6 results about "Thematic relation" patented technology

The invention belongs to the technical field of natural language processing, and discloses an information density calculation method and an application system thereof, and the system comprises a semantic unit extraction module, a multi-attribute filling module, an information density scoring module, a density distribution modeling module and a downstream application interface module. The semantic unit extraction module identifies subject-object structures, proper noun combinations and verb-object phrases from an original text through fusion word segmentation, syntactic dependency analysis and semantic role labeling, and outputs a structured semantic unit list in combination with unified term expression of a domain dictionary and a concept ontology. The invention provides a new method for modeling information density from a semantic structure level, which is different from a word frequency statistics or black box probability method, emphasizes structure interpretability, attribute combinability and application suitability, is especially suitable for scenes such as intelligent abstracts, document compression, semantic annotation, knowledge graph construction and the like, and has a wide application prospect. And the method has definite novelty, practicability and generalizability.

The application provides a sentence comparison method and device and related products, which can improve the efficiency of sentence comparison. The above method can be applied to a sentence comparison device, which is configured with a first word similarity table including the similarity of a plurality of words. In a specific implementation, the sentence comparison device obtains a first sentence and a second sentence to be compared, then compares the semantic role information of the words in the above two sentences to determine the mapping relationship between the words in the above two sentences, wherein the semantic role of the word is used to describe the semantic function of the word in the sentence, the words with the mapping relationship include the words with matching semantic role information, then the first word similarity table is queried to obtain the similarity between the above words with the mapping relationship, and then the similarity between the above words with the mapping relationship is used to determine the similarity of the first sentence and the second sentence, and finally the sentence comparison result is obtained.

The application relates to a semantic role labeling method fusing a component tree structure, and belongs to the technical field of computer natural language processing. The method is from the data angle, firstly converts the original component tree into a binary tree according to rules, for all semantic relations, the relation of the left and right children of a node in the component tree can be corresponded, thereby the relation between the semantic role and the tree structure is established, and the syntactic information is integrated into the semantic role labeling from the data angle. Meanwhile, the method constructs a component tree label system, firstly converts the component tree into a dependency tree, then finds the corresponding core word under the node by using the dependency relation, thereby labels the direction corresponding to the core word, and meanwhile converts the multi-branch node into a binary. Then, the semantic relation is labeled in the component tree by using the semantic role labeling information, if multiple verbs share the same role, the core word direction is changed into parallel. The method effectively improves the accuracy of the semantic role labeling.

The invention relates to the technical field of natural language processing, and discloses a semantic intelligent analysis method and system for an English text, and the system comprises a data module which is used for comparing an analyzed grammar with a database, mining the meaning of each sentence segment of the text, carrying out the role marking of the semantics, completing the scene simulation of the dialogue of the sentence segment, and obtaining a semantic analysis result; and semantic meanings are further mined. According to the method, multiple advanced semantic analysis technologies are integrated, character and scene simulation is substituted, the tagging sequence is calculated on the basis of part-of-speech and word vectors, features are defined to measure tagging rationality, and weights are calculated for optimization, so that the prediction accuracy of the semantic role tagging standard sequence is remarkably improved; according to the method and the system, the semantic role of each component in the text, such as an executor and a receiver, can be more accurately understood by the system, so that the semantic connotation of the text can be more deeply and accurately mastered, and compared with the prior art, the semantic understanding depth and precision are remarkably improved.

This invention discloses a large-scale model-based answer analysis and management method and system, relating to the field of answer analysis technology. The large-scale model-based answer analysis and management system includes an answer analysis module and an answer review module. This invention constructs an answer-based spoken language mapping knowledge graph and combines it with the semantic role labeling capabilities of the large-scale model to achieve a mapping from surface text to deep semantic structures. This effectively solves the problems of non-standard and colloquial expressions in subjective answers, improving the system's understanding and tolerance for non-standard expressions. By introducing construction logic deduction paths from the expert question bank, non-standard answer words are decoupled into implicit practical action features and expected process purpose features. Similarity comparison is then performed based on engineering utility, elevating the judgment of answer results from keyword matching to engineering logic consistency judgment, significantly improving the professionalism and credibility of the judgment results.

The embodiment of the invention discloses a document-level time sequence relation extraction method, which is based on event time argument feature fusion, utilizes a time argument theory in linguistics to guide a model extraction effect, and fuses tenses, postures and time adverbs of sentences as additional information into word embedding expression of event trigger words, so that the time sequence relation extraction efficiency is improved. The method comprises the following steps: capturing a long-distance inter-sentence relationship by using utterance features generated by a rhetorical structure theory analyzer, capturing a dependency relationship between a document structure and words through syntactic analysis, capturing time features by using time parameters in semantic role annotation, and learning and transmitting the features by a convolutional network based on a gated graph. By adopting the technical scheme of the invention, an effect better than that of a baseline is obtained on an event time sequence relation extraction task.