17 results about "Syntactic tree" patented technology

The invention relates to a neural machine translation selective knowledge distillation method based on dependency constraint self-attention, and belongs to the technical field of machine translation. An existing knowledge distillation method has the problems that only vocabulary-level probability distribution is transmitted, syntactic structure constraints are ignored, and the capacity of a student model is reduced, so that the complex syntactic modeling capacity is insufficient. Therefore, according to the method, a syntactic matrix converted through a source language dependency syntactic tree is provided, linear combination is adopted to dynamically correct self-attention weight distribution of an encoder, and explicit syntactic constraints are synchronously injected into a teacher-student model. Through a selective distillation strategy of syntax perception, deep knowledge effective for training in a teacher model is screened, a cross-language syntax corresponding relation is obtained in combination with structure alignment distillation, and model compression and translation performance enhancement is realized through attention optimization and a selective knowledge transmission mechanism guided by a dependency syntax.

The application discloses an aspect-level sentiment analysis method, system and device based on emotional knowledge and a medium, and can be widely applied in the technical field of sentiment analysis. The application obtains the dependency syntax tree of an input sentence, constructs the dependency graph structure of the sentence according to the dependency syntax tree, and then fuses the emotional knowledge and the position information into the dependency graph structure to obtain the adjacency matrix expressing the correlation between the nodes in the sentence. The global sharing of the emotional knowledge node parameters realizes the storage, updating and sharing of the emotional knowledge, thereby improving the fusion degree of the emotional knowledge. Then, the aspect-level sentiment analysis model is trained according to the sentences in the review corpus and the adjacency matrix, thereby reducing the cognitive bias of the model and improving the prediction performance of the model.

This application discloses a text readability analysis method, system, and electronic device based on NLP processing. The method extracts multiple character entities; performs word segmentation on the preprocessed text to be analyzed to obtain a word sequence and constructs a dependency syntax tree; based on the multiple character entities, the preprocessed text to be analyzed, and the dependency syntax tree, it extracts features such as the number of characters, the entropy of character personality diversity, the conflict density, the dialogue ratio, the relationship density, and the relationship complexity; it processes and fuses these features to obtain a fused feature vector; it inputs the fused feature vector into an encoder to obtain a preliminary score vector; and it determines the readability score of the text to be analyzed based on the preliminary score vector. This application can improve the accuracy of text readability analysis.

The application discloses a text language automatic detection method and system based on syllable and affix features, relates to the field of natural language processing, and comprises the following steps: text preprocessing and basic language unit extraction are performed on a text to be detected to obtain a text syllable sequence and an affix list; based on the affix list, a multidimensional pragmatic scene distribution vector in the context of the text syllable sequence is extracted, and core connectivity in a pre-constructed morphological paradigm knowledge graph is acquired; the function load value of the affix is matched from an affix function load database, the affix function load value is normalized, and a weighted affix feature vector is generated; syntax dependency relationship analysis and preliminary structure construction are performed on the text to be detected, and a dependency syntax tree of the text to be detected is generated. The application improves the detection accuracy and result interpretability of highly similar languages and mixed code texts by explicitly modeling and quantitatively evaluating deep morphological-syntactic rule features of languages.

A grammatical error correction method incorporating component syntactic information belongs to the field of artificial intelligence technology. It includes: extracting component syntactic information from a given statement; using the erroneous statement, its corresponding correct statement, and the component syntactic information as input data; and constructing a multi-task grammatical error correction model that integrates component syntactic information to correct the erroneous statement. This method first extracts component syntactic information from the statement using grammatical analysis, serializes the statement's component syntactic tree to obtain a component syntactic sequence, and constructs triplet pairs as input data. Second, an adapter module is introduced to construct a multi-head attention mechanism model based on multi-task learning, learning the potential relationships between erroneous and correct statements, and between erroneous statements and component syntactic sequences. Finally, through pre-training and lightweight fine-tuning of the adapter module, the features of the erroneous statement, the correct statement, and the component syntactic sequence are fused to complete the grammatical error correction.

The present application relates to the technical field of natural language processing, and provides a translation method and device, electronic equipment and a storage medium, wherein the method comprises: determining to-be-translated data and a scene label corresponding to the to-be-translated data; performing dependency syntax analysis on the to-be-translated data to obtain syntax tree data representing the grammatical dependency relationship between words in the to-be-translated data; and translating the to-be-translated data based on the scene label and the syntax tree data to obtain target translation data corresponding to the to-be-translated data, which not only effectively solves the problems of part-of-speech misjudgment of polysemous words and structural confusion in translation from an agglutinative language to a fusional language, but also takes into account the grammatical accuracy of the language structure and the business professionalism of the specific field expression, greatly improving the translation accuracy and the final text quality of machine translation in the vertical field and complex conversational scenarios.

The embodiment of the application belongs to the field of artificial intelligence, and relates to a text abstract generation method based on semantic blocks, comprising the following steps: obtaining sample data, performing component syntax analysis on the sample data to obtain a syntax tree, determining semantic blocks according to the syntax tree, inputting the semantic blocks into a pre-constructed initial text abstract model, encoding the semantic blocks to obtain semantic block codes, performing weighted calculation on the semantic block codes to obtain semantic block sequence vectors, performing attention mechanism calculation on the semantic block sequence vectors to obtain semantic block relationship vectors, inputting the semantic block relationship vectors into a CRF layer for training, outputting a predicted classification result, calculating a loss function, adjusting model parameters of the initial abstract generation model based on the loss function, ending iteration, generating a text abstract model, inputting a text to be processed into the text abstract model, and outputting a text abstract. The application also provides a text abstract generation device based on semantic blocks, equipment and a storage medium. The application can make the abstract more concise and refined.

The invention relates to the technical field of artificial intelligence and data analysis, and particularly provides a self-learning data analysis model recommendation method and system based on domain adaptation, and the method comprises the steps: dividing an input text into atomic analysis units through employing a syntactic tree analysis and paragraph topic clustering algorithm, pre-labeling entities in the atomic analysis unit based on a domain dictionary and a rule engine; according to the atomic analysis unit, outputting an analysis model recommendation result by adopting a semantic word segmentation optimization method, a multi-granularity retrieval matching method and a double-weight calculation sorting method; representing an association relationship between entities in the analysis model recommendation result based on an entity association graph; and performing structure updating on the entity association graph based on the user interaction behavior. According to the method, the text analysis accuracy, the semantic understanding depth, the recommendation precision and the dynamic updating capability of the knowledge base are remarkably improved, an efficient, accurate and self-adaptive solution is provided for data analysis in the vertical fields of medical treatment, finance, education and the like, and the method has important value and wide application prospects.

This invention relates to a multilingual syntax tree generation method based on multi-source syntax guidance and large-scale model collaborative optimization, belonging to the field of natural language processing. The method first generates a dependency syntax tree from the source language text using a traditional syntax analyzer, and performs quality assessment based on the reliability of the root node and dependency relations. For structures with low scores, the Qwen3-8B model is introduced for preliminary correction to improve the quality of the source tree. Subsequently, the segmented target language text and the quality-aligned source language syntax structure are used together as input prompts to guide multiple large-scale models to collaboratively generate the target language syntax tree, achieving cross-language syntax structure transfer. Finally, through consistency integration, rule compliance verification, and format standardization steps, high-quality, uniformly formatted pseudo-syntax tree data is generated. This invention can significantly improve the accuracy of low-resource language syntax analysis and the effectiveness and reliability of data generation standardization in low-resource dependency analysis tasks.

The application provides a sentiment element extraction method and system based on syntax-aware candidate matching, which specifically comprises the following steps: performing syntax analysis on input text to obtain a syntax tree to extract part-of-speech tags and phrase structures; extracting a candidate attribute word set from the syntax tree based on a preset attribute part-of-speech pattern, retrieving attribute sample examples from an example library according to text syntax vector representations corresponding to candidate attribute word phrase structures, and using the attribute sample examples to guide a plurality of large language models to generate reliable triplets; extracting a candidate opinion word set from the syntax tree based on a preset opinion part-of-speech pattern, retrieving opinion sample examples from the example library according to text syntax vector representations corresponding to candidate opinion word phrase structures, and using the opinion sample examples to guide the plurality of large language models to generate reliable quadruplets; and fusing the reliable triplets and the reliable quadruplets to obtain a sentiment element extraction result.

The method for mapping a noun phrase to a description logic concept based on epitaxy firstly exhaustively lists all text segments of the noun phrase, generates a mapping table of the text segments to resources in a knowledge base; then generates an analysis sequence according to the word segmentation, part-of-speech tagging and syntax tree of the noun phrase; and finally, according to the analysis sequence, continuously refines basic concepts generated by the indexed resources from the concept of EL++, until all words are analyzed, to obtain the description logic concept to which the noun phrase is mapped. The application can automatically process complex noun phrases containing implicit relations and generate high-quality description logic concepts through analysis of the syntax tree.

The invention relates to the field of financial science and technology, in particular to the field of artificial intelligence, and particularly relates to a question separation method, device and equipment and a storage medium. The method comprises the steps that target phrases are traversed and matched in a domain knowledge tree to determine knowledge leaf node weights corresponding to the target phrases; in response to the fact that the number of the knowledge leaf node weights is at least two and the ratio of the maximum knowledge leaf node weight to the minimum knowledge leaf node weight is in a preset ratio range, matching the target word group in the syntactic tree to determine a syntactic leaf node weight corresponding to the target word group; responding to the condition that the number of the syntax leaf node weights is at least two and the ratio of the maximum syntax leaf node weight to the minimum syntax leaf node weight is in a preset ratio range, determining that at least two single questions exist in the customer questions; syntactic matching nodes obtained by matching the target phrases in the syntactic tree are determined, and client questions are separated based on the syntactic matching nodes to obtain single questions. The method and the device are convenient for improving the answering accuracy of the customer questions.

This invention relates to the field of character recognition and grammatical analysis technology, and discloses an automatic proofreading and error correction system for electronic publications based on artificial intelligence. The system includes: a data acquisition module for acquiring a sequence stream of text to be proofread; a syntactic parsing module for constructing a dependency syntax tree and identifying multi-level nested clauses; a structure processing module for generating feature projection vectors using feature space projection mapping when the syntactic nesting depth exceeds a threshold, thereby compensating for semantic features and maintaining logical closure; a verification module for determining the structural deviation index between the local syntactic matrix and the global semantic vector; and an error correction decision module for outputting error correction signals. This invention utilizes a feature projection compensation mechanism to fill in semantic gaps caused by local truncation, ensures the connectivity of long-range grammatical dependencies, eliminates false positives caused by loss of contextual information, and effectively enhances the system's parsing accuracy for ultra-long and complex sentences.

The invention discloses a multi-feature fusion ancient language named entity recognition method based on a large language model. The method comprises the following steps: extracting sentence semantic vectors by utilizing a pre-trained ancient language model GuwenBERT; sanza is adopted for dependency syntactic analysis, and structural features such as subject-called dependency, centering dependency and syntactic tree depth are extracted; the semantic features and the structural features are spliced to form fusion representation, and a similarity index is constructed based on FAISS to retrieve a small number of annotation examples; a large language model is guided to complete clue recognition, reasoning judgment and entity labeling in sequence through structured reasoning Prompt, and automatic recognition of personal names, place names, official names and time names in ancient texts is achieved. According to the method, the accuracy and robustness of ancient language named entity recognition are remarkably improved under the small sample condition, and an efficient technical scheme is provided for ancient book digitization and knowledge graph construction.

The application discloses a Tibetan verb valence information extraction method based on a dependency syntax tree library, relates to the cross technical field of computational linguistics and natural language processing, and comprises the following steps: acquiring a Tibetan raw corpus; the source of the Tibetan raw corpus comprises literature, news, history, novels, teaching materials and a cloud Tibetan brat syntax tree library tool; preprocessing the Tibetan raw corpus to generate a dependency syntax tree library; analyzing the dependency syntax tree library to determine automatic verb valence information extraction rules; the automatic verb valence information extraction rules comprise zero-valence verb extraction rules, one-valence verb extraction rules, two-valence verb extraction rules and three-valence verb extraction rules; acquiring a Tibetan sentence to be extracted for verb valence information, and executing the automatic verb valence information extraction rules to obtain Tibetan verb valence information in the Tibetan sentence. The method improves the generation accuracy of Tibetan verb valence information.

The present application relates to the technical field of instruction analysis, in particular to a multi-stage alarm adaptive control method based on operation instruction analysis rules, comprising: constructing a dependency syntax tree and extracting instruction semantic triples by using a natural language processing model; mapping the triples to a semantic constraint graph to extract safety numerical boundaries, and dynamically correcting in combination with real-time environmental conditions; generating an instruction risk index by comprehensively considering parameter overrun and semantic deficiency probability, and triggering a hierarchical adaptive control according to the matched threshold value. The present application breaks the dependence of traditional industrial control on rigid protocols by constructing a multi-dimensional heterogeneous graph and a deep semantic analysis model, enhances the inclusiveness of non-standard instructions, and uses the risk vector module length to dimensionally evaluate the instruction risk, thereby realizing a multi-stage control strategy from intelligent semantic completion to interactive error correction guidance.

Provided is a system control planning-execution monitoring architecture, including a planning domain portal configured to analyze planning domain related files received from a user and specify a planning domain; a planning problem portal configured to analyze planning problem related files received from the user the user and specify a planning problem therefrom and a planner module configured to receive outputs from the planning domain portal and the planning problem portal and output a plan including a list of actions for completion by the system. The system also produces an active language (ALA) program responsive to the plan output from the planner including embedded monitoring checkpoints. A syntactic analysis module is configured to receive as an input the ALA program and definition of a syntax of the ALA program and produce an abstract syntax tree (AST) therefrom; and an executive module configured to (i) receive an input from the planning domain portal, (ii) determine how components of ALA should be executed based on the received planning domain input in the components of the ALA.