Abstract: Implementations of semantic parsing using pre-trained language models are provided. One aspect includes a computing system for semantic parsing of natural language.

Abstract: Systems and methods are provided for implementing conversational large language model (“LLM”) or other AI/ML-based user tenant orchestration. A first prompt is generated based on natural language (“NL”) input from a user. The first prompt is used by a first LLM or AI/ML system to generate a query to access data items that are stored in a portion of a multitenant data storage system, the portion being accessible by the user. Once accessed and received, the data items are input into a second prompt that is used by a second LLM or AI/ML system to return a set of functions with corresponding sets of arguments. The set of functions are executed according to the sets of arguments, and the results of the executed functions are used to generate a response to the NL input. The generated response is then caused to be presented to the user via a user interface.

Abstract: A computer-implemented method is presented. The method comprises sequentially receiving a plurality of utterance prefixes, each sequentially received utterance prefix derived from a progressively longer incomplete portion of a full user utterance. For each sequentially received utterance prefix, a complete dataflow program is predicted based on the utterance prefix. The complete dataflow program includes a plurality of program nodes to be executed to satisfy the full user utterance. One or more program nodes are selected from the predicted complete dataflow program to speculatively execute based on at least the utterance prefix.

Abstract: Examples are disclosed that related to synthesizing a dataset of utterances in an automated manner using a computer while preserving user privacy. The synthesized dataset of utterances is usable to train a machine learning model. In one example, a differentially private parse tree generation model is trained based at least on private parse trees of a private utterance-parse tree dataset. A differentially private parse-to-utterance model is trained based at least on private utterances and corresponding private parse trees of the private utterance-parse tree dataset. A synthesized parse tree dataset is generated. The synthesized parse tree dataset includes synthesized parse trees sampled at random from the trained differentially private parse tree generation model. A synthesized utterance dataset is generated, via the trained differentially private parse-to-utterance model.

Abstract: A computer-implemented method is presented. The method comprises sequentially receiving a plurality of utterance prefixes, each sequentially received utterance prefix derived from a progressively longer incomplete portion of a full user utterance. For each sequentially received utterance prefix, a complete dataflow program is predicted based on the utterance prefix. The complete dataflow program includes a plurality of program nodes to be executed to satisfy the full user utterance. One or more program nodes are selected from the predicted complete dataflow program to speculatively execute based on at least the utterance prefix.

Abstract: Systems and methods are provided for automatically generating a program based on a natural language utterance using semantic parsing. The semantic parsing includes translating a natural language utterance into instructions in a logical form for execution. The methods use a pre-trained natural language model and generate a canonical utterance as an intermediate form before generating the logical form. The natural language model may be an auto-regressive natural language model with a transformer to paraphrase a sequence of words or tokens in the natural language utterance. The methods generate a prompt including exemplar input/output pairs as a few-shot learning technique for the natural language model to predict words or tokens. The methods further use constrained decoding to determine a canonical utterance, iteratively selecting sequence of words as predicted by the model against rules for canonical utterances. The methods generate a program based on the canonical utterance for execution in an application.

Abstract: A business object model, which reflects data that is used during a given business transaction, is utilized to generate interfaces. This business object model facilitates commercial transactions by providing consistent interfaces that are suitable for use across industries, across businesses, and across different departments within a business during a business transaction. In some operations, software creates, updates, or otherwise processes information related to a business partner relationship and a business partner hierarchy business object.

Abstract: A communications method utilizes memory areas to buffer portions of the media streams. These buffer areas are shared by user applications, with the desirable consequence of reducing workload for the server system distributing media to the user (client) applications. The preferred method allows optimal balancing of buffering delays and server loads, as well as optimal choice of buffer contents for the shared memory buffers.