Abstract: An example method for prompt-based query generation is provided. The method includes receiving, by a computing device, at least two prompts associated with a retrieval task to be performed on a corpus of documents associated with the task. The method includes applying, based on the at least two prompts and the corpus of documents, a large language model to generate a synthetic training dataset comprising a plurality of query-document pairs, wherein each query-document pair comprises a synthetically generated query and a document from the corpus of documents. The method includes training, on the plurality of query?document pairs from the synthetic training dataset, a document retrieval model to take an input query associated with the retrieval task and predict an output document retrieved from the corpus of documents. The method includes providing, by the computing device, the trained document retrieval model.

Abstract: A seat assembly for a vehicle includes a seat frame and a plurality of support units disposed on the seat frame. Each of the plurality of support units has a support tray, a cylinder connected to the support tray, a pressure sensor, an intake valve, and an exhaust valve. A gas supply to the cylinder is controllable via the inlet valve, a gas discharge from the cylinder is controllable via the exhaust valve, and an occupant of the vehicle is supportable by the support tray and a support force and a support height of the support tray is adjustable. A controller is configured to receive a pressure signal detected by the pressure sensor of each of the plurality of support units to control an open state or a closed state of the intake valve and the exhaust valve of each of the plurality of support units separately.

Abstract: An example method includes providing, to a sequence model (i) a plurality of few-shot prompts, wherein each prompt comprises a demonstration passage, a demonstration task, and a demonstration query, wherein the demonstration task describes a type of retrieval, and wherein the demonstration query is relevant to the demonstration task, and (ii) a plurality of passages sampled from a corpus of passages. The method also includes receiving, from the sequence model and for the plurality of passages and based on the plurality of few-shot prompts, a respective plurality of predicted task-query pairs, the sequence model having been prompted to predict a task based on an input passage, and predict an output query relevant to the predicted task. The method further includes generating a synthetic training dataset comprising the plurality of passages and the respective plurality of predicted task-query pairs. The method also includes providing the synthetic training dataset.

Abstract: Disclosed are a method and an apparatus for multi-round alignment of gas long-distance pipeline magnetic flux leakage internal inspection data. The method includes: identifying the primary feature point data of two sets of internal inspection data, dividing the pipeline into multiple primary pipeline sections, identifying the secondary feature points in the primary pipeline sections, aligning the secondary feature points using a segment splitting algorithm, re-aligning unaligned secondary feature points, and aligning remaining feature points and defects in the secondary pipeline sections.

Abstract: Disclosed are a method and an apparatus for multi-round alignment of gas long-distance pipeline magnetic flux leakage internal inspection data. The method includes: identifying the primary feature point data of two sets of internal inspection data, dividing the pipeline into multiple primary pipeline sections, identifying the secondary feature points in the primary pipeline sections, aligning the secondary feature points using a segment splitting algorithm, re-aligning unaligned secondary feature points, and aligning remaining feature points and defects in the secondary pipeline sections.

Abstract: There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive an input sentence including a first predicate and at least a first argument depending from the first predicate, identify the first predicate, identify the first argument based on the first predicate, apply a dependency multiplication to determine a semantic role of the first argument based on the first predicate, and assign the first argument to an argument cluster including one or more similar arguments based on the semantic role of the first argument.

Abstract: There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive an input sentence including a first predicate and at least a first argument depending from the first predicate, identify the first predicate, identify the first argument based on the first predicate, apply a dependency multiplication to determine a semantic role of the first argument based on the first predicate, and assign the first argument to an argument cluster including one or more similar arguments based on the semantic role of the first argument.

Abstract: A spoken language understanding (SLU) system receives a sequence of words corresponding to one or more spoken utterances of a user, which is passed through a spoken language understanding module to produce a sequence of intentions. The sequence of words are passed through a first subnetwork of a multi-scale recurrent neural network (MSRNN), and the sequence of intentions are passed through a second subnetwork of the multi-scale recurrent neural network (MSRNN). Then, the outputs of the first subnetwork and the second subnetwork are combined to predict a goal of the user.

Abstract: A spoken language understanding (SLU) system receives a sequence of words corresponding to one or more spoken utterances of a user, which is passed through a spoken language understanding module to produce a sequence of intentions. The sequence of words are passed through a first subnetwork of a multi-scale recurrent neural network (MSRNN), and the sequence of intentions are passed through a second subnetwork of the multi-scale recurrent neural network (MSRNN). Then, the outputs of the first subnetwork and the second subnetwork are combined to predict a goal of the user.