge corpus, which is further used as input (202) for the encoder-decoder model. Concept input tokens and prototype input tokens are scaled to limit potential skew that may be introduced by the prototype (218). Additionally, position indicators are generated for each input token, which indicate the relative position each respective input token as compared to other input tokens. As such, when decoding the scaled encoded input tokens, the decoder (214) may be more attuned to the scenario bias that is introduced by the prototype (218) when generating a model output (204). Thus, the encoder-decoder model need not rely solely on the set of concepts when generating the model output (204).

Abstract: Systems and methods are provided for generating a keyword sequence from an input query. A first text sequence corresponding to an input query may be received and encoded into a source sequence representation using an encoder of a machine learning model. A keyword sentence may then be generated from the source sequence representation using a decoder of the machine learning model. The decoder may generate a modified generation score for a plurality of prediction tokens, wherein the modified generation score is based on the respective prediction token generation score and a maximum generation score for a suffix of each prediction token. The decoder may then select the prediction token of the plurality of prediction tokens based on the modified generation score, and add the selected prediction token to the previously decoded partial hypothesis provided by the decoder.

Abstract: A retrieval-augmented code completion system uses the context of a partially-formed source code snippet of a source code program and a hint to predict the source code tokens needed to complete the partially-formed source code snippet. The hint is a source code segment that completes a semantically-similar source code segment of the partially-formed source code snippet. The hint is found in a retrieval source code database using a hybrid retrieval technique. A deep learning decoder model uses the context of the partially-formed source code snippet and the hint to predict the most likely candidate sequence of source code tokens to complete the partially-formed source code snippet.

Abstract: Described herein is a mechanism to identify user intent in requests submitted to a system such as a digital assistant or question-answer systems. Embodiments utilize a match methodology instead of a classification methodology. Features derived from a subgraph retrieved from a knowledge base based on the request are concatenated with pretrained word embeddings for both the request and a candidate predicate. The concatenated inputs for both the request and predicate are encoded using two independent LSTM networks and then a matching score is calculated using a match LSTM network. The result is identified based on the matching scores for a plurality of candidate predicates. The pretrained word embeddings allow for knowledge transfer since pretrained word embeddings in one intent domain can apply to another intent domain without retraining.

Abstract: In implementations of the subject matter described herein, a new approach for presenting a response to a message in a conversation is proposed. Generally speaking, in response to receiving a message in a conversation, the received message will be matched with one or more documents on the sentence basis. That is, the received message is compared with the sentences from a document(s), rather than predefined query-response pairs. In this way, a whole sentence may be selected from the document as a candidate response. Then the suitability of this sentence with respect to the ongoing conversation will be determined, and the response will be generated and rendered in an adaptive way based on the suitability. As a result, the user experiences may be significantly enhanced in the chatbot scenario.

Abstract: A training system produces a resource-efficient machine-trained model via a training architecture that employs plural processing paths. Some of the processing paths incorporate the use of auxiliary information that imparts external knowledge about source items being processed. The training architecture also employs contrastive learning that operates at different respective levels within the training architecture. For instance, the training architecture uses encoder-level contrastive learning to compare output information generated by different encoders within the training architecture. The training architecture uses decoder-level contrastive learning to compare output information produced by different decoders within the training architecture. An inference-stage system performs an application task using the model produced by the training system.

Abstract: Implementations of the subject matter described herein provide a solution for generating a text from the structured data. In this solution, the structured data is converted into its representation, where the structured data comprises a plurality of cells, and the representation of the structured data comprises plurality of representations of the plurality of cells. A natural language sentence associated with the structured data may be determined based on the representation of the structured data, thereby implementing the function of converting the structured data into a text.

Abstract: Computing technology is described herein that provides an attention mechanism, implemented by a neural network, that generates attention information based on head-specific query information and shared key and value (KV) information, without computing head-specific key information and head-specific value information, and without caching the head-specific key information and the head-specific value information in memory. This manner of operation allows the computing technology to make efficient use of processing and memory resources. In some implementations, the attention mechanism is part of decoder of an encoder-decoder system, or a standalone decoder system. In some implementations, the computing technology leverages the attention information to generate synthesized text based on input text.

Abstract: A design method for an inerter with adaptively adjusted inertia ratio is based on a lead screw-flywheel inerter, which is to change the positions of mass blocks on a flywheel along the radial direction of the flywheel, so as to change of the moment of inertia of the flywheel, and thus to realize adaptive adjustment of the inertia ratio of the inerter. Specifically, the change of angular velocity of the flywheel is caused by the change of an external force load on a lead screw, a centrifugal force on the mass blocks in spring-mass block structures is changed by the angular velocity, and the positions of the mass blocks in the radial direction of the flywheel is determined by the balanced relation of the centrifugal force and a spring restore force, so that the design purpose is achieved.

Abstract: In embodiments of the present disclosure, there is provided an assertion-based question answering manner. After a question and the related passage are obtained, an assertion answer to the question is determined based on content of the passage, and the assertion answer has a predetermined structure and represents a complete semantic meaning. Then, the assertion answer to the question may be outputted to the user. In the embodiments of the present disclosure, the question and the relevant passage are used as input, and a semi-structured assertion answer is output. The assertion answer according to embodiments of the present disclosure can provide richer semantic content than the traditional short answer, and provide a more concise expression than the traditional long answer, thereby ensuring accuracy of the answer while improving the user experience.

Abstract: The present invention provides a method for analyzing global stability of a conveying fluid pipe-nonlinear energy sink system, and belongs to the technical field of system stability proof and analysis of a control system. The method comprises: establishing a high-order partial differential model of a conveying fluid pipe-nonlinear energy sink system based on a target energy transfer theory, discretizing the model into a second-order nonlinear ordinary differential form by means of the Galerkin approximation method, and further transforming the model into a quadratic model containing gradient information first; then obtaining a global stability judgment condition of the system by means of the energy disturbance technology, and verifying the theoretical results by means of the numerical method finally.

Abstract: A transformer-based neural network includes at least one mask attention network (MAN). The MAN computes an original attention data structure that expresses influence between pairs of data items in a sequence of data items. The MAN then modifies the original data structure by mask values in a mask data structure, to produce a modified attention data structure. Compared to the original attention data structure, the modified attention data structure better accounts for the influence of neighboring data items in the sequence of data items, given a particular data item under consideration. The mask data structure used by the MAN can have static and/or machine-trained mask values. In one implementation, the transformer-based neural network includes at least one MAN in combination with at least one other attention network that does not use a mask data structure, and at least one feed-forward neural network.

Abstract: Implementations of the present disclosure relate to text generation with a customizable style. In a method, a first natural language is received; the first natural language text is converted, via a text generation model, into a second natural language text that at least partly reflects the meaning of the first natural language text and has a style distinguishable from the first natural language text, the text generation model comprising a modifiable parameter; and in response to receiving a modification to the parameter, the first natural language text is converted, via the text generation model, into a third natural language text that at least partly reflects the meaning of the first natural language text and includes a style distinguishable from both the first natural language text and the second natural language text.

Abstract: In embodiments of the present disclosure, there is provided an approach for fact checking based on semantic graphs. According to embodiments of the present disclosure, after obtaining a text to be fact checked, a plurality of evidence sentences related to the text are retrieved from an evidence database. Then, semantic graphs of the text and the evidence sentences are constructed based on the semantic analysis, and a veracity of a statement in the text can be determined based on the semantic graphs. Embodiments of the present disclosure propose a graph-based reasoning approach for fact checking, and use the constructed semantic graphs to facilitate verification of the truthfulness of the text, thereby improving the accuracy for fact checking.