8 results about "Neural network language models" patented technology

The application discloses a speech recognition text processing method and device, electronic equipment and storage medium, and relates to the field of artificial intelligence. The method comprises the following steps: obtaining a speech recognition text, and performing error detection on the speech recognition text based on a pre-set error detection rule to obtain an error word group, wherein the error detection rule is set based on a word segmentation dictionary and a statistical language model; performing primary error correction processing on the error word group according to a pre-set error correction rule, wherein the error correction rule is constructed based on a predetermined language model; in response to the failure of the primary error correction processing of part of the error word groups, inputting the part of the error word groups into a pre-trained neural network language model for secondary error correction processing; and performing error correction processing on the error word groups according to the results of the primary error correction processing and the secondary error correction processing to generate an error-corrected speech recognition text. Through the application, the accuracy of speech recognition can be improved.

Embodiments described herein provide a method of building an artificial intelligence (AI) agent to respond to a task request from a user. The method includes: receiving a set of single-modal data samples of a plurality of modalities; selecting a first single-modal data sample of a first modality and a second single-modal data sample of a second modality; generating a question associated with the first single-modal data sample and the second single-modal data sample; generating an answer with a reasoning to the question based on a second input prompt; training, a second neural network based language model, using a dataset comprising the question and the answer to generate a candidate answer in response to a training query; building the AI conversation bot through an application programming interface to the trained second neural network language model; and generating, using the AI conversation bot, a response to the task request.

Embodiments described herein provide a framework for evaluating and training neural network-based language models. Under the framework, training datasets that can be used to evaluate and train the models are generated by modifying sample training datasets such that the training datasets may include unanswerable context, inconsistent context, and / or counterfactual context. A portion of the training datasets is used to evaluate a model's faithfulness quality. Based on the evaluation, a subset of the training datasets can be selected and used to train the model, which improves the faithfulness quality of the model.

Embodiments described herein provide a multi-stage training and / or post-training framework to train and / or finetune a GLLM for domain-specific tasks so as to build an AI agent in a variety of technical applications. Specifically, the training framework comprises a first stage of combined continual pretraining (CPT) and instruction tuning (IT), and a second state of preference training.

Embodiments described herein provide a multi-stage training and / or post-training framework to train and / or finetune a GLLM for domain-specific tasks so as to build an AI agent in a variety of technical applications. Specifically, the training framework comprises a first stage of combined continual pretraining (CPT) and instruction tuning (IT), and a second state of preference training.

The application discloses a context-aware dependency-guided kernel fuzzing test case mutation method and system, and belongs to the technical field of software security and operating system kernel testing. The method comprises the following steps: dynamically collecting and minimizing a high-potential system call sequence set as a training set; modeling the dependency relationship contained in the training set based on a neural network language model, and using the language model to realize context-aware dependency-guided mutation in the mutation stage, so as to help selecting a system call suitable for the current context and establishing an effective state path; alternately switching between exploration and utilization stages, dynamically scheduling mutation operations through an upper bound confidence algorithm to balance the diversity and efficiency of the test, and avoiding falling into a local optimum; and repeating the above steps until the fuzzing test is completed. The application can improve the quality of test cases, trigger the deep code logic of the kernel, and optimize the coverage rate and the efficiency of vulnerability mining.

Embodiments described herein provide a code generation framework that explores a code search space of code generation tasks through a tree-based structure. Specifically, the code generation framework comprises a Thinker model, a Solver model, and a Debugger model to implement strategy-planning, solution implementation, and solution improving correspondingly. posing comprehensive roles needed for code generation.

A system for industrial plant logbook analysis by neural network language model, having a processor, a memory, and one or more programs stored in the memory. The one or more programs comprising instructions configured to receive a logbook of the industrial plant and extract an entity hierarchy flow providing details of hierarchy of various components of the industrial plant, such that the entity hierarchy flow is based on one or more data driven algorithms, design documentation, and a plant context hierarchy document. The system further trains the neural network language model with the entity hierarchy flow, where the training is based on a pretrained language model. The system further receives a user input requesting the industrial plant logbook analysis, such that based on the user input the system calculates a token output of the industrial plant logbook analysis using the trained neural network language model. The system further validates the calculated token output by a generative AI validation layer, updates the token output of the logbook analysis, and displays the updated output of the logbook analysis to the user.