3533 results about "Sentence" patented technology

A system and method for speech recognition includes generating a set of likely hypotheses in recognizing speech, rescoring the likely hypotheses by using semantic content by employing semantic structured language models, and scoring parse trees to identify a best sentence according to the sentence's parse tree by employing the semantic structured language models to clarify the recognized speech.

The invention provides a method and a system for converting the query sentence of a database. After a database table and a field are set, the name and field of the required database are selected in the foreground and the self-defined query sentence is inputted by a user according to the service requirement, and the query sentence inputted by the user is subjected to grammar analysis and validation, thus finishing the analysis by scanning the query sentence for only one time. By converting the service Chinese query sentence into a standard English SQL (structured query language) query sentence required by a service system, the invention fulfills the function of converting a service database query sentence into a standard executable SQL sentence, wherein the sentence acquired by the service system is directly available to the system, so that a common user can flexibly and freely use the database without mastering the query tool, SQL syntax and other professional technique of the database.

The invention provides a method of constructing a text classification model. The method comprises the steps of: constructing a training sample set according to structure features of characters, wordsand sentences of text information, wherein each piece of sample data in the training sample set corresponds to a feature matrix A of a piece of text information about the words and a feature matrix Babout the characters and a category vector O corresponding to the piece of text information, and the dimension number of O is the same as a category number; and using the feature matrix A about the words and the feature matrix B about the characters in the training matrix set as input and the corresponding category vector O as output to train a deep learning model to obtain the text classificationmodel. Classification is carried out according to the classification model constructed by the method, an accuracy rate of text classification can be improved, and the method is particularly suitablefor use in short-text classification.

The invention discloses an aspect-level emotion classification model and method based on dual-memory attention, belonging to the technical field of text emotion classification. The model of the invention mainly comprises three modules: an encoder composed of a standard GRU loop neural network, a GRU loop neural network decoder introducing a feedforward neural network attention layer and a Softmaxclassifier. The model treats input statements as a sequence, based on the attention paid to the position of the aspect-level words in the sentence, Two memory modules are constructed from the originaltext sequence and the hidden layer state of the encoder respectively. The randomly initialized attention distribution is fine-tuned through the attention layer of the feedforward neural network to capture the important emotional features in the sentences, and the encoder-decoder classification model is established based on the learning ability of the GRU loop neural network to the sequence to achieve aspect-level affective classification capabilities. The invention can remarkably improve the robustness of the text emotion classification and improve the classification accuracy.

Input texts, e.g., electronic text files containing a written work, are received by the invention. Selected visual characteristics of text, such as such as font case, font type, font size, font color, word spacing, and line spacing, are automatically applied to the text and are varied within the text to produce enhanced text. The variation may occur as frequently as character to character, or word to word, sentence to sentence, line to line, paragraph to paragraph, or some other frequency. The resulting enhanced text is visually different from the received text (provided the applied variations are not already present in the received text). The enhanced text is then visually displayed to a reader, as by providing it on a computer monitor or in printed form. The enhanced text, having more visible variety than the received text, is believed to result in greater reading speed, comprehension, and/or interest in people having certain types of reading deficiencies.

The invention provides a Q&A method based on a hierarchal memory network. The method comprises the following steps: firstly performing sentence granularity memory encoding, and finishing the information inference of the sentence granularity memory unit through an attention mechanism in multi-rounds of iterations under the stimulation of the problem semantic encoding, screening the sentence through k maximum sampling, and further performing the word granularity memory encoding on the basis of the sentence granularity encoding, namely, performing the memory encoding on two levels to form the hierarchal memory encoding; the output word probability distribution is predicted through the combination of the sentence granularity memory unit and the word granularity memory unit, the accuracy of the automatic Q&A is improved, and the answer selection problem of low-frequency word and unlisted word is effectively solved.

The invention discloses a text classification method combining dynamic word embedding with part-of-speech tagging, and provides the text classification method based on a deep neural network through combining dynamic word embedding with part-of-speech tagging. The method can fully utilize the advantages that a large-scale corpus can provide more accurate grammar and semantic information, and can also adjust word embedding by combining with the features of the corpus during a model training process, and thus the features of the corpus can be better learned. Meanwhile, classification accuracy can be further improved by combining with part of speech information of words in sentences. The invention also comprehensively utilizes the advantages of LSTM in the aspect of learning context information of words and part of speech in the sentences, and the advantages of CNN in the aspect of learning text local features. The classification model provided by the invention has the advantages of high accuracy and strong universality, and achieves good effect in some famous public corpuses including IMDB corpus, Movie Review and TREC.

This invention discloses a method and a device for optimizing query SQL request, in which, the method includes: standardizing the field names and bynames in the SQL sentences to eliminate the redundant associated relations in them, converting said SQL sentences into a grammar tree to be optimized for logic relation to be converted to standard SQL sentences.

A system for coding and decoding languages that includes a first set of computerized databases and each of database storing a predetermined number of indexed information elements (such as words) and a second set of computerized databases wherein each database includes a predetermined number of structural arrangements for using the information elements. The indexed information elements are classified by the component class of a sentence or phrase. They may be classified as verbs, adjectives, etc. and this holds true for the same indexed entry for the different databases for a particular information element. The system decodes the information elements in a sentence, or phrase and matches a corresponding structural arrangement in a given language which holds for the other language.

The invention discloses a commodity target word oriented emotional tendency analysis method, which belongs to the field of the analysis processing of online shopping commodity reviews. The method comprises the following four steps that: 1: corpus preprocessing: carrying out word segmentation on a dataset, and converting a category label into a vector form according to a category number; 2: word vector training: training review data subjected to the word segmentation through a CBOW (Continuous Bag-of-Words Model) to obtain a word vector; 3: adopting a neural network structure, and using an LSTM(Long Short Term Memory) network model structure to enable the network to pay attention to whole-sentence contents; and 4: review sentence emotion classification: taking the output of the neural network as the input of a Softmax function to obtain a final result. By use of the method, semantic description in a semantic space is more accurate, the data is trained through the neural network so as to optimize the weight and the offset parameter in the neural network, parameters trained after continuous iteration make a loss value minimum, at the time, the trained parameters are used for traininga test set, and therefore, higher accuracy can be obtained.

The invention is a kind of Chinese and foreign languages double-way automatic translation method which is based on the sentential form conversion and adopts the Chinese phonetic codes with the word as the unit, and it belongs to the automatic translation technology field. By the method we can translate Chinese and another language such as English to each other expediently, on one hand, it overcomes the present faults that all the Chinese-foreign languages translation can only be done by the Chinese characters and Chinese spelling because of that Chinese uses the connecting written Chinese phonetic codes by word which only adopts twenty-six Latin letters as the code element and includes Chinese sound, rhythm and tone to expresses information when translating, that Chinese characters and Chinese phonetic signs can not be compatible with ASCII codes completely and the malpractice that before every translation, the Chinese information that Chinese characters expresses has to be divided to single word, on the other hand, because of adopting the sentential form conversion method which bases on the lexical and the syntax system coincident with the goal language, to make the automatic translation method more exact than the traditional translation method, and the effectiveness better. However the inputting Chinese form is Chinese characters, Chinese spelling or Chinese phonetic codes, it can not only translates by the traditional method but also translate after changing the Chinese characters to Chinese phonetic codes, likely, if needed, the Chinese phonetic codes gotten after translation can not only express the Chinese information directly, but also be conversed to Chinese characters, Chinese spelling, Chinese sound, Chinese special person, Chinese localism or minority language sound.

The invention discloses a neural network based analyzing method for recognizing emotional tendency of text comments, and belongs to the technical field of computer language and work processing. The method is characterized in that the text comment data are processed through CBOW; each sentence is accurately divided into words or terms, and each sentence is provided with a corresponding class label; the emotional tendency of the comments is determined through a long-and-short term memory LSTM model; the label of each sentence is obtained and compared with a true label to obtain the accuracy rate; and a neural network model is trained to obtain the optimal accuracy rate, thus achieving the purpose of recognizing the emotional tendency of the text comments based on the neural network. According to the method, the GPU is utilized to accelerate the neural network training process, so that the emotion classing accuracy rate is increased, and moreover, the mass corpus data training speed is increased; the emotional tendency of the comments can be effectively recognized; and the method particularly has a good application prospect on e-commerce, film and other fields.

A computer system for parsing bulk message information into intelligent question retrieval models receives text-based data associated with a particular user. The system encodes the word into a context-dependent vector, wherein the context-dependent vector indicates the meaning of the word across a semantic space. The system also identifies within a context-independent database a context-independent vector that is associated with the word. Further, the system generates an objective output by combining the context-dependent vector and the context-independent vector. Further still, the system generates a sentence encoding representation by processing at least a portion of the text-based data through a high-level feature embedded convolutional semantic model to generate numerical representations of questions and answers within the text-based dataset. The sentence encoding representation is generated at least in part based upon the objective output.

The invention discloses an entity relationship joint extraction method based on multi-label labeling and a composite attention mechanism, which comprises the following steps: collecting corpus data for research, then removing sentences of which the relationship labels are 'None', and performing multi-label labeling on the rest sentences to form a training set; inputting the sentences subjected tomulti-label labeling into a joint extraction model, identifying entities contained in the sentences and relationships among the entities through the joint extraction model, and constructing a triple;and correcting the extracted triples by utilizing a relationship alignment model so as to adapt to multi-label labeling of (head entity E1 and tail entity E2) entity pairs. The method has the advantages that the accuracy of triple extraction can be effectively improved, and the method is an effective tool for information extraction of unstructured data.