43 results about "Machine reading" patented technology

The present invention relates to the technical field of wireless network optimization operations and maintenance, and provides a two-stage optimized wireless network optimization field long entity recognition method and system. The method comprises: using a pretrained long entity recognition model to process acquired text content to be recognized to obtain a long entity recognition result; by means of a first-stage predecessor task, acquiring a pretrained model TelBert having domain knowledge; and in a second stage, introducing semantic information related to an entity to obtain a machine reading comprehension framework-based long entity recognition model, and decoding the entity by means of a dual-pointer network. According to the present invention, knowledge in a specific field is learned by adding an entity type prediction task, the text representation learning capability of a base model is enhanced, and the difficulty of model tuning in a few-shot scenario is alleviated; the entity recognition model is improved to obtain an MRC-LER model suitable for document-level long entity recognition; and a semantic similarity-based evaluation index is proposed, and the effective extraction rate of entity key information is reasonably evaluated.

The invention discloses an equipment defect grade classification method and system based on a knowledge graph, and belongs to the field of equipment defect classification. Structured information is extracted through a two-stage pipeline extraction algorithm; a few-sample named entity recognition task is realized by a prompt-based machine reading understanding named entity recognition method; judging the relationship between the paired entities based on a prompted relationship extraction method; according to the template-based structured data triple extraction method, original structured data is analyzed into a knowledge triple; deep structure information in the knowledge graph is learned by expanding first-order to second-order proximity; realizing candidate entity generation and candidate path extraction based on a dual-channel recall strategy; and performing fine-grained semantic matching and sorting on the input defect text and the candidate path based on a single-tower structure to position the most similar defect type. According to the method, the knowledge graph construction technology is utilized to solve the problems of integration, processing and efficient utilization of multi-source heterogeneous data, and the efficiency and accuracy of defect classification are improved.

The present application relates to a kind of machine reading comprehension method based on repeated span prediction, belong to natural language processing machine reading comprehension field.The method includes: for the reading comprehension task of span prediction form, increase the task of predicting repeated span.The task first finds all repeated spans in text paragraph based on greedy algorithm, then the short span contained in long span is filtered, after obtaining repeated span set, for each group of repeated span, randomly select one as answer span, and other spans in group are replaced by mask.Processed text is input into pre-training model, and representation vector is obtained, and based on softmax, which span in paragraph should the mask position point to be predicted.In the task, the obtained model is further fine-tuned on target task.The method considers the problem of lack of span knowledge of pre-training model, and constructs data in unsupervised manner, so that the model can better learn span representation, and improve the performance of model in span prediction.

Systems, devices, and methods discussed herein are directed to generating an answer to an input query using machine reading comprehension techniques and a lattice of supported decision trees. A supported decision tree can be generated from the various decision chains (e.g., a sequence of elements comprising a premise and a decision connected by rhetorical relationships), where the nodes of the decision tree are identified from the plurality of decision chains and ordered based on a set of predefined priority rules. A lattice may include nodes that individually correspond to a respective supported decision tree. Nodes of the lattice may be identified for an input query. The passages corresponding to those nodes may be obtained and an answer for the query may be generated from the obtained passages using machine reading comprehension techniques. The generated answer may be provided in response to the query.

A moving image comprising: at least one genuine machine-readable image (e.g. barcode 22) capable of actuating a function in a machine reading system 101,104; at least one non-readable image (fake) tha

A machine reading comprehension method includes obtaining a question text and an article text associated with the question text, generating a first knowledge text corresponding to the question text and a second knowledge text corresponding to the article text based on a knowledge set, encoding the question text and the article text to generate an original target text encoding, encoding the first knowledge text and the second knowledge text to generate a knowledge text encoding, performing a fusion operation on the original target text encoding and the knowledge text encoding, importing part of the knowledge in the knowledge set into the original target text encoding to generate a reinforced target text encoding, and obtaining an answer corresponding to the question text based on the reinforced target text encoding, and outputting the answer.

The invention relates to a traffic network security event extraction method based on machine reading understanding, which performs joint training and optimization on a trigger word prediction module and an argument extraction module by sharing a coding layer of a pre-training language model, so that two tasks promote each other in a shared semantic space. Accurate context constraints are provided for argument role judgment through trigger word recognition, disambiguation of trigger word types is facilitated through argument information, and the deep interactive optimization mechanism enables the model to learn collaborative representation sensitive to the whole event structure. Therefore, the overall accuracy of event extraction and the generalization ability of the model are remarkably improved, and the inherent error propagation problem in a traditional assembly line method is solved.

Systems, devices, and methods discussed herein are directed to generating an answer to an input query using machine reading comprehension techniques and a lattice of supported decision trees. A supported decision tree can be generated from the various decision chains (e.g., a sequence of elements comprising a premise and a decision connected by rhetorical relationships), where the nodes of the decision tree are identified from the plurality of decision chains and ordered based on a set of predefined priority rules. A lattice may include nodes that individually correspond to a respective supported decision tree. Nodes of the lattice may be identified for an input query. The passages corresponding to those nodes may be obtained and an answer for the query may be generated from the obtained passages using machine reading comprehension techniques. The generated answer may be provided in response to the query.

A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and / or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.

This invention proposes a method for extracting entity relations from power technology standards based on multi-turn automatic question answering, comprising: Step 1. Constructing a corpus of power technology standards; Step 2. Constructing information extraction element templates for different types of power technology standards corpus; Step 3. Constructing a question-and-answer corpus of power technology standards based on the information extraction element templates; Step 4. Constructing a text classification module for the power technology standards corpus described in Step 1; Step 5. Automatically constructing a multi-turn question-and-answer and question module by matching the text classification results with the information extraction element templates in Step 4. This module breaks down complex questions into simpler ones and provides step-by-step reasoning answers; Step 6. Constructing a machine reading comprehension module for the power technology standards question-and-answer corpus, which provides step-by-step reasoning answers to the questions automatically constructed in Step 5, thus completing the extraction method of this invention. This invention can effectively alleviate the phenomena of overlapping relations and cross-sentence dependencies in complex texts.

The application discloses a machine reading comprehension event extraction method and device based on template bridging, and medium, the method steps comprise: step S01. Input text and trigger word question template are obtained and combined to form an input instance with a trigger word question prompt template; step S02. Syntax analysis is performed on the input instance to form an adjacency graph, the input text and the trigger word question prompt template are connected according to the adjacency graph to obtain a link graph, and global features are extracted according to the link graph; the global features and semantic features are fused to identify the trigger word and the trigger word type; step S03. A argument question prompt template is generated, the prompt template is combined with the input text to form an input instance with a question prompt template; step S04. Argument extraction is performed to obtain argument and argument type output. The application has the advantages of simple implementation method, high event extraction efficiency and precision, good portability and the like.

The application discloses a machine reading comprehension model training method based on contrast learning long-distance supervision. The method comprises the following steps: 1) for each given <question, answer> pair, first, a text paragraph containing the <question, answer> pair is retrieved from a text corpus, and an answer string is found and positioned in the text paragraph as an annotation of an answer position, thereby obtaining a training instance bag for the <question, answer> pair; and a text paragraph not containing the answer in the <question, answer> pair is taken as a negative example text paragraph; 2) inputting the question and the text paragraph in the training instance into a machine reading comprehension model, obtaining an answer position of the training instance according to a predicted output, and updating a confidence of the training instance according to a probability distribution of an answer start and end position; and 3) training the machine reading comprehension model based on the training instance after the confidence is updated. The application can avoid the prediction shortcut and semantic drift problems caused by the wrong annotated instance.

Improving the efficiency of human or machine reading and recognizing graphics, images, text, symbols, spaces, or objects is a very important issue. For example, fast reading can help people get information quickly. The invention achieves one or more of the following objectives by means of graphics, images, text, symbols, spaces or objects arranged in different arrangements: reducing the speed, frequency, amplitude, distance of eye movement, improving the efficiency of visual recognition, achieving rapid reading, improving the utilization rate of paper and display device, reducing the use of paper, reducing the felling of trees, and protecting the environment.

This invention relates to the field of bridge text information retrieval technology, specifically to a few-sample machine reading comprehension method for bridge detection text. In this method, even with a limited amount of sample data, each sample can be fully utilized. Simulated prediction data can be constructed using a question classification model and an answer prediction model, while actual training data can be obtained through manual annotation. Compared to existing technologies, this method fully develops and utilizes the collected text data. By using simulated training data and text data to be annotated, the answer extraction model undergoes two training sessions after pre-training (Pre-Training) and fine-tuning (Pre-Tuning). Compared to existing training methods that use pre-training + fine-tuning, this method significantly improves the training effect of the answer extraction model even when only identical text data is available.

The application discloses a kind of based on machine reading comprehension's chapter-level event extraction method, device and equipment and storage medium.It is given input chapter and corresponding fill-in-the-blank template, model generates fill-in-the-blank according to the corresponding argument slot in template on the basis of chapter content, realizes the extraction of event argument.The application is aimed at chapter-level event extraction and few-sample event extraction problem, realizes using machine reading comprehension mechanism to traditional event extraction task, provides a kind of fill-in-the-blank template level event extraction mode information fusion method and machine reading comprehension method based on pre-training language model.The application further discloses an end-to-end encoder-decoder model, by using the natural language understanding ability of pre-training language model, excavates the potential knowledge of pre-training language model, can improve the generalization performance of model in few-sample situation, improve the adaptive ability of model on extraction task in different fields.

The application relates to a machine reading comprehension method for electric power professional knowledge, wherein an original question is input into an answer retrieval module for preliminary retrieval to obtain a plurality of first answers and a prediction probability of each first answer; a mother, the original question and the first answer are input into an evidence extraction module to extract an evidence label corresponding to the first answer from text content of the mother; wherein the mother comprises original text, text content in a drawing and text content in a picture; the original question, the first answer and the corresponding evidence label are input into an answer verification module to determine a formal answer with the maximum probability from the plurality of first answers. The application is especially suitable for machine reading comprehension of multiple documents and has good accuracy.

This invention relates to the field of multi-label text classification technology and discloses a few-sample multi-label text classification method based on machine reading comprehension, comprising the following steps: First, the multi-label text dataset is preprocessed, its format is standardized, and labels are added. Next, auxiliary questions are designed based on the labels and combined with text instances to form input data. A RoBERTa model is used as the backbone of the joint encoder to learn the semantic relevance between the text and the questions, and a label graph representing the label relationships is constructed. Through feature fusion, the model is trained to minimize the loss function, and hyperparameters are tuned using a validation set. Finally, the model performance is evaluated on a test set and compared with traditional methods to verify its advantages and component contributions. By transforming multi-label text classification into a machine reading comprehension task, it helps to better capture the semantic relevance between text and labels, significantly improving the accuracy of multi-label text classification.

This application provides a method, apparatus, device, and readable storage medium for reasoning about public opinion risks. It obtains public opinion information by annotating real-time acquired internet information using a pre-trained deep learning model, and then performs reasoning based on this information to derive public opinion risk information. The public opinion risk information and the original information are then stored together. When search keywords are input, no interactive matching is required, and relevant information can be displayed quickly and accurately. The public opinion information derived through corpus reasoning is public opinion risk information and does not alter the original text content, ensuring the accuracy of the public opinion risk information. Therefore, this application is suitable for relatively complex needs, significantly improving the accuracy of judging public opinion risks through machine reading comprehension and the response speed of real-time question answering.

The application discloses a kind of reading comprehension analysis methods based on knowledge graph, wherein the method comprises: obtaining to be processed reading text;Determine the sentence knowledge graph corresponding to each to be processed sentence in the text part respectively, and based on each sentence knowledge graph and the logical relationship word between adjacent to be processed sentence, the text knowledge graph corresponding to the text part is constructed;For each question stem in the question and answer part, based on the text knowledge graph, the answer associated sentence associated with the current question stem in the text part is determined;Based on the answer associated sentence, at least one current candidate answer associated with the current question stem is evaluated to determine the target answer based on the corresponding answer evaluation attribute. Solve the problem that machine reading comprehension is not accurate in predicting the answer corresponding to the question in the reading text in polynomial question and answer, and achieve the effect of improving the accuracy of determining the target answer corresponding to the question in the reading text.

This invention relates to a method for denoising evidence sentences based on post-verification, belonging to the field of machine reading comprehension technology in natural language processing. First, static word vectors are used as the training set for pseudo-evidence labeling. A model is trained on the labeled data, including answer classification and evidence sentence span prediction, and the optimal model is saved. A candidate evidence list is obtained based on the optimal model's predictions. The predicted evidence is then denoised according to the optimal model. The candidate evidence is rearranged based on its score, and the candidate evidence with the highest score is selected as the final evidence sentence. After re-evaluation, the accuracy of the new evidence and the overall accuracy are obtained, and these are compared with the original accuracy to measure the effectiveness of the method. This invention can perform evidence denoising with a low-cost model, achieving excellent results, and can also be applied to various tasks involving evidence extraction.

The invention discloses a virtual restoration method, device and system for a non-intrusive stained machine-readable answer sheet. The method comprises the steps that processing equipment acquires an original scanning image of the machine-readable answer sheet; performing answer recognition on the original scanning image, determining a target machine-readable answer sheet which fails in recognition, and sending the target original scanning image to the terminal equipment; receiving a target original scanning image which is returned by the terminal equipment and carries fouling labeling information, wherein the fouling labeling information is stored in metadata of the target original scanning image; and according to the fouling labeling information, carrying out fouling restoration on the image copy of the original scanning image of the target machine-readable answer sheet. According to the method, automatic labeling and repairing of the stained machine-readable answer sheet are realized, the target original scanning image is reserved as the original certificate, the repairing operation is carried out on the image copy, the repairing track can be traced, original data damage is avoided, and original protection and traceability requirements are balanced.

An electronic device including at least one wireless communication circuit configured to transmit and receive a wireless signal to and from a nearby device positioned around the electronic device; at least one processor operatively connected to the at least one wireless communication circuit; and memory storing instructions. The instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: receive, from a user, an utterance for controlling the electronic device or the nearby device; based on an analysis result of the utterance, obtain information utilized for machine reading comprehension; obtain additional information related to the utterance by performing the machine reading comprehension based on the information; and based on the additional information, provide the user with a response corresponding to the utterance.

The application relates to the technical field of artificial intelligence, and discloses an automatic question answering method and device, computer equipment and a computer readable storage medium, the method comprising: obtaining candidate entities of each word in a to-be-predicted question according to a preset alias dictionary; determining an entity name corresponding to the to-be-predicted question based on a preset entity recognition model and according to the to-be-predicted question and a plurality of candidate entities; determining a triple corresponding to the entity name according to the entity name and a preset graph database; determining a target attribute name corresponding to the to-be-predicted question based on a preset attribute mapping model and according to each attribute name and the to-be-predicted question, and taking an attribute value corresponding to the target attribute name as a question answer of the to-be-predicted question; and implementing semantic coding of entity recognition of a question by the preset entity recognition model and attribute mapping of the question by the attribute mapping model, improving the representation ability and generalization ability of machine reading of a text, and thus improving the accuracy of the preset entity recognition model and the attribute mapping model.

An AI-based story creating method for children's interaction with physical objects, which belongs to the technical field of children's education and entertainment, and comprises the following steps: S1, a user placing a puzzle module (9) having an NFC chip in a designated area of a story machine; S2, the story machine reading a UID code of the puzzle module (9) by means of a built-in NFC reader, and retrieving a preset prompt word on the basis of the UID code; S3, a single-chip microcomputer converting the prompt word into an AI model input; S4, an AI model generating story content on the basis of the prompt word; S5, converting the generated story content into a voice signal by means of a voice processing chip, and generating corresponding visual content by means of a video processing chip; and S6, playing the voice story content by means of a built-in loudspeaker, and simultaneously projecting the corresponding visual content by means of a laser projector, so as to provide dual audio-video experience. The present invention can increase the degree of participation of children during story creation, and effectively attract their attention, thus improving learning interests.

The application discloses a joint event detection and extraction method and device based on end-to-end machine reading comprehension, and belongs to the technical field of information extraction and natural language processing. The joint event detection and extraction method based on end-to-end machine reading comprehension comprises the following steps: S1, data preprocessing, analyzing a data set, traversing all argument roles contained in the data set to form an argument role set; different question templates are designed for different arguments; S2, generation of question and answer pairs, converting event extraction into machine reading comprehension, and generating questions according to the templates designed in the step S1; S3, inputting a given sentence and generated questions into a model of joint event detection and extraction based on end-to-end machine reading comprehension; and S4, heuristic post-processing. The application solves the technical problem that the existing event extraction method based on machine reading comprehension is mainly pipeline type, is prone to error transmission, and cannot effectively utilize the correlation between event types and arguments.

This invention discloses a sentiment cause pair extraction method based on multi-turn machine reading comprehension, belonging to the fields of natural language processing and machine learning. This invention decomposes the sentiment cause pair extraction task using a multi-turn structure, mitigating the label sparsity problem at the clause level rather than the clause pair level by processing the task at the clause level, thus improving the efficiency of document sentiment cause pair extraction. Furthermore, by utilizing question design and the interaction between questions and clauses in machine reading comprehension methods, the relationship between sentiment clauses and cause clauses is fully established. This established relationship enables the extraction of sentiment cause pairs under various complex relationships, broadening its applicability. The extracted candidate document sentiment cause pairs are verified using a multi-turn machine reading comprehension method with a reflective mechanism, and explicit causal semantic information is used to improve the F1 score of the sentiment cause pair extraction task. This invention is applied to the fields of natural language processing and machine learning, solving related technical problems.

The present disclosure relates to a natural language processing method and device, a model training method and device, and a storage medium. The present disclosure pre-trains a machine learning model through each triple, so that the pre-trained machine learning model can seamlessly and naturally process various natural language understanding tasks under the machine reading comprehension paradigm. In addition, because the data format used for model training in the pre-training stage is consistent with the data format used for model training in the fine-tuning stage, the pre-training target and the fine-tuning target are the same, thereby enabling seamless connection between the pre-training stage and the fine-tuning stage. After pre-training the model using a large amount of low-cost data, the pre-trained machine learning model can be calibrated using a small amount of target task data, thereby enabling the general knowledge learned in the pre-training stage to be successfully transferred to the fine-tuned model, and ensuring the accuracy of the fine-tuned model.

A generation unit that takes a question Qi that is a word sequence representing a current question in a dialogue, a document P used to generate an answer Ai to the question Qi, a question history {Qi-1, . . . , Qi-k} that is a set of word sequences representing k past questions, and an answer history {Ai-1, . . . , Ai-k} that is a set of word sequences representing answers to the k questions as inputs, and generates the answer Ai by machine reading comprehension in an extractive mode or a generative mode using pre-trained model parameters is provided.

The application belongs to the field of natural language processing, and particularly relates to a question and answer method based on a gated global attention machine reading comprehension model, which comprises the following steps: obtaining an article to be answered, performing feature extraction on the article, inputting article representation, question representation and option representation into an encoding layer respectively to obtain context information representation of the article, context information representation of the question and context information representation of the option; performing information interaction on the context information representation of the article, the context information representation of the question and the context information representation of the option by using an attention interaction layer to obtain deep interaction information of the question-article-answer; inputting the deep interaction information of the question-article-answer into an answer output layer to obtain a question result; the application helps the model to learn accurate information about the question by introducing global node information, and fully excavates logical information of the article and the question by introducing a three-attention mechanism, thereby improving the efficiency and accuracy of the intelligent question and answer system.

A question answer system for automatically generating an answer to a question of a user according to an exemplary embodiment of the present disclosure includes a user interface configured to receive a video URL address and the question from the user, a video analysis unit configured to download a video through the video URL address, divide the video into a plurality of sections, and recognize a speech, convert the speech into text, and extract text included in an image for each section to generate content of the video as text data, and a machine reading comprehension engine configured to receive the text data from the video analysis unit and extract the answer to the question from the text data.