Abstract: A method includes accessing document including sentences, document being associated with configuration flag indicating whether ABSA, SLSA, or both are to be performed; inputting the document into language model that generates chunks of token embeddings for the document; and, based on the configuration flag, performing at least one from among the ABSA and the SLSA by inputting the chunks of token embeddings into a multi-task model. When performing the SLSA, a part of token embeddings in each of the chunks is masked, and the masked token embeddings do not belong to a particular sentence on which the SLSA is performed.

Abstract: A computer-implemented method includes: accessing a plurality of datasets, where each dataset of the plurality of datasets includes training examples; selecting datasets that include the training examples in a source language and a target language; and sampling, based on a sampling weight that is determined for each of the selected datasets, the training examples from the selected datasets to generate the training batches; training an ML model for performing at least a first task using the training examples of the training batches, by interleavingly inputting the training batches to the ML model; and outputting the trained ML model configured to perform the at least the first task on input utterances provided in at least one among the source language and the target language. The sampling weight is determined for each of the selected datasets based on one or more attributes common to the training examples of the selected dataset.

Abstract: Techniques disclosed herein can include receiving an instruction to perform a stress test on one or more cloud computing resources of a cloud computing system. Worker nodes of the cloud computing system can be provisioned by a resource manager to perform the stress test on the cloud computing resources. The resource manager can instruct the one or more worker nodes of the cloud computing system to perform the stress test. Data generated by the worker nodes during the stress test can be received by the resource manager and used to train a projection framework comprising a trained machine learning model. The projection framework can generate a resource projection and the projection can be used to provision cloud computing resources to host the cloud service.

Abstract: A novel system is described for performing hierarchical named entity recognition (“HNER”) processing that includes identifying categories at different hierarchical levels for a named entity. The HNER system uses a novel architecture comprising an encoder model and a system of trained machine learning (ML) models to perform the HNER processing, where each trained model in the system of ML models corresponds to a particular hierarchical level, and each model is trained to extract one or more named entities and predict a category for each extracted named entity for the corresponding hierarchical level. Novel techniques are also described for training the various models in HNER system including an encoder model and models in the system of models.