Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a plan for an input task. The method involves receiving a query for the input task and obtaining candidate task-plan examples. An initial plan, comprising an initial action sequence, is obtained for the input task. For each candidate example, an action sequence similarity score is computed, measuring similarity between the initial action sequence and the action sequence in the candidate example. A set of task-plan examples is selected from the candidates using these similarity scores. Finally, a generative machine learning model processes the query and prompt inputs generated from the selected set of examples to generate an output plan. This approach improves plan generation by selecting relevant examples based on procedural similarity rather than superficial task description similarity, enhancing the quality and accuracy of the output plan.

Abstract: A language processing method is provided comprising forming a feature from at least one word from an input sequence of words; generating an address of a memory cell storing a weight for the feature based on a hash function using the feature as argument; retrieving the weight for the feature from the memory cell with the address; and generating a dependency tree for the input sequence based on the weight and a second order dependency parsing algorithm. A corresponding electronic device is provided as well.

Abstract: A language processing method is provided comprising forming a feature from at least one word from an input sequence of words; generating an address of a memory cell storing a weight for the feature based on a hash function using the feature as argument; retrieving the weight for the feature from the memory cell with the address; and generating a dependency tree for the input sequence based on the weight and a second order dependency parsing algorithm. A corresponding electronic device is provided as well.