62 results about "Semantic role labeling" 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.

A system and method are disclosed for providing semi-supervised learning for a spoken language understanding module using semantic role labeling. The method embodiment relates to a method of generating a spoken language understanding module. Steps in the method comprise selecting at least one predicate / argument pair as an intent from a set of the most frequent predicate / argument pairs for a domain, labeling training data using mapping rules associated with the selected at least one predicate / argument pair, training a call-type classification model using the labeled training data, re-labeling the training data using the call-type classification model and iteratively several of the above steps until training set labels converge.

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.

A system and method for predicting price fluctuations in financial markets. Our approach utilizes both market history and public news articles, published before the beginning of trading each day, to produce a set of recommended investment actions. We empirically show that these markets are surprisingly predictable, even by purely market-historical techniques. Furthermore, analyzing relevant news articles captures information features independent of the markets history, and combining the two methods significantly improves results. Capturing usable features from news articles requires some linguistic sophistication the standard naïve bag-f-words approach does not yield predictive features. Instead, we use part-of-speech tagging, dependency parsing and semantic role labeling to generate features that improve system accuracy. We evaluate our system on eight political prediction markets from 2004 and show that we can make effective investment decisions based on our systems predictions, whose profits greatly exceed those generated by a baseline system.

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.

A question-answering system for searching exact answers in text documents provided in the electronic or digital form to questions formulated by user in the natural language is based on automatic semantic labeling of text documents and user questions. The system performs semantic labeling with the help of markers in terms of basic knowledge types, their components and attributes, in terms of question types from the predefined classifier for target words, and in terms of components of possible answers. A matching procedure makes use of mentioned types of semantic labels to determine exact answers to questions and present them to the user in the form of fragments of sentences or a newly synthesized phrase in the natural language. Users can independently add new types of questions to the system classifier and develop required linguistic patterns for the system linguistic knowledge base.

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 invention discloses a semantic similarity analysis method based on text clustering. The method comprises the following steps: taking unprocessed text data as input; performing word frequency statistics on texts subjected to data preprocessing, adding word frequency statistics information serving as priori knowledge into text clustering, proposing a posteriori judgment criterion, and performingan unsupervised clustering method on the basis of taking the word frequency statistics as a classifier to improve the accuracy and timeliness of a text clustering result; carrying out synonym ambiguity elimination on the processed text, and carrying out semantic role labeling; and generating a semantic vector fused with the context features, processing the text sequence by adopting two LSTMs withcompletely same structures and parameters, adding the product and variance of the results, amplifying the same points and differences of the texts, and calculating to obtain a final result of similarity analysis. The method can be applied to actual scenes of text similarity analysis in various different fields, and text data of different types can be well processed.

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.

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.

Methods and devices for story detection in text are provided. A device can include an input device for receiving text data a processor configured to: tokenize each paragraph in the text data and split each tokenized paragraph into sentences; parse each sentence from the tokenized paragraphs; label each predicate in each sentence with its respective semantic role; and assign a verb class to each predicate; and determine whether respective arguments of each predicate contains a character. The device can further include a support vector machine configured to determine whether a story is present within each paragraph based upon whether each predicate contains a character.

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 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.

The embodiment of the invention provides a method for identifying sensitive information in a judgment document, which comprises the following steps of: 1, obtaining the judgment document from a Chinese judgment document network, and performing sentence segmentation and word segmentation processing on the judgment document; 2, carrying out named entity recognition on the processed judgment document, and extracting entities and attribute values; 3, carrying out semantic role labeling on the processed judgment document, and constructing a triple about the event occurrence situation; 4, carrying out relation extraction on the extracted entities and the attribute values, and constructing a relation triple; 5, constructing a structural data network through entity alignment according to the triples and the relational triples of the event occurrence conditions; and step 6, defining sensitive information according to the information content which is not suitable for being disclosed, and markingthe corresponding sensitive information in the judgment document by utilizing the structure data network. The embodiment of the invention provides the method for identifying the sensitive informationin the judgment document, the sensitive information in the judgment document is identified by utilizing semantic understanding of machine learning on legal concepts and natural languages, and the identification method has good practical significance for judicial disclosure and guarantee of public right of informed and supervision.

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 discloses an event extraction and processing method for case-following electronic files. The method comprises the following steps: step 1, acquiring required file data from a case-following electronic file circulation processing platform and storing the required file data into a database; 2, constructing an event trigger word dictionary, matching an electronic file event descriptionparagraph, and performing text preprocessing methods such as sentence segmentation, word segmentation and part-of-speech tagging; 3, event attribute extraction: combining dependency syntax analysis and a semantic role labeling method to obtain six event attributes including an applicant, a susceptor, a behavior, time, a place and a mode of an event; and step 4, event aggregation: aggregating the atomic events into topic events, combining similar topic events, and storing the topic events into an event database. According to the method, the problem that crime fact information is rapidly obtained by the case-following electronic file is solved, event extraction and organization can be more accurately carried out on crime facts, and the method is a basis for efficient and high-quality paper marking.

The invention relates to the field of artificial intelligence, in particular to a corpus text processing method, device and equipment and a storage medium. The corpus text processing method comprisesthe steps of obtaining a target corpus text, and performing semantic role labeling on the target corpus text to obtain a plurality of semantic units carrying word orders corresponding to the target corpus text; constructing a regular semantic expression corresponding to the target corpus text based on the semantic unit and a preset rule set, wherein the regular semantic expression comprises a plurality of regular semantic tags; and constructing a semantic dictionary corresponding to the regular semantic tag, and generating a regular semantic template corresponding to the target corpus text based on the regular semantic expression and the semantic dictionary. According to the corpus text processing method, the problem that the execution efficiency is low due to the fact that a literal expression mode is adopted when a mining template is constructed through traditional keyword matching or regular expression matching is effectively solved. The invention further relates to digital medicaltreatment which is applied to robot online medical consultation and inquiry.

Disclosed is a method for generating a semantic image labeling model, comprising: forming a first CNN and a second CNN, respectively; randomly initializing the first CNN; inputting a raw image and a plurality of predetermined label ground truth annotations to the first CNN to iteratively update weights of the first CNN so that a category label probability for the raw image, which is output from the first CNN, approaches the predetermined label ground truth annotations; randomly initializing the second CNN; inputting the category label probability to the second CNN to correct the input categorylabel probability so as to determine classification errors of the category label probabilities; updating the second CNN by back-propagating the classification errors; concatenating the updated firstCNN and the updated second CNN; classifying each pixel in the raw image into one of a plurality of general object categories; and back-propagating classification errors through the concatenated CNN toupdate weights of the concatenated CNN until the classification errors less than a predetermined threshold.

The invention provides a Russian semantic role labeling method, system and device and a storage medium. Aiming at the characteristics of Russian, the relation between predicates and arguments is reasonably utilized, the semantic role annotation of the Russian can be well realized, the semantic role annotation accuracy is improved, and higher annotation performance is obtained. The method comprisesthe following steps: 1, preprocessing corpora, extracting classification characteristics, and converting the classification characteristics into characteristic vectors; 2, constructing classificationmodels based on neural networks of different architectures, and inputting classification features into the classification models for training to obtain trained classification models; 3, based on a voting fusion mechanism, fusing the trained classification models according to the principle that a small number obeys a majority to obtain a fusion model; 4, inputting the preprocessed corpus into a fusion model, identifying a semantic role, attaching a prediction label, and performing performance evaluation on an obtained semantic role prediction result.

The invention relates to a sentence vector generation method and system oriented to an intelligent question-answering system. The method comprises the following steps: performing Chinese word segmentation on a given Chinese sentence; generating a corresponding Chinese word vector for each word according to a word segmentation result; performing semantic role labeling on the sentences to generate a semantic relation graph of the sentences; taking word vectors as input, coding sentences, and outputing a hidden state vector of each word vector; encoding the semantic relation graph to generate an adjacent matrix of the semantic relation graph; and inputting the adjacent matrix of the semantic relation graph and the hidden state vector of the word vector into a GCN, and performing layer-by-layer fusion iteration with each output of the middle layer of the BERT pre-training model to obtain a final coded sentence vector. Compared with a general sentence vector generation method, due to the fact that semantic structure codes of sentences are fused in the invention, richer and more instructive information is provided, higher-quality input is provided for similar question semantic matching, and the query precision is improved.

The invention relates to the field of artificial intelligence, and discloses an intelligent question-answering method, a device, equipment and a storage medium. The method comprises the steps of acquiring and labeling question corpora through a semantic role labeling model, and obtaining labeled phrases and corresponding role types; according to the role type, determining a phrase category librarycorresponding to the annotated phrases, wherein the phrase category library comprises sub-categories, and the sub-categories comprise template phrases; calculating the similarity between the annotated phrases and template phrases in a corresponding phrase category library, and determining sub-categories of the annotated phrases; querying a corresponding standard question from a standard questionlibrary according to the role type and the subclass of the annotated phrase; and constructing a corresponding standard answer according to the standard question and outputting the standard answer. According to the method, the statement closest to the semantic meaning of the user question can be quickly and accurately found from the standard question and answer, the response quality and speed are ensured, and the user experience is improved. In addition, the invention also relates to a blockchain technology, and the question corpus of the user can be stored in the blockchain.