56 results about "Dependency structure" patented technology

A method or module for creating an Language Neutral Syntax (LNS) representation of a sentence from a language particular syntax representation such as found in the Penn Treebank for use by different applications. The method or module includes a node generator configured to create hierarchical and dependent nodes using phrasal and constituent nodes of the language particular syntax. A node dependency generator is configured to create an unordered hierarchical dependency structure for the hierarchical and dependent nodes using a semantic relation between the hierarchical and dependent nodes derived from the language particular syntax.

The present invention provides a high-precision syntactic structure analysis method to contribute to promotion of precise language processing technique. A monolingual document and a document translated from the monolingual document are input. If a plurality of analysis results occurs and is difficult to identify in the syntactic structure analysis in the monolingual document, such as a dependency structure analysis, a dependency structure is examined in the translation document, and an optimum dependency structure analysis is performed based on the examination result.

In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.

The invention discloses a text orientation analysis method which comprises the following steps of: preprocessing a review text; identifying a dependency relation structure of the Chinese syntax; calculating content polarity values of sentiment words; completing two-tuples extraction of evaluated objects and evaluation words and determining a slave relation between the evaluated objects; weighting and summing orientation values of the sentiment words to obtain an orientation value of a sentence so as to implement discrimination on orientation of a sentence level; discriminating appraising orientation of sentiment in the review by positive and negative polarity values of the sentence level; and according to the size of a polarity absolute value, discriminating intensity of appraising sentiment in the review. A product review orientation discriminator comprises an acquisition module, a preprocessing module, a syntactic analysis module, a sentiment calculating engine, a two-tuples mining engine, a content controller and a sentiment discriminator. According to the invention, a combined sentiment dictionary is combined and a domain ontology is added into text orientation analysis; accuracy of polarity calculation of the sentiment words and (the evaluated objects and the evaluation words) two-tuples extraction is improved; and orientation analysis on product reviews in a forum is implemented.

The present invention relates to systems, apparatus, and methods of using usage data to determine the dependency structures of a web application, including dependency structures between follow-on objects of an initial object in a web transaction. In one embodiment, an input URL and associated dynamic response data are analyzed for such nested or dependent relationships. In further embodiments, analysis of these relationships are used to improve prefetching operations to lower overall page load times.

An apparatus and method for deleting objects from an object-relational system in a customizable and database independent manner. The apparatus and method provide a customizable and database independent mechanism for the deletion of object data from a relational database. The method implemented by the apparatus determines the dependency structure of a relational database using database metadata. The dependency structure is then utilized to determine the type of deletion to be performed on data representations of the object and its related objects, i.e., parent or child objects. The deletion actions include cascade deletion and nullify columns deletion. Appropriate SQL statements are then automatically generated at run-time to perform the deletion of the object data from the relational database.

A method of aligning nodes of dependency structures obtained from a bilingual corpus includes a two-phase approach wherein a first phase comprises associating nodes of the dependency structures to form tentative correspondences. The nodes of the dependency structures are then aligned as a function of the tentative correspondences and structural considerations. Mappings are obtained from the aligned dependency structures. The mappings can be expanded with varying types and amounts of local context in order that a more fluent translation can be obtained when translation is performed.

The invention discloses a relation extraction method based on combination of an attention mechanism and a graph long-short-term memory neural network. The method comprises the following steps of extracting context information in sentences through BiLSTM, and entity position information and entity label information are introduced to expand word vector features; extracting the sentence dependency structure tree through a Stanford Parser tool to generate an initial sentence structure matrix, and introducing an attention mechanism to perform attention calculation on the initial sentence structurematrix to obtain weight information of the structure matrix in the sentence; and taking the extracted sentence context information and the weight information of the sentence structure as input, and performing relationship extraction on the input by using a relationship extraction model based on the combination of an attention mechanism and a graph long-short-term memory neural network to finally obtain triple information of an entity. According to the method, evaluation is carried out on a TACRED data junction and a Semeval2010 task8 data set respectively, and the performance of the model is superior to that of an existing mainstream deep learning extraction model.

The invention provides a method and a device for calculating text similarity and realizing search processing achieved through a computer. The method comprises the following steps: acquiring a first text cluster and a second cluster; decoding the first text cluster according to a preset phrase translation model and a dependency structure model to obtain K translation text clusters; respectively calculating a first semantic similarity value between the K translation text clusters and the second text cluster, and calculating a second semantic similarity value between the first text cluster and the second text cluster according to the K calculated semantic similarity values. By adopting the method and the device, the problem of long distance dependency relationship in sentences is solved, the semantics of searched sentences can be relatively well expressed, the searched sentences can be relatively well matched with webpage titles, and a user can obtain semantic matching search result items, so that the search experience of the user is improved.

The present invention deals with noisy data not by eliminating low frequency dependency structures, but rather by weighting the dependency structures. The dependency structures are weighted to give less weight to dependency structures which are more likely incorrect and to give more weight to dependency structures which are more likely correct.

The invention relates to a strength enhanced type low angle dependency structure color material and a preparation method thereof, in particular to a preparation method of the strength enhanced type low angle dependency structure color material, and belongs to the preparation field of color generation materials. The strength enhanced type low angle dependency structure color material consists of aninverse opal photonic crystal and an elastomer filled in protein structure gaps of the inverse opal photonic crystal, wherein the elastomer comprises polydimethylsiloxane, polyurethane, polysulfide rubber and polybutadiene rubber. The method is low in cost, simple and practicable, provides more possibilities for structure color materials in actual application, and especially has wide applicationprospects in the coloring field of building and packaging materials.

A method is provided for managing, in a computer system, design of a database system having a set of schemata. The method includes, in a first computer process, extracting dependencies from the database system and identifying the set of schemata. The method further includes, for each specific schema in the set of schemata, creating in a second computer process a partition that, in turn, contains a further partition for each element of the specific schema, so as to establish a hierarchy of partitions in accordance with the structure of the set of schemata. The method also includes storing a representation of the database system including subsystems, dependency relationships among the subsystems, and the hierarchy of partitions. Finally, the method includes providing a graphical output from the computer system, based on the stored representation, in which appears a display of the subsystems in a hierarchy of partitions within a dependency structure matrix, such matrix graphically indicating the dependency relationships among subsystems. Related apparatus and computer products are also provided.

A method (which can be computer implemented) for processing a plurality of adjacent rows of data units, using a plurality of parallel processors, given (i) a predetermined processing order, and (ii) a specified inter-row dependency structure, includes the steps of determining starting times for each individual one of the processors, and maintaining synchronization across the processors, while ensuring that the dependency structure is not violated. Not all the starting times are the same, and a sum of absolute differences between (i) starting times of any given processor, and (ii) that one of the processors having an earliest starting time, is minimized.

This invention provides a language processing apparatus analyzing a dependency structure of an input sentence, including: a segment unit model parameter estimating part estimating a segment unit model parameter as a parameter of a probability model to analyze the dependency structure by using a feature in a unit of segment; a sentence unit model parameter estimating part estimating a sentence unit model parameter as a parameter of a probability model to analyze the dependency structure by using a feature in a unit of sentence; a dynamic sample generating part generating a sample of the dependency structure of the input sentence from the probability model characterized by the sentence unit model parameter and the segment unit model parameter; and a dependency structure determining part determining a suitable dependency structure from the sample of the dependency structure of the input sentence generated by the dynamic sample generating part.

Disclosure relates to a statistical machine translation field, and more particularly to a method and a device for filtering a translation rule and generating a target word in a hierarchical phrase-based statistical machine translation. The method and device filters a translation rule using a relaxed-well-formed dependency structure and generates a target word by referring to a head word of a source word in a hierarchical phrase-based statistical machine translation. The disclosure improves a translation performance while reducing a number of translation rules, in comparison with a hierarchical phrase-based original translation rule table.

An apparatus and method for calculating a score of matching a sentence with a query pattern having a dependency structure. The apparatus includes: an input unit acquiring an analysis target sentence, a query pattern and an index value indexing how a linguistic unit in the sentence tends to modify another; and a score calculation unit calculating a matching score indexing the degree of matching of the sentence with the query pattern. The matching score is represented by a function having an index value with which a dependency relation included in the query pattern is associated. The score is calculated by attempting association between a substructure of the query pattern and a range in the sentence and by performing recursive calculation in the substructure and the range while storing partial calculation result of the function in a memory area for reuse.

The invention discloses a science and technology project text semantic extraction and representation analysis method, which comprises the following steps: S1, outputting a natural language text consistent with input semantics according to the semantics of structured representation; s2, recombining continuous word sequences into word sequences for the natural language text by adopting a word segmentation algorithm to form a to-be-processed text; s3, analyzing semantic association among language units of sentences in the to-be-processed text, and presenting the semantic association in a dependency structure; and S4, training the corpus by using a supervised or unsupervised machine learning method to obtain a classification model for classifying documents of unknown categories to obtain one or more predefined category labels. According to the invention, science and technology project approval review work is more efficient and intelligent.

An apparatus for analyzing Chinese according to one aspect of the present invention includes a dependency structure analyzer analyzing a dependency relationship between words by extracting a parent word being a dependency destination of each of the words and a child word being a dependent from each of the words. The words are obtained by dividing a Chinese sentence. The apparatus also includes a lihe-word processor referring to lihe-word information that includes a first word and capable of being a part of a lihe-word and a second word forming the lihe-word with the first word. The lihe-word processor detects the first word and the second word from the words analyzed, and then changes a dependency destination of a word depending on both the first word and the second word to the lihe-word formed by combining the first word with the second word.

A method is provided for managing, in a computer system, design of a database system having a set of schemata. The method includes, in a first computer process, extracting dependencies from the database system and identifying the set of schemata. The method further includes, for each specific schema in the set of schemata, creating in a second computer process a partition that, in turn, contains a further partition for each element of the specific schema, so as to establish a hierarchy of partitions in accordance with the structure of the set of schemata. The method also includes storing a representation of the database system including subsystems, dependency relationships among the subsystems, and the hierarchy of partitions. Finally, the method includes providing a graphical output from the computer system, based on the stored representation, in which appears a display of the subsystems in a hierarchy of partitions within a dependency structure matrix, such matrix graphically indicating the dependency relationships among subsystems. Related apparatus and computer products are also provided.

A computer-implemented machine translation system translates text from a first language to a second language. The system includes a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language. A module receives input text in a first language and outputs output text in a second language based on accessing the plurality of mappings.

The invention discloses a trigger word determination method, which comprises the following steps of identifying a target entity pair in a target text sentence, the target entity pair comprising a first entity and a second entity; if the distance between the first entity and the second entity is greater than or equal to a preset threshold value, or if the distance between the first entity and the second entity is less than the preset threshold value and the first entity and the second entity do not contain mesons, constructing a dependency relationship structure diagram of the target text sentence; determining the association rules of the corresponding nodes in the dependency relationship structure diagram; calculating a target comprehensive importance score of each node relative to the target entity pair according to the corresponding association rules; and determining a trigger word in the target text sentence according to the target comprehensive importance score. According to the method, in the determination process of the trigger word, dependence on a dictionary is not needed, the limitation of the application field is avoided, and the transportability is strong.

Systems and methods are provided for identifying combinatorial feature interactions, including capturing statistical dependencies between categorical variables, with the statistical dependencies being stored in a computer readable storage medium. A model is selected based on the statistical dependencies using a neighborhood estimation strategy, with the neighborhood estimation strategy including generating sets of arbitrarily high-order feature interactions using at least one rule forest and optimizing one or more likelihood functions. A damped mean-field approach is applied to the model to obtain parameters of a Markov random field (MRF); a sparse high-order semi-restricted MRF is produced by adding a hidden layer to the MRF; indirect long-range dependencies between feature groups are modeled using the sparse high-order semi-restricted MRF; and a combinatorial dependency structure between variables is output.

The invention discloses an international Chinese-teaching oriented grammar point identification method, and relates to the technical field of Chinese grammar point identification. The method comprises the following steps: determining a grammar knowledge base according to a grammatical syllabus, supplementing and perfecting the grammar knowledge base in combination with the annotation analysis on the international Chinese teaching material, and actually selecting to-be-identified grammar points facing to the teaching; and automatically identifying the grammar points in a to be analyzed text through a regex match technology. Without consideration of automatic syntax analysis method based on a phrase structure and a dependency structure, the method disclosed by the invention comprises constructing a matched resource based on the teaching practice, and using the practical tool to finally realize the automatic identification of the grammar point facing the international Chinese teaching, thereby achieving the target of meeting the grammar point identification requirement in the international Chinese teaching.

The invention relates to a Chinese structured event extraction method, and belongs to the technical field of information extraction. The Chinese structured event extraction method comprises the following steps of: performing syntactic dependency structure analysis on an unstructured text statement by using a syntactic dependency analysis tool to obtain a syntactic dependency analysis tree; analyzing the characteristics of the Chinese linguistic and syntactic dependency analysis tree, constructing a core verb chain, and identifying all events existing in the statement; adding a semantic dependency relationship to the syntactic dependency analysis tree by means of a semantic dependency analysis tool, and constructing a syntactic semantic dependency analysis tree; adjusting dependency structures of event core verbs, prepositions and passive language states in the syntactic semantic dependency analysis tree, and constructing a syntactic semantic dependency analysis event graph. According to the method, data does not need to be manually annotated, the structured event can be well extracted, and the extraction accuracy and recall rate are high.

The invention provides an open event extraction method and system based on a multi-channel hierarchical graph attention network, and the method comprises the steps: obtaining a given document, and building a document syntax dependency tree according to the given document; the method comprises the following steps: based on a document syntax dependency tree, sequentially adjusting a dependency structure, associating default components, adding a sequence sequence and associating ancestor nodes and descendant nodes to construct a bidirectional dependency graph; based on the original graph attention network, node types are embedded and hierarchical adjustment is carried out so as to modify the feature convergence process of the original graph attention network, and then a hierarchical graph attention network is constructed; constructing to obtain a three-channel graph attention network; and inputting words in a given document into the three-channel graph attention network to update the embedded representation, and performing four-classification judgment through the full-connection network to realize extraction of the open event. The feature coding capability of the graph structure can be effectively enhanced.

The invention discloses a man-machine collaborative construction method for a domain term semantic knowledge base. The method comprises the following steps: based on a HowNet semantic theory system, four key processes are collaboratively constructed according to the characteristics of terms and comprises term internal dependency structure analysis, term internal word meaning item auxiliary selection, term internal dynamic role relation auxiliary judgment and term DEF generation. According to the term internal dynamic role relation auxiliary judgment method, three judgment methods are provided,and the three judgment methods are a maximum entropy classifier and similarity-based method combination, a KNN classification method based on first-meaning original pre-selection and an active learning method based on KNN. According to the method, a domain term semantic knowledge base is constructed from the term semantic level according to the thought from bottom to top, and the relation type between terms in terms is judged from the semantic level and the statistical level; under the condition that the training corpus is not sufficient, the model can still obtain a good effect.