16 results about "Logic form" patented technology

The invention discloses an electric power field credible question-answering system based on a knowledge graph and multiple agents, and belongs to the technical field of intelligent power grids. The electric power field credible question-answering system comprises the steps that an existing knowledge base is stored through a vector knowledge base, the knowledge graph and a relational database, and then a multi-agent system is constructed based on a large language model; a complex problem is decomposed into a plurality of sub-problems by adopting a logic form language in real-time dialogue, solving is carried out based on operators such as planning, reasoning and retrieval, symbolization and structuring of a problem solving process are realized, knowledge is aligned and integrated by using a semantic reasoning technology, a semantic relationship between the knowledge is identified and established, and a real-time dialogue result is obtained. And realizing credible questions and answers in a manner of recalling related knowledge. According to the method, the deep fusion of the unstructured text, the structured data and the semantic relationship is realized by constructing the multi-modal knowledge storage system, the knowledge coverage rate and the semantic consistency are remarkably improved, and the understanding and response capabilities of the system to compound problems are improved.

The present disclosure relates to manufacturing training and testing data by leveraging data augmentation techniques to generate examples of long context database schemas. Aspects are directed towards accessing a training dataset comprising training examples where each training example may include i) a prompt including a natural language utterance and a database schema having one or more tables, and ii) a gold logical form corresponding to the natural language utterance, combining the tables from the database schemas in the training examples may generate a combined database schema set, generating a set of long context training examples based on the training dataset and the combined database schema set, and incorporating the long context database schema into the selected training example to generate a long context training example to train a generative artificial intelligence model with at least the set of long context training examples to generate a trained generative artificial intelligence model.

Techniques are disclosed herein for providing and using a natural language to logical form model having execution and sematic error correction capabilities. In one aspect, a method is disclosed that includes: accessing a set of training examples and generating a set of error correction training examples via an iterative process performed for each training example. The iterative process includes generating an inferred logical form, executing the inferred logical form on a database, when executing the inferred logical form on the database fails, obtaining an execution error message corresponding to the failure, and recording the inferred logical form and the execution error message as part of an execution error example, and populating an error correction prompt template with the execution error example to generate an error correction training example. A machine learning model may then be trained with at least the set of error correction training examples.

The present disclosure is related to techniques for converting a natural language utterance to a logical form query and deriving a natural language interpretation of the logical form query. The techniques include accessing a Meaning Resource Language (MRL) query and converting the MRL query into a MRL structure including logical form statements. The converting includes extracting operations and associated attributes from the MRL query and generating the logical form statements from the operations and associated attributes. The techniques further include translating each of the logical form statements into a natural language expression based on a grammar data structure that includes a set of rules for translating logical form statements into corresponding natural language expressions, combining the natural language expressions into a single natural language expression, and providing the single natural language expression as an interpretation of the natural language utterance.

Techniques are disclosed for augmenting training data for training a machine learning model to generate database queries. Training data comprising a first training example comprising a first natural language utterance, a logical form for the first natural language utterance, and associated first metadata is obtained. From the first training example, a template utterance is generated. A second natural language utterance is generated by filling slots in the template utterance based on a database schema and database values. Updated metadata is produced based on the first metadata and the second natural language utterance. A second training example is generated, comprising the second natural language utterance, the logical form for the first natural language utterance, and the updated metadata. The training data is augmented by adding the second training example. A machine learning model is trained to generate a database query comprising the database operation using the augmented training data set.

Techniques are disclosed herein for synthesizing synthetic training data to facilitate training a natural language to logical form model. In one aspect, training data can be synthesized from original under a framework based on templates and a synchronous context-free grammar. In one aspect, training data can be synthesized under a framework based on a probabilistic context-free grammar and a translator. In one aspect, training data can be synthesized under a framework based on tree-to-string translation. In one aspect, the synthetic training data can be combined with original training data in order to train a machine learning model to translate an utterance to a logical form.

Techniques are disclosed herein for providing and using a natural language to logical form model having execution and sematic error correction capabilities. In one aspect, a method is disclosed that includes: accessing a set of training examples and generating a set of error correction training examples via an iterative process performed for each training example. The iterative process includes generating an inferred logical form, executing the inferred logical form on a database, when executing the inferred logical form on the database fails, obtaining an execution error message corresponding to the failure, and recording the inferred logical form and the execution error message as part of an execution error example, and populating an error correction prompt template with the execution error example to generate an error correction training example. A machine learning model may then be trained with at least the set of error correction training examples.

The present disclosure relates to improved semantic parsers including a coarse semantic parser and a fine semantic parser. Techniques are described for improving a semantic parser of a dialog system by decomposing the semantic parser into a coarse semantic parser and a fine semantic parser. The methods described herein include accessing an utterance received in a dialog system. The utterance is a text-based natural language expression. The methods further include applying a coarse semantic parser to the utterance to determine an intermediate logical form for the utterance. The intermediate logical form indicates one or more intents in the utterance. The methods further include applying a fine semantic parser to the intermediate logical form to determine a logical form for the utterance. The logical form is a syntactic expression of the utterance according to an established grammar, and the logical form includes one or more parameters of the one or more intents. The logical form can be used to have a conversation with a user of the dialog system.

The present disclosure relates to machine learning techniques for In-Context-Learning (ICL) with pattern-based retrieval for the task of converting Natural Language (NL) to Structured Query Language (SQL). Aspects are directed towards acquiring a natural language utterance and a database schema, searching, using at least a portion of the natural language utterance as a key, a memory bank for one or more in-context examples that are relevant to the key, generating a prompt comprising the natural language query, the database schema, and the one or more in-context examples, transmitting the prompt to a first pretrained generative artificial intelligence model, receiving, from the first pretrained generative artificial intelligence model, a logical form corresponding to the natural language utterance based at least in part on the prompt, executing the logical form on a database to obtain a query result, and providing the query result to a user.

The invention discloses a large model question answering method and device based on bidirectional sorting and a storage medium. The method comprises the steps that a first candidate logic form list of natural language target questions is generated through a large language model; transcribing each candidate logic form into a corresponding natural language question by using a transcription model; calculating the semantic similarity between each transcription question and the natural language target question; reordering the candidate logic forms according to the semantic similarity to obtain a second candidate logic form list; fusing the first candidate logic form list and the second candidate logic form list by using a credibility perception DOA fusion method to obtain a third candidate logic form list; and querying an answer corresponding to the target question in the knowledge base according to the third candidate logic form list. While the candidate coverage range is ensured, the position of the golden logic form in the fusion list is remarkably improved, and the efficient execution of large model question answering and the question answering accuracy are effectively improved.

Techniques for augmenting training data include accessing training data comprising a plurality of training examples comprising a first training example comprising a first natural language utterance and a first logical form for the first natural language utterance. A second natural language utterance is generated by adding or replacing one or more values in the first natural language utterance. A logical form for the second natural language utterance is generated. A second training example is generated, comprising the second natural language utterance and the logical form for the second natural language utterance. The training data is augmented by adding the second training example to the plurality of training examples to generate an augmented training data set. A machine learning model is trained to generate logical forms for utterances using the augmented training data set.

This invention discloses a large-scale question-answering method, apparatus, and storage medium based on bidirectional ranking. The method includes: generating a first candidate logical form list for a natural language target question using a large language model; transcribing each candidate logical form into a corresponding natural language question using a transcription model; calculating the semantic similarity between each transcribed question and the natural language target question; reordering the candidate logical forms according to the semantic similarity to obtain a second candidate logical form list; fusing the first and second candidate logical form lists using a credibility-aware Polda fusion method to obtain a third candidate logical form list; and querying the answer corresponding to the target question in a knowledge base based on the third candidate logical form list. While ensuring candidate coverage, this method significantly improves the position of the most valuable logical form in the fused list, effectively enhancing the efficiency and accuracy of large-scale question-answering.

Systems and methods identify whether an input utterance is suitable for providing to a machine learning model configured to generate a query for a database. Techniques include generating an input string by concatenating a natural language utterance with a database schema representation for a database; providing the input string to a first machine learning model; based on the input string, generating, by the first machine learning model, a score indicating whether the natural language utterance is translatable to a database query for the database and should be routed to a second machine learning model, the second machine learning model configured to generate a query for the database based on the natural language utterance; comparing the score to a threshold value; and responsive to determining that the score exceeds the threshold value, providing the natural language utterance or the input string to the second machine learning model.

The invention discloses a semantic continuity guarantee method and device, a terminal and a storage medium, and the method comprises the steps: carrying out the structural representation of a natural language demand, and determining the structural demand information; converting the structured demand information into a formalized protocol in a linear tense logic form; performing semantic representation and semantic alignment on the formalized protocol according to the first image data, and determining aligned semantic representation; decoding the aligned semantic representation, and determining executable data; determining a target mode according to the available CPU resources of the system and the edge equipment information, performing runtime guarantee based on the target mode and the executable data, and determining a runtime guarantee result; and generating a device control instruction based on the runtime guarantee result through the operating system security center. Therefore, the problems that the existing method in the prior art cannot fundamentally solve the problem of lack of full-link semantic continuity and is difficult to meet the high-reliability operation requirement of the safety key AI system in a dynamic environment can be effectively solved.

Techniques are disclosed herein for addressing catastrophic forgetting and over-generalization while training a model to transform natural language to a logical form such as a meaning representation language. The techniques include accessing training data comprising natural language examples, augmenting the training data to generate expanded training data, training a machine learning model on the expanded training data, and providing the trained machine learning model. The augmenting includes (i) generating contrastive examples by revising natural language of examples identified to have caused regression during training of a machine learning model with the training data, (ii) generating alternative examples by modifying operators of examples identified within the training data that belong to a concept that exhibits bias, or (iii) a combination of (i) and (ii).

This disclosure provides a knowledge graph question answering method based on code style context learning. For an input code style learning question and a knowledge base, a large language model is first used to obtain a function call sequence through code style context learning. A dense retrieval system is then used to link entities extracted from the function calls and to perform relation matching on the relation names extracted from the function calls. Finally, a program interpreter executes the generated function call sequence to obtain the logical form, which is then further converted into an executable query to obtain the answer to the question. This method effectively solves the formatting error problem in logical form generation through metafunction design and retrieval enhancement strategies. It not only avoids secondary training of a large model but also significantly improves generalization performance in scenarios with few or no samples.