Abstract: A computing system is provided including processing circuitry configured to implement a ranker module configured to jointly compute relevance scores of a set of candidate keywords to a query, and to generate a ranked list of candidate keywords based on the relevance scores. The ranker module includes a cross attention encoder configured to jointly compute the relevance scores by obtaining contextual embeddings for query tokens in the query and union of keyword tokens in the set of keywords, selectively pooling the contextual embeddings for the query tokens and the union of keyword tokens, inputting the selectively pooled contextual embeddings into a classifier that has been trained to predict a relevance score of the plurality of keywords to the query based on the contextual embeddings to output a relevance score for each query-keyword pair for the keywords in the set of candidate keywords, and outputting the ranked list of candidate keywords.

Abstract: The present invention relates to a class of 4-methanesulfonylbenzamide compounds with sulfur-containing substituents at the 3-position, represented by general formula (I), including their stereoisomers, agriculturally acceptable salts, preparation methods, herbicidal compositions, and their use in the field of plant protection, wherein R1, R2, X, Q, and n are as defined herein.

Abstract: A tagging system appends supplemental information to an original sequence of items, to produce a supplemented sequence of items. The tagging system includes a transformer-based encoder neural network that maps the supplemented sequence into hidden state information. The tagging system includes a post-processing neural network that transform the hidden state information into a tagged output sequence of items. That is, each item in the tagged output sequence includes a tag that identifies its entity class or some other characteristic. The tagging system can increase the accuracy of the tags it produces by virtue of the inclusion of the supplemental information added to each original sequence. A training system trains the tagging system to perform plural tasks, which further increases the accuracy of the tags it produces. The training system may commence training of the tagging system using a pre-trained model for the encoder neural network.

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 gemcitabine liposome pharmaceutical composition, a preparation method therefor and use thereof. According to the preparation method for the liposome, by means of optimization and control of the proportion of phospholipid to cholesterol, the proportion of the total lipid to an optional long circulating functional material, the proportion of the total lipid to a drug, and the type and the concentration of a salt solution in an aqueous interior, a liposome, which has high encapsulation efficiency, good storage stability, and high filtering performance, is not easy to leak, is stable and controllable to release, prolongs the half-life remarkably, improves the therapeutic effect, and reduces toxic and side effects, is prepared. In addition, the provided liposome prescription and preparation process are simple, and scaled-up production and clinical popularization and application are facilitated.

Abstract: A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts comprise receiving conversational data indicative of an interaction between a client computing device and a generative model. The conversational data is provided as input into an intent classification module and the intent classification module produces an output indicative of a user intent based upon the conversational data. An anchor generation module generates anchor text indicative of portions of the conversational data correlated with the user intent. A content query based upon the anchor text is generated and content responsive to the content query is obtained and presented at the client computing device.

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: An information retrieval technique uses one or more machine-trained models to generate one or more metadata embeddings. The technique then combines a query embedding with the metadata embedding(s). In some cases, the technique performs this operation using a graph convolution operation. This yields an augmented embedding. The technique then uses the augmented embedding to retrieve at least one item. The augmented embedding lies in the same vector space as target-item embeddings associated with candidate target items. Otherwise, the vector spaces associated with the query embedding and metadata embedding(s) can be different. In some implementations, the technique use dense retrieval, which enables the technique to deliver output results in real time.

Abstract: A method of interfacing a discrete digital workshop information system is provided, where the information system includes mutual integration among product lifecycle management (PLM), enterprise resource planning (ERP), a manufacturing execution system (MES), an energy management system (EMS), and a warehouse management system (WMS) of a finished product. A method of interfacing based on a data dictionary fusing different function datasets is proposed to solve the problems of a current discrete industry information system, such as single in function, a small amount of integrated information, a large number of “information islands” existing, incapable of achieving full-process informatization management and control, difficulty in product quality tracing and the like. By the method, it is possible to realize flexible production in a discrete manufacturing industry, precise management and control of a production process, significant improvement in product quality and significant reduction in operating costs.

Abstract: A cooling panel for a melter is disclosed that includes first and second outer walls and a plurality of side walls coupled to the first and second outer walls. The first and second outer walls and the plurality of side walls define an interior space. Each of the first and second outer walls, moreover, has a plurality of openings. The cooling panel further includes a plurality of baffles disposed in the interior space. The baffles include a plurality of projections. The respective openings of the outer walls and projections of the baffles fit together and are connected from outside of the cooling panel so that the outer walls and the baffles are fixed together, and the side walls are fixed to the outer walls so that the cooling panel is fluid-tight.

Abstract: Methods, systems, and devices supporting configurable resistivities for lines in a memory device, such as access lines in a memory array are described. For example, metal lines at different levels of a memory device may be oxidized to different extents in order for the lines at different levels of the memory device to have different resistivities. This may allow the resistivity of lines to be tuned on a level-by-level basis without altering the fabrication techniques and related parameters used to initially form the lines at the different levels, which may have benefits related to at least reduced cost and complexity. Lines may be oxidized to a controlled extent using either a dry or wet process.

Abstract: A technique serves information items associated with at least two item-serving modes using shared resources. For example, the technique delivers dynamic search ads in a dynamic search ad (DSA) mode using processing resources that were originally developed for serving text ads in a text ad (TA) mode. In a first aspect, the technique repurposes a part of the TA-mode processing flow to find a set of landing pages associated with a query. In a second aspect, the technique performs further processing based on output results generated by the TA-mode processing flow, with the objective of identifying a set of landing pages associated with the query. Overall, the technique reduces the consumption of resources in the serving of ads, and simplifies the maintenance of an ad-serving system. The technique also allows one mode to use algorithmic advances developed for use in another mode.

Abstract: Technologies described herein relate to dense retrieval and ranking of search results. A query indicating a computing context or user input is received. An embedding of the query is computed by way of a first encoder, and candidate results selected from a pool of potential results based upon the embedding of the query and embeddings of the potential results. A similarity score for a first of the candidate results is computed by way of a second encoder trained based upon an order metric that defines a ranking over a training set of potential results. The first encoder is trained based upon output of the second encoder prior to computing the embedding of the query. The candidate results are ranked based upon the similarity score of the first candidate result, and results responsive to the query are identified based upon the ranking. The identified results are output to a computing device.

Abstract: Technologies described herein relate to dense retrieval and ranking of search results. A query indicating a computing context or user input is received. An embedding of the query is computed by way of a first encoder, and candidate results selected from a pool of potential results based upon the embedding of the query and embeddings of the potential results. A similarity score for a first of the candidate results is computed by way of a second encoder trained based upon an order metric that defines a ranking over a training set of potential results. The first encoder is trained based upon output of the second encoder prior to computing the embedding of the query. The candidate results are ranked based upon the similarity score of the first candidate result, and results responsive to the query are identified based upon the ranking. The identified results are output to a computing device.

Abstract: A technique performs the task of knowledge-graph completion in a manner that is both scalable and resource efficient. In some implementations, the technique identifies a source entity having a source-target relation that connects the source entity to a yet-to-be-determined target entity. The technique also identifies a source-entity data item that provides a passage of source-entity text pertaining to the source entity. The technique uses a machine-trained encoder model to map the source-entity data item to source-entity encoded information. The technique then predicts an identity of the target entity based on the source-entity encoded information, and based on predicate encoded information that encodes the source-target relation. In some implementations, the technique also predicts the target entity based on a consideration of one or more neighboring entities that are connected to the source entity and their respective source-to-neighbor relations.

Abstract: A system for detecting material accumulation relative to rotating ground-engaging tools includes an agricultural implement having a frame and first and second ground-engaging tools supported relative to the frame, with the first ground-engaging tool corresponding to a different tool type than the second ground-engaging tool. The system also includes first and second speed sensor configured to provide data indicative of the rotational speeds of the first and second ground-engaging tools, respectively. In addition, the system includes a computing system communicatively coupled to the first and second speed sensors.

Abstract: A method of interfacing a discrete digital workshop information system is provided, where the information system includes mutual integration among product lifecycle management (PLM), enterprise resource planning (ERP), a manufacturing execution system (MES), an energy management system (EMS), and a warehouse management system (WMS) of a finished product. A method of interfacing based on a data dictionary fusing different function datasets is proposed to solve the problems of a current discrete industry information system, such as single in function, a small amount of integrated information, a large number of “information islands” existing, incapable of achieving full-process informatization management and control, difficulty in product quality tracing and the like. By the method, it is possible to realize flexible production in a discrete manufacturing industry, precise management and control of a production process, significant improvement in product quality and significant reduction in operating costs.

Abstract: Methods, systems, and devices supporting configurable resistivities for lines in a memory device, such as access lines in a memory array are described. For example, metal lines at different levels of a memory device may be oxidized to different extents in order for the lines at different levels of the memory device to have different resistivities. This may allow the resistivity of lines to be tuned on a level-by-level basis without altering the fabrication techniques and related parameters used to initially form the lines at the different levels, which may have benefits related to at least reduced cost and complexity. Lines may be oxidized to a controlled extent using either a dry or wet process.

Abstract: A computing device is provided including a processor configured to execute a transformer including an encoder having a global layer configured to receive tokenized embeddings for each of a plurality of tokens in a local input sequence and compute a global self-attention vector for each of the tokenized embeddings. The encoder further includes a local layer configured to receive each global self-attention vector from the global layer and compute local self-attention for each local input sequence, and add and normalize the global self-attention vector with the local self-attention vector to thereby produce an encoder representation including a self-attention vector for each local input sequence that includes both global self-attention values and local self-attention values. The transformer is configured to output a prediction for the global input sequence based on the encoder representation of each of the local input sequences of the global input sequence.

Abstract: A system for detecting material accumulation relative to rotating ground-penetrating tools of an agricultural implement includes an agricultural implement having a frame and at least one rotating ground-penetrating tool supported relative to the frame. The rotating ground-penetrating tool(s) is configured to penetrate into the ground to a given penetration depth. The system also includes a tool speed sensor configured to provide data indicative of a rotational speed of the ground-penetrating tool(s) and a computing system communicatively coupled to the tool speed sensor. The computing system is configured to monitor the rotational speed of the ground-penetrating tool(s) based on the data provided by the tool speed sensor, determine a threshold rotational speed based at least in part on the penetration depth of the ground-penetrating tool(s), and determine when the rotational speed of the ground-penetrating tool(s) falls below the threshold rotational speed.