160 results about "Syntactic tree" patented technology

Machine translation decoding is accomplished by receiving as input a text segment in a source language to be translated into a target language, generating an initial translation as a current target language translation, applying one or more modification operators to the current target language translation to generate one or more modified target language translations, determining whether one or more of the modified target language translations represents an improved translation in comparison with the current target language translation, setting a modified target language translation as the current target language translation, and repeating these steps until occurrence of a termination condition. Automatically generating a tree (e.g., either a syntactic tree or a discourse tree) can be accomplished by receiving as input a tree corresponding to a source language text segment, and applying one or more decision rules to the received input to generate a tree corresponding to a target language text segment.

The invention relates to a method for realizing optimization of a data source extensive makeup language (XML) query system based on sub-queries. The method comprises the following steps: receiving corresponding XML query input information; carrying out morphological analysis and syntactic analysis, and verifying the correctness and the validity; if the analysis is successful and the verification is passed, generating an XML analytical syntactic tree; translating the XML analytical syntactic tree, and converting the XML query input information into intermediate logical representation; carrying out rewriting treatment, and generating a target query expression; and calling supported querying and computing engines for querying and computing, and acquiring output query results. By adopting the method for realizing the optimization of the data source XML query system based on the sub-queries, the query rewriting can be used for converting a procedural query into a descriptive query, the sub-queries are optimized, and certain specific sub-queries are rewritten into equivalent attended operation of a plurality of tables by the combination of the sub-queries, thus the levels of query sentences are reduced as much as possible, the treatment of planning optimization can be carried out conveniently, and the method has stable and reliable working performance and wider application range.

The invention discloses an extraction method of a semantic relation between Chinese entities. The extraction method comprises the following steps of: carrying out syntactic analysis on natural statements to determine a complete syntactic tree of the natural statements; extracting a shortest path containing tree between two Chinese entities from the complete syntactic tree; extracting a path verb nearest to a second Chinese entity from the shortest path containing tree; respectively acquiring the semantic information of the two Chinese entities and the path verb; adding the three acquired semantic information into a root node of the shortest path containing tree according to a preset rule to determine the expanded shortest path containing tree to be a natural statement relation tree; and carrying out relation classification on the relation tree by utilizing a prestored classification model. According to the extraction method of the semantic relation between Chinese entities, which is disclosed by the invention, the relation tree contains abundant structured information and lexical semantic information and has better generality and semantic relation extraction overall performance, the dependence degree of a large-scale corpus is relieved, and meanwhile, the calculated amount of the system is lower.

A system for translating messages is provided. The system includes a parsing unit that parses a first message and a second message in which the same content is respectively described in a first language and a second language that are different from each other so as to generate a first syntactic tree that represents the structure of the first message and a second syntactic tree that represents the structure of the second message, a determining unit that, in a case where the representation of a phrase represented by a certain subtree included in the first syntactic tree matches the representation of a phrase represented by a subtree, corresponding to the subtree, in the second syntactic tree, determines that the phrase is a phrase that need not be translated, and a translation unit that, in a process of generating a fourth message described in a fourth language by translating a third message described in a third language, outputs the phrase that need not be translated and is included in the third message, as represented in the third message, the phrase being put in the fourth message after the translation.

The invention provides an event extraction method and system fusing dependency information and a pre-trained language model. The method comprises the steps of taking a dependency syntax tree of a sentence as input, learning dependency syntax features by using a graph convolutional neural network, adding a dependency relationship prediction task, capturing a more important dependency relationship in a multi-task learning mode, and finally enhancing underlying syntax expression by using a BERT pre-training language model to complete event extraction of Chinese sentences. Therefore, the performance of trigger word extraction and argument extraction under the event extraction task is improved.

The invention discloses a man-machine interaction question-answering method and system based on complex intention intelligent recognition, and the method comprises the steps: obtaining an original question sentence of a user, carrying out the sentence segmentation and part-of-speech tagging, and obtaining the part-of-speech information of each component word of the question sentence; performing dependency syntax analysis on the question sentence to obtain a dependency syntax tree; carrying out industry entity identification to obtain industry entities and the number, and extracting a core dependency tree to simplify questions; carrying out industry question relation classification on the questions, carrying out Chinese multi-intention question rewriting, and then carrying out knowledge retrieval on the questions; and selecting and generating answers for knowledge retrieval results, and returning the answers to the user. According to the method and system, multi-intention complex questions can be effectively simplified in any industrial scene, the intention of the user can be accurately understood, the industrial knowledge can be more naturally fed back to the user, the user can more accurately and quickly obtain the required industrial knowledge, the user experience is improved, and the method and system are particularly suitable for man-machine interaction intelligent questions and answers in the medical industry.

The invention discloses a spoken language evaluation method based on grammatical analysis and a spoken language evaluation system. The spoken language evaluation method is characterized in that syntax content of a voice segment can be extracted, and a syntactic tree can be established according to the syntax, and then the node similarity between the syntactic tree and the preset syntactic tree can be calculated, and the word order evaluation result of the voice segment can be acquired; the predicate verb of the voice segment can be acquired, and the predicate verb in the preset predicate verb corpus can be identified to acquire the tense evaluation result of the voice segment; the grammatical evaluation result of the voice segment can be acquired according to the word order evaluation result of the voice segment and the tense evaluation result of the voice segment. According to the invention, the spoken language evaluation can be carried out from three aspects, namely fluency, accuracy, and grammatical evaluation, and then by combining the spoken language voice quality evaluation index and the spoken language content evaluation index, the evaluation model is more objective, comprehensive, and accurate.

The invention provides a static checking method and a static checking device for source code pairing. The method comprises the following steps of: performing lexical analysis on source codes, filtering annotation in the source codes, and splitting the source codes into a plurality of mark flows; performing syntactic analysis on the mark flows to construct a syntactic tree; performing semantic analysis on the syntactic tree, searching elements required to be paired, and marking an action region of the elements required to be paired; judging whether the elements required to be paired are paired in the action region or not; if the non-paired elements required to be paired are discovered, judging whether correction is allowed or not; if the correction is allowed, adding pairs at the end of the action region; and if the correction is not allowed, giving an alarm and a prompt. By the method, the pairing detecting efficiency can be effectively improved, stability of a system is improved, certain boundary errors are effectively avoided, user programs can be automatically corrected according to setting of a user, and the workload of a programmer is greatly reduced.

Instructional systems are assumed to include one or more learners, human and/or automated, content, means of presenting information to and receiving responses from learners, and an automated tutor capable of deciding what and when information is to be presented to the learner and how to react to feedback from the learner based on configurable options and the current status of the learner model. This invention discloses a method for authoring and delivering highly adaptive instructional systems based on abstract syntax tree representations of the problems to be solved by learners and, of the requisite knowledge structures to be acquired. Authoring includes: a) receiving and/or constructing abstract syntax tree representations of essentially any kind of to-be-acquired knowledge (KR), b) methods for representing problem schemas in an observable medium enabling communication between tutors and learners and c) configuring the learning and tutorial environment to achieve desired learning. Delivery includes general-purpose methods for: d) generating specific problems, updating the learner model and sequencing diagnosis and instruction.

A parser for natural language text is provided. The parser is trained by accessing a corpus of labeled utterances. The parser extracts details of the syntactic tree structures and part of speech tags from the labeled utterances. The details extracted from the tree structures include Simple Links which are the key to the improved efficiency of this new approach. The parser creates a language model using the details that were extracted from the corpus. The parser then uses the language model to parse utterances.

The invention discloses a knowledge graph relational data classification method based on a syntactic attention neural network. The method mainly comprises the following steps: collecting a design document of a complex equipment design process, and establishing a design document corpus according to text data of the design document; carrying out text preprocessing on the collected text data of the design document; establishing an entity relationship classification model based on a syntactic attention deep neural network; inputting the preprocessing result and the category label into the model for offline training; and inputting to-be-predicted text data into the trained syntactic attention-based deep neural network, and predicting to obtain a relationship category result corresponding to thekeyword text in the text data. According to the method, semantic information and syntax information are adaptively combined, so that the accuracy of entity relationship category prediction of the text data of the design document is effectively improved, and which part of path of the dependency syntax tree of the statement has higher weight in the prediction process of the model can be deduced.

The invention discloses a user comment attribute extraction method based on bi-directional dependency syntactic tree representation. The method comprises the steps that 1) given user comment text is preprocessed, and a dependency syntactic tree is generated; 2) a bi-directional dependency syntactic tree representation network is established, and dependency characteristics among words are extracted; 3) the dependency characteristics are input into a bi-directional LSTM nerve network, sequence characteristics among the words are extracted on the basis of the dependency characteristics, and accordingly the dependency characteristics are effectively combined with the sequence characteristics; 4) the combined characteristics are coded by using a linear chain condition random field; 5) a Viterbialgorithm is used for conducting decoding to obtain comment attributes of all text. According to the user comment attribute extraction method, the aim is effectively achieved that in user comment attribute extraction tasks, the dependency characteristics of text syntax are extracted and efficiently combined with the sequence characteristics to achieve end-to-end training; the condition random field is used for coding the combined characteristics, the Viterbi algorithm is used for decoding the combined characteristics, and the good effect can be achieved in the user comment attribute extraction tasks.

The embodiment of the invention discloses a method and device for evaluating translation quality. A specific embodiment of the method comprises the steps of obtaining a to-be-evaluated translation anda reference translation; inputting the to-be-evaluated translation and the reference translation into a pre-trained replication encoding model to obtain semantic similarity of the to-be-evaluated translation and the reference translation, the replication encoding model being a neural network used for calculating a probability that a pair of sentences is replicated sentences; respectively analyzing the translation to be evaluated and the reference translation into two syntactic trees through a syntactic analyzer; calculating the similarity of the two syntax trees as the text similarity of thetranslation to be evaluated and the reference translation; and taking the weighted sum of the semantic similarity and the text similarity as a translation quality score. According to the embodiment, by combining the scores of the indexes, comprehensive evaluation of the current translation in the aspects of semantics, syntax, lexical and overall information intelligibility can be reflected, and the situation that the automatic evaluation score is high, but the intelligibility is low is avoided.

The embodiment of the invention relates to an entity relationship extraction method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out word segmentation of a to-be-extracted target text to acquire words; performing part-of-speech tagging on each word to obtain a part-of-speech tag of each word; performing dependency syntax analysis on the targettext based on the part-of-speech label of each word to obtain a dependency syntax tree of the target text; and determining a syntax mode conforming to the target text based on the dependency syntax tree, and extracting an entity relationship triad from the target text based on the syntax mode. Therefore, the entity relationship triples can be efficiently and accurately extracted from the corpus data.

The invention discloses a hotspot information finding method and system. The method includes the steps of obtaining a to-be-processed text, conducting word dividing and part-of-speech tagging on the to-be-processed text, conducting parsing on the text subjected to word dividing to obtain a dependence syntactic tree of each sentence in the to-be-processed text, removing stop words in the dependence syntactic tree of each sentence in the to-be-processed text to obtain to-be-analyzed dependence syntactic tree, establishing a small world network through the to-be-analyzed dependence syntactic tree, conducting hotspot analysis according to the to-be-analyzed dependence syntactic tree and the small world network, and obtaining hotspot information in the to-be-processed text according to the hotspot analysis result. By means of the method and system, the hotspot information in the to-be-processed text can be efficiently and accurately found.

The embodiment of the invention discloses a MySQL based SQL parser and a parsing method thereof.The technical problem that existing lexical and syntactic analysis tools do not support unique SQL statements of MySQL and cannot achieve the function of expanding the MySQL through annotations and accordingly the complexity of the data analysis process is caused is solved.The MySQL based SQL parser comprises a lexical analyzer, a syntactic analyzer and a syntactic tree analyzer, wherein the lexical analyzer conducts MySQL language lexical analysis on acquired character streams, outputs token flows corresponding to MySQL languages to the syntactic analyzer for syntactic segment analysis corresponding to the MySQL languages and outputs syntactic trees corresponding to syntactic segments to the syntactic tree analyzer for analysis.

The invention relates to a Chinese-cranial nerve machine translation method fusing syntactic analytic trees, and belongs to the technical field of natural language processing. Machine translation of Chinese-Vietnamese and Vietnamese-Chinese can be realized. A Chinese-Vietnamese bilingual parallel corpus constructed through Internet crawling and manual translation is used as a training data set. The method aims to solve the problem of translation errors caused by insufficient training corpus in current Chinese-Yue machine translation. The method comprises the following steps: performing word segmentation, part-of-speech tagging and syntactic analysis on a source language to obtain a syntactic tree of the source language; and then vectorizing the syntactic labels and fusing the vectorized syntactic labels into a coding process of machine translation model training to train a machine translation model. An obtained model can effectively complete translation between Chinese and Vietnamese.An experiment result shows that compared with a benchmark system which does not fuse the syntactic parsing tree, the translation obtained by the method is smoother, and 0.6 BLEU values are improved.

The embodiment of the invention discloses a method and a device for analyzing a multi-dimensional query sentence in an online analysis processing server. The method comprises the following steps of: analyzing a multi-dimensional query sentence and generating a syntactic tree according to an analyzed result, wherein a node of the syntactic tree comprises a horizontal axis object, a longitudinal axis object, a slicing axis object, a calculating member object, a calculating unit object and a custom function CDF object; when a multi-dimensional query expression of various objects on the syntactictree is executed, if a function needs to be called, judging whether the function is a custom function or not according to a function definition of the custom function, if so, entering the executing process of the custom function; otherwise, judging whether the function is a standard function or not according to the function definition of a standard function; and if so, entering the executing process of a marking function. By the embodiment of the invention, the working efficiency of a developer in the development process of the whole OLAP system can be improved.

The invention discloses a knowledge graph question and answer training system with an automatic template generation function, and the system comprises a predicate dictionary and category dictionary construction module which is used for constructing a predicate dictionary and a category dictionary in a remote supervision mode; a backbone query generation module which is used for obtaining sub-graphs of the theme entity and the answer entity of each training question and answer pair in the knowledge graph, and using variables to replace answer nodes in the sub-graphs to form backbone queries; asemantic alignment module which is used for aligning question phrases with backbone query semantic elements by using dependency syntactic analysis and a shaping linear alignment technology; a templateubiquitous module which is used for storing the dependency syntax tree, the backbone query and the corresponding relationship into a template library as templates; and a sorting model training modulewhich is used for performing classified learning on every two matching templates by using a machine learning binary classifier according to the matching degree to obtain a question template sorting model, so that the problems of high labor cost and low problem coverage rate in the prior art are solved.

Techniques for computer-generated conversation are disclosed. In an example, a method identifies text postings from a conversation. The method creates, for each text fragment of each text posting, a syntactic tree and a discourse tree. The method creates parse thickets, each parse thicket including the syntactic tree and discourse tree of a unique pair of text postings. The method extracts, from each parse thicket, a common text segment and obtains a set of candidate search results by providing the common text segments to a search engine. The candidate search results can be further refined for relevancy and mental state and posted as a response to a conversation.

The invention relates to a method for establishing a tree structure and a tree-structure-based machine translation system. The method includes the steps of performing word segmentation, part-of-speech tagging and word alignment for bilingual sentence pairs in a bilingual corpus; performing bilingual segmentation for the bilingual sentence pairs to generate bilingual sub-sentence pairs shorter than the former sentence pairs according to the result of word alignment, and performing word realignment for the generated bilingual sub-sentence pairs; combining sub-sentences to achieve word alignment of the bilingual sentence pairs according to the result of word realignment of the bilingual sub-sentence pairs, and constituting a compressed forest for the bilingual sentence pairs; and selecting the proper tree structure from the compressed forest. The method can be used for establishing the tree-structure-based translation system with the language pairs having part-of-speech tagging resources without any syntactic tree resources.