60 results about "Thematic relation" patented technology

Systems and methods are provided for automated semantic role labeling for languages having complex morphology. In one aspect, a method for processing natural language text includes receiving as input a natural language text sentence comprising a sequence of white-space delimited words including inflicted words that are formed of morphemes including a stem and one or more affixes, identifying a target verb as a stem of an inflicted word in the text sentence, grouping morphemes from one or more inflicted words with the same syntactic role into constituents, and predicting a semantic role of a constituent for the target verb.

The invention discloses a query sentence analyzing method based on understanding of natural languages and a system thereof, and belongs to the technical field of information retrieval. The query sentence analyzing method comprises the following steps: (1) automatic segmenting, named entity identification and part-of-speech tagging of an input Chinese query sentence are implemented; (2) syntax structure of the segmented sentence is analyzed so as to obtain a syntax structural tree, and meaning of each word is determined according to the sentence after the part-of-speech tagging; (3) according to the syntax structure and the meaning of each word, semantic roles of predicates in the sentence are tagged; and (4) according to the analyzed result of the sentence from the levels of syntactics, syntax and semantics, keywords are expanded and the keywords that can reflect user information retrieval requirements are extracted. The query sentence analyzing system of the invention comprises a syntactic analyzing module, a syntax analyzing module, a semantic analyzing module and a keyword extracting module. The query sentence analyzing method and system can greatly improve the accuracy of query results and provide desired query results for users.

Document comparisons can be performed at a semantic level by utilizing a rules base in which groups of rules are applied sequentially. In one implementation, (1) syntactic rules are applied to a document to form a tagged sequence in which individual words are tagged with their syntactic categories, (2) ambiguity rules are applied to the tagged sequence to resolve ambiguities, thereby providing a resolved tag sequence, (3) grammar rules are applied to the resolved tagged sequence to determine semantic roles of individual tagged words, thereby providing a role-specific resolved tagged sequence, and (4) property rules are applied to match properties (e.g., adjectives) with the words they modify, thereby providing a semantic feature structure. The semantic feature structure is then compared to at least one other structure.

The invention relates to a multi-granularity semantic chunk based entity attribute and attribute value extracting method, and belongs to the technical field of Web mining and information extraction. The method comprises the following steps that a corpus set is constructed and free text extraction is performed; a corpus is subjected to word segmentation, part-of-speech tagging and phrase recognition; the corpus is subjected to semantic role labeling; the corpus is subjected to dependency grammar analysis; the corpus is subjected to semantic dependency analysis; candidate entities, attributes and attribute value triads based on three granularities of words, phrases and semantic roles are extracted; the candidate entities, attributes and attribute value triads are corrected and subjected to error classification by means of a trained classifier. Compared with the prior art, the entities, attributes and attribute value triads based on three granularities of words, phrases and semantic roles are automatically extracted from a free text, the entity attribute and attribute value extraction accuracy and efficiency are improved, and the wide application prospect is achieved in the fields of theme detection, information retrieval, automatic abstracting, question and answer systems and the like.

The invention provides an event element extraction method and device, computing equipment and a storage medium, and the event element extraction method comprises the steps: obtaining an input text, and determining a relation feature vector of each word in the input text; Obtaining argument of each word in the input text through a semantic role labeling model based on the relation feature vector ofeach word in the input text; Obtaining entity words contained in the input file and types and position information of the entity words through a named entity recognition method; Determining an eventelement type needing to be extracted according to the event type of the input text, and performing element alignment on the words corresponding to the arguments and the entity words based on the typesof the event elements needing to be extracted, the arguments and the types and position information of the entity words, and determining names of the types of the event elements and the correspondingentity words in the input text.

The invention discloses a semantic character labeling method of a natural language sentence, which is characterized in that Chinese syntax analysis and semantic character label are simultaneously realized by adopting a combined learning model. The invention can simultaneously output the syntax analysis result of one sentence and gives the semantic role labeling result of a predicative by using a combined model. Because semantic information is increased in a syntax analysis model in the combined learning model, a model trained is particularly suitable for a semantic role labeling task. Therefore, the semantic role label output by the model has high performance. Meanwhile, the performance between the result output by a single syntax analysis model and the syntax analysis result output by the combined model is not large. Particularly, the syntax analysis performance can also be improved by adding semantic information.

The embodiment of the invention discloses a method and device for labeling a semantic role. The method comprises the steps that at least one classification feature of a participle in an object statement to be labeled is acquired; semantic representation information of the acquired classification features is determined; semantic representation of all the classification features is adopted as input of a pre-generated neural network classifier, and semantic role labeling is carried out on the participle through the neural network classifier. According to the technical scheme, the complex and sparse feature based on a plurality of words, a plurality of word characteristics, a plurality of depending arc signs and a plurality of depending paths can be easily mapped into a dense feature, therefore, the dimension of feature space and feature establishment complexity are lowered, and a plurality of features can be combined automatically.

The invention discloses a semantic role labeling method based on a synergetic neural network, and relates to the fields of semantic role labeling, mode identification and synergetic neural networks, in particular to a method for introducing the principle of the synergetic neural network into shallow semantic analysis. The semantic role labeling method comprises the following steps: extracting characteristics from training language material and testing language material and constructing corresponding semantic characteristic vectors; performing kernel transformation on the semantic characteristic vectors and constructing a prototype pattern and a mode to be tested on the basis; constructing an order parameter and calculating a plurality of candidate roles for each dependent component; constructing a predicate base and combining the candidate roles of all the dependent components corresponding each predicate to get role chains of all the predicates; and optimizing a network parameter, performing dynamic evolution on the synergetic neural network to get an optimal role chain, and outputting the labeling mode. The principle of the synergetic neural network is firstly introduced into the semantic role labeling, and the method can be widely applicable to various natural language processing tasks. The semantic role labeling method has better application prospects and application value.

The present invention provides a method for extracting relationships between words in textual data. Initially, a classifier is trained to identify text data having a specific format, such as situation-response or cause-effect, using a training corpus. The classifier receives input identifying components of the text data having the specified format and then extracts features from the text data having the specified format, such as the part of speech for words in the text data, the semantic role of words within the text data and sentence structure. These extracted features are then applied to text data to identify components of the text data which have the specified format. Rules are then extracted from the text data having the specified format.

A method for creating a predictive model is disclosed herein, including the steps of determining trends and patterns in electronic data, using at least a first machine language algorithm, refining the determination of the algorithm, searching for social models that describe the identified trends and patterns using at least a second machine language algorithm, verifying causal links, constructing at least one model about human node behavior and interactions, utilizing the social models to do at least one of the following: validate hypotheses, predict future behavior, and examine hypothetical scenarios, automatically updating predictions when new data is introduced, using probabilistic techniques to learn hierarchical structure in unstructured text, continuously updating a set of themes, examining grammatical rules of each component of text, matching grammatical constituents to semantic roles, and reorganizing data into clusters of entities with common attributes.

The invention is applicable to the technical field of Internet, and provides a Chinese semantic role labeling method and device, a computer device and a computer readable storage medium, and the method comprises the steps: processing a pre-acquired Chinese corpus of a training set, and obtaining a final representation of words of the training set; processing the pre-acquired Chinese corpus of theverification set to obtain the final representation of the words of the verification set; constructing a sequence labeling model by adopting bidirectional GRU and CRF, setting initial parameters for the sequence labeling model, and optimizing the parameters of the sequence labeling model; and carrying out performance evaluation on the sequence labeling model after parameter optimization through final representation of words of the verification set, taking the sequence labeling model with the performance meeting a preset condition as a target sequence labeling model, and carrying out Chinese semantic role labeling on Chinese corpora in a pre-acquired test set through the model. According to the Chinese semantic role labeling method provided by the invention, the operation of Chinese semantic role labeling can be simplified, and the semantic role labeling efficiency can be improved.

Part-of-speech tagging of a Chinese ambiguity word is one of the major problems influencing performance of a Chinese information processing system currently. The ambiguity word is a grammatical phenomenon of one word with multiple parts of speech existing in Chinese, such as a gerund isomorph. The invention discloses a Chinese ambiguity word processing method based on dependency parsing. The method comprises the following three steps: a sentence containing a large number of ambiguity words is firstly selected to serve as a training language material, and an ambiguity word semantic role statistical rule with high accuracy and coverage is obtained through dependency parsing; then, sentence dividing, word dividing, part-of-speech tagging and dependency parsing pre-treating are carried out on a to-be-processed text, and on the base of a morphology, syntax and context rule bank, parts of speech of ambiguity words in a word dividing result are tagged; and finally, the ambiguity word semantic role statistical rule obtained in advance is adopted, the part of speech of an ambiguity word in a different context environment can be accurately recognized through dependency parsing. The method can effectively improve part-of-speech tagging accuracy in the case of Chinese text processing, and can be widely applied to various Chinese information processing systems.

The invention relates to a statistical machine translation method based on a predicate argument structure (PAS). The statistical machine translation method comprises the following steps of: carrying out word segmentation, automatic word alignment, syntactic analysis and bilingual combined semantic role labeling on bilingual sentences in a bilingual corpora; extracting PAS conversion rules of the bilingual sentences according to results of the bilingual combined semantic role labeling so as to model the relationship between PASs of two languages; matching a plurality of semantic role labeling results of sentences to be translated by using the PAS conversion rules and carrying out corresponding translation; and structuring a translation hypergraph according to results of matching and translation based on the PAS conversion rules to finally generate a translation result.

The invention provides a machine translation evaluation method and equipment and a machine translation method and equipment which are used for a cross-language question and answer system. The machine translation evaluation method comprises the steps that semantic role labeling is conducted on source language query sentences and corresponding target language query sentences obtained through machine translation; the alignment probability of each labeled argument in the source language query sentences and each labeled argument in the target language query sentences is calculated; the translation quality of the target language query sentences is determined on the basis of all the calculated alignment probabilities. According to the method, a novel machine translation evaluation scheme which utilizes semantic role labeling and is based on the argument alignment probabilities is provided; by means of the method, accurate machine translation evaluation can be provided, and then the performance of the cross-language question and answer system is improved.

The invention relates to a system and a method for acquiring characteristics favorable for text retrieval. By using the system and the method, a user can acquire the characteristics which are related to personal retrieval requirements and are favorable for retrieval, such as a key word, a sequence, a grammatical pattern, a semantic role and the like. By means of the characteristics, the user can construct more effective query so as to improve the efficiency of searching documents; on the other hand, the invention also relates to a system and a method for evaluating the value of things related with an input text, wherein the user can acquire the evaluation of various things related with the input text by submitting the input text; simultaneously. The invention also relates to a system and a method for evaluating career advantages according to a resume of a person at the same time, which provide career advantage grade of various skills and experiences related to the resume of the person by means of a job notice library and / or a resume library; and the invention also relates to a system and a method for document retrieval by using a text as a query input, which can quickly shrink a retrieval range and avoid losing a search result with potential value.

The invention relates to a method of processing minority characters into Chinese language, and in particular relates to a united labeling method for syntax of Tibet language and semantic roles. The united labeling method comprises the following steps of: a) distinguishing a simple sentence and a compound sentence; b) labeling semantic roles; c) recognizing a predicate; d) classifying verb semantics; e) labeling a syntactic structure; f) editing and revising semantic role labeling results. According to the united labeling method, the syntax of Tibet language and semantic features are extracted, on the one hand, semantic role information such as a performer, a receiver, time, a place and a way expressed in the sentence can be labeled by directly utilizing grammatical labels of the Tibet language; on the other hand, a syntax analytical process can be reacted upon by the predicate semantic role labeling result so that the influence of the syntax labeling which is not well-determined can be reduced, and accordingly the performance of a sentence processing system can be improved.

The invention provides a person relation analyzing method as well as a method and a device for providing person information. The method comprises the following steps: abstracting a plurality of sentences in content data related to a person; conducting interdependency analysis on the sentences respectively to generate a plurality of interdependency analysis trees; conducting semantic character tagging on the sentences respectively according to the interdependency analysis trees to generate a plurality of semantic character tagging results; generating a person time and space relation chart according to the semantic character tagging results; generating a person relation knowledge base of the interest person according to the person time and space relation chart. The person relation knowledge base related to the person is acquired accurately by conducting interdependency analysis and semantic character tagging on the person content data; abundant and accurate person relation information is provided for a user.

Methods and apparatus are described for facilitating discovery of information of interest in a document collection. A document model is proposed in which important terms and their semantic roles are represented. This document model is then used to facilitate searching and / or browsing of the document collection.

The invention provides an atlas construction method and device and electronic equipment. The atlas construction method comprises the steps of obtaining and preprocessing dialogue data in a target field; carrying out semantic role labeling on the preprocessed dialogue data and obtaining arguments of the dialogue data; constructing a user map node and a customer service map node according to the argument of the dialogue data and the business entity; calculating map vector similarity between the user map nodes and the customer service map nodes, and if conditions are met, combining the user map nodes and the customer service map nodes; extracting knowledge points of which the number of times exceeds a preset threshold value and event relations from the map nodes subjected to merging processing, constructing a knowledge map according to the knowledge points, and constructing a fact map according to the event relations to obtain a map corresponding to the target field; The technical problems that the construction process of the map depends on combing of professionals, the construction cost is high, more maintenance entities exist, the constructed map is low in precision and long in timeconsumption are solved, the construction cost and the maintenance cost of the map are reduced, and the map precision is improved.

The invention discloses a triad extraction method of a safety report text. The method comprises the steps of obtaining the safety report text; performing clause processing on the security report text; carrying out word segmentation processing and part-of-speech tagging on the result of sentence segmentation processing by utilizing a word segmentation and part-of-speech tagging joint model constructed by fusing external knowledge, and outputting a word segmentation and part-of-speech tagging result; performing syntactic analysis on the segmented words and the part-of-speech tagging result based on a dependency syntactic analysis method, and obtaining grammatical components and the relation between the grammatical components in the segmented words and the part-of-speech tagging result; performing semantic role labeling, and obtaining arguments of a given predicate; and outputting the triad in the main and called guest form. The invention further discloses a corresponding device, electronic equipment and a computer readable storage medium; the safety report text is analyzed according to a syntactic analysis mode, triples are extracted, proper nouns of the security field are added in the word segmentation process, the model can better recognize the position and length of the subject, and the meaning of the subject-called bin in the triad can be better expressed to meet the requirements of accurate information analysis and screening.

The invention relates to a sentence similarity assessment method based on a deep semantic model and semantic role labeling. The method comprises the steps that a text character string is mapped to a feature vector in the low semantic space, and the cosine similarity is used for measuring the similarity between two sentences; an existing semantic role is reserved, and other semantic roles are processed in a unified mode; according to the similarity between predicates, predicate pairing is performed on sentence pairs to obtain predicate matching pairs, and a similar calculated value between semantic roles is further obtained; the multiple semantic roles of each of the multiple predicates of each sentence are subjected to semantic collocation, the semantic role similarity is calculated, the similarity calculated through the deep semantic model and the similarity calculated on the basis of the semantic roles are linearly combined to be adopted as the final sentence similarity. On the basisof the semantic roles, the Pearson's correlation coefficient is increased by 2.226%, and is 0.226% higher than that of the top one result on the SemEval2017 evaluation official website.

The invention relates to a semantic role recognition method based on a phrase structure tree. The method comprises the steps of sentence pruning, wherein when a system inputs one sentence, phrase analysis is performed on the sentence, the analyzed result is subjected to pruning through a parenthesis or a coordination structure, the complexity of the sentence is simplified, and the length of the sentence is shortened; clause extracting processing, wherein on the basis of the phrase structure tree, clauses in the pruned sentences are extracted, the extracted clauses and the remaining portion obtained after the clauses are extracted are subjected to semantic role analysis separately, the complete sentence semantic role is obtained, and the analysis result of the semantic role is reduced; boundary correction, wherein the reduced semantic role is combined with the phrase tree to perform predicate argument boundary correction on the sentences, and finally the sentence semantic role analysisresult is output. The sentence complexity is simplified, the sentence length is shortened, the complex and long sentence can be effectively processed, and the semantic role labeling condition is improved.

This invention maps possibly noisy digital input from any of a number of different hardware or software sources such as keyboards, automatic speech recognition systems, cell phones, smart phones or the web onto an interpretation consisting of an action and one or more physical objects, such as robots, machinery, vehicles, etc. or digital objects such as data files, tables and databases. Tables and lists of (i) homonyms and misrecognitions, (ii) thematic relation patterns, and (iii) lexicons are used to generate alternative forms of the input which are scored to determine the best interpretation of the noisy input. The actions may be executed internally or output to any device which contains a digital component such as, but not limited to, a computer, a robot, a cell phone, a smart phone or the web. This invention may be implemented on sequential and parallel compute engines and systems.

The invention relates to the technical field of natural language processing, and provides a method for marking semantic roles by fusing predicate prior information. The method for conducting superficial semantic analysis on a sentence includes the steps that 1, word segmentation and syntactic analysis are conducted on the sentence; 2, the core predicate in the sentence is found; 3, for the current predicate, by the utilization of a basic semantic role marking system, an initial semantic role marking result is generated, so that an initial candidate argument is obtained; 4, the predicate argument group distribution conditions of all predicates in training data are calculated; 5, combined analysis is conducted on the initial semantic role marking result, first, the core argument of all candidate arguments is recognized, and then the predicate argument group with the highest score is calculated according to the probability distribution of a predicate argument group of the current predicate to serve as a final semantic role marking result. The characteristics of the predicates can be sufficiently mined, relation between the predicates and the arguments is reasonably utilized, and the accuracy of semantic role marking is improved.

The invention belongs to the field of natural language processing research and particularly discloses an intelligent answering system for a learning machine. The intelligent answering system comprises a semantic analysis unit, a second relation establishing unit, a rational analysis unit and an answer extracting unit, wherein multiple obtained candidate answers are evaluated, the candidate answer with the highest evaluated value is used as an answer, and then a system result is provided. The intelligent answering system can be effectively combined with the learning machine of the prior art, will not be influenced by the number of questions of a question bank of the existing learning machine, can conduct analysis and judgment automatically and intelligently provide answers, and effectively fills up the blank in the aspect. The intelligent answering system has the advantages that corresponding relations between semantic roles are established in authentic Chinese materials, and an induction path is formed between the questions and the answers; the granularity of reading comprehension questions and answers reaches the chuck level, and more natural and more appropriate answers are provided.