9 results about "Dependency grammar" patented technology

This invention belongs to the field of computer vision technology, specifically a tree-structured video description generation method based on perceptual grammar knowledge. This invention explicitly utilizes semantic information inherent in language, using dependency structure analysis tools to transform sequential sentences into a syntax tree structure. By analyzing the connections between parent and child nodes in the tree, the dependency grammar structure within the sentence is explicitly modeled. A perceptual context attention network is used to model the contextual information generated along different paths during the generation process. Simultaneously, reinforcement learning and iterative generation training methods are introduced during the training phase to further improve model performance. Qualitative and quantitative experiments demonstrate that the model has the ability to generate more accurate and semantically richer descriptions.

The invention relates to a Chinese cross-language dependency syntactic analysis method based on an information screening network, and belongs to the field of natural language processing. The method comprises the following steps: firstly, extracting word embedding expressions of Chinese and Vietnamese sentences by utilizing a cross-language pre-training model XLM-RoBERTa; secondly, encoding the two languages by using independent and private BiLSTM (Bidirectional Long Short Term Memory); then inputting feature information of the BiLSTM of the source language and the BiLSTM of the target language into an information screening network, wherein the network dynamically learns matching weights among specific expressions of different languages; secondly, using MLPs to reduce the dimension of the feature to obtain the syntactic relationship representation and the part-of-speech tag representation of each word; and finally, decoding by using a double-affine decoder, and searching for an optimal dependency syntax tree at the same time. According to the method, the matching weight information of different languages is dynamically learned, so that the source language information is effectively screened and utilized, and a remarkable effect is achieved in an experiment.

The present application discloses a retrospective verification method, device, and electronic device for NOTAM parsing results, relating to the field of artificial intelligence. The method comprises: obtaining the parsing results of the NOTAM by the target system; determining the key information of the NOTAM from the parsing results through an inverse model, and reconstructing and generating the target NOTAM based on the key information; detecting the similarity between the target NOTAM and the NOTAM; performing dependency grammar analysis on the target NOTAM and the NOTAM to obtain an analysis result, wherein the dependency grammar analysis is used to analyze the word dependency relationship and grammatical role relationship between the target NOTAM and the NOTAM; and determining the parsing accuracy of the NOTAM by the target system based on the similarity and analysis result. The present application solves the technical problem that the prior art mainly uses expert rules to verify the NOTAM parsing results, resulting in low verification efficiency of the NOTAM parsing results, thereby affecting aviation safety.

The present invention belongs to the field of document-level event extraction and provides a document-level event extraction method and system based on a hypergraph neural network. The method comprises obtaining document text data; extracting document-level events using a trained document-level joint extraction model based on the document text data; and designing an improved affine graph parser to enable the model to more fully capture grammatical dependency information and longer-range dependency grammatical information for local feature extraction. Furthermore, a hypergraph convolutional network is introduced for global feature extraction, while sentence and word association matrices are constructed. An effective fusion mechanism for local features and the association matrix is ​​designed to enhance the feature extraction capabilities of the hypergraph convolutional network.

The present application discloses a text processing detection method, apparatus, device, and computer storage medium. The method includes: obtaining a first text; determining a target text segment including a quantifier from the first text; performing dependency grammar analysis on multiple words in the target text segment according to the parts of speech of the multiple words in the target text segment to obtain a first dependency grammar relationship between each word in the target text segment; constructing a dependency grammar relationship tree according to the first dependency grammar relationship; determining at least one target dependency grammar relationship structure that matches a preset dependency grammar relationship structure from the dependency grammar relationship tree; and determining a target semantic relationship structure corresponding to the at least one target dependency grammar relationship structure according to the one-to-one correspondence between the preset dependency grammar relationship structure and the preset semantic relationship structure. By using the text processing method, apparatus, device, and computer storage medium provided by the present application, the semantic relationship between a quantifier and other words can be accurately determined.

The present invention belongs to the field of natural language processing, and provides a query statement semantic tree generation encoding method and system, obtains a given query statement, and classifies it according to the completeness of the query statement; for the incomplete query statement, uses the process completion large language model to complete the query process based on the guidance of the thinking chain; based on the complete query statement or the completed query statement, extracts the deep semantic association between adjacent words through the component analysis tree, extracts the long-distance association of non-adjacent words through the dependency syntax tree, and fuses the dependency syntax tree and the component analysis tree to form a final semantic tree. The present invention classifies the query statement by completeness, and then uses the large language model to automatically infer and improve the query statement, thereby generating a semantic tree that can accurately reflect the intermediate process of the action, realizes the supplement of key semantic content, and can support accurate action retrieval and positioning in open scene videos.

The application discloses a text similarity determination method, device and equipment and a storage medium. The method comprises the following steps: obtaining a plurality of texts to be processed, performing word segmentation processing on each text to obtain a plurality of word segmentation results corresponding to each text respectively; determining CoNLL format data corresponding to each word segmentation result, and constructing a dependency grammar tree corresponding to each text according to the CoNLL format data corresponding to each text respectively; generating a dependency matrix matched with each text according to the dependency grammar tree corresponding to each text respectively, and determining a target similarity between the plurality of texts according to the dependency matrices. The technical scheme of the embodiment of the application can reduce the complexity of the text similarity determination method and improve the accuracy of the text similarity determination result.

The present invention relates to a machine translation testing method. The method constructs a dependency syntax tree for a sentence, prunes the syntax tree according to specific rules, destroys the validity of the sentence based on a set of dependency syntax tree-level deletion operators, deletes words or phrases from the original sentence to generate a new grammatically and semantically valid sentence, then inputs the original text and the newly generated sentence into the machine translation system being tested, calculates the bag-of-words distance, sorts and expands the sentences according to the bag-of-words distance, selects the five sentences with the largest distance, manually labels the original sentence and the translated sentence results, marks the erroneous sentences, and completes the test of the machine translation system. The purpose of the present invention is to solve the problem that current machine translation testing mainly generates test cases by replacing some words in the sentence, and the test performance is mainly limited by the maturity of the language model used. While amplifying the data, the invariance of the basic structure of the sentence is guaranteed, thereby discovering more errors, many of which could not be discovered by previous machine translation testing technologies.

The application discloses a rule and dependency grammar-based spatiotemporal correlation degree calculation method, which comprises the following steps: obtaining an open field text sequence, and preprocessing the text sequence to obtain a preprocessed text sequence; performing syntactic analysis on the preprocessed text sequence, formulating a rule matching table, and matching the syntactic analysis result according to the rule matching table to obtain candidate triplets and spatiotemporal information; calculating a spatiotemporal correlation degree value according to a dependency path of a relation predicate in the candidate triplets and the spatiotemporal information, a dependency distance of a head entity and the spatiotemporal information, a spatiotemporal feature of head and tail entity types, and a spatiotemporal semantic feature of the relation predicate; defining two threshold values, comparing the spatiotemporal correlation degree value with the two threshold values, determining a classification result of the spatiotemporal correlation degree, and generating a knowledge expression model. The application accurately calculates spatiotemporal correlation by comprehensively considering the context and spatiotemporal information of the text, thereby obtaining a spatiotemporal knowledge expression model and more accurately conveying the semantics of the text.