22 results about "Coreference" patented technology

The invention discloses an anaphora disambiguation method and system based on big language model enhanced text and structured query language generation. The method comprises the following steps: receiving a natural language question of a user, and analyzing and generating structured table field information through mode information; identifying and rewriting fuzzy time expression in the problem; extracting ambiguous entities, and replacing the ambiguous entities with database standard values through semantic matching and fuzzy matching; synthesizing the information to generate a structured query language statement and executing the structured query language statement; and if the execution result is null, automatically triggering an anaphora disambiguation process, performing error correction and re-matching on field values in the statement through a dual matching mechanism, and generating and executing a corrected query statement. According to the method, the problems of fuzzy anaphora, indefinite time expression, low matching accuracy, resource waste and the like in a traditional SQL system are effectively solved through a strategy of combining pre-processing and post-processing, and the accuracy, robustness and execution efficiency of complex query are remarkably improved.

The embodiment of the invention discloses a key anaphora analysis method and device in voice-to-text conversion, a medium and a product. The method comprises the following steps: constructing an interpersonal relationship knowledge graph of a user and splitting according to an interpersonal relationship type; when the text sequence of the user voice conversion contains the third-person pronouns and meets a preset condition, acquiring context information and acquiring anaphora objects of the third-person pronouns, a relationship type between the anaphora objects and the user and the confidence coefficient of the relationship type; sorting and traversing the relation sub-atlases based on the relation type and the confidence coefficient to obtain candidate relation sub-atlases; and when the reference object is successfully matched with any one of the sub-nodes in the candidate relation sub-graph and the first annotation fields of the sub-nodes, acquiring a character sequence containing a correct third-person pronoun based on the second annotation fields of the sub-nodes. According to the method, the anaphora objects of the third-person pronouns are obtained through semantic analysis, and the anaphora objects are matched in a multi-dimensional mode in combination with the interpersonal relationship knowledge graph so as to obtain the correct third-person pronouns.

The invention relates to the technical field of natural language processing, in particular to a risk review method and system for contract terms, and the method comprises the following steps: obtaining a to-be-reviewed contract text, deconstructing sentences of each contract term, and obtaining a term analysis feature set; according to the method, contract terms are disassembled into basic semantic units sentence by sentence, feature details of syntactic tree depth, anaphora distance, logic nested layers and terminology density are extracted, four types of index combinations in a feature set are analyzed through terms, measurement of single-term analysis complexity scores is achieved, score aggregation of the complexity is further analyzed through terms, and the complexity of the contract is analyzed. According to the method, a specific index capable of quantifying the overall understandability risk of a contract is formed, topic clustering and semantic weight distribution are executed on a to-be-examined contract and a standard contract text library at the same time, the actual emphasis condition of each topic is determined, and the topic with large semantic deviation is positioned as a missing risk for targeted marking.

This invention relates to the field of natural language processing technology and discloses a method for resolving referential inconsistencies across long texts in cross-dialogue contexts. The method includes: segmenting the long text into blocks and vectorizing it to form a queryable vector index set; constructing a hybrid label and semantic index by combining a business entity dictionary and historical weakly supervised signals to generate a candidate entity set; inputting the candidate entity set and block summaries into a dual-channel scoring model, where the first channel uses a zero-shot common-reference classifier to generate a probability score, and the second channel is calibrated based on business rules; weighting and fusing the two to generate the final matching score for candidate entity pairs; constructing a weighted entity graph and applying the maximum spanning tree algorithm to solve for the global preliminary referential chain structure; correcting and filling in conflicting entities appearing in the global preliminary referential chain structure by combining entity type, block summary, and context vector information to form a global referential chain set. This invention has the advantages of improving global consistency and accuracy.

The invention provides an electronic data semantic abstracting and evidence sorting method combined with a large language model, and relates to the technical field of artificial intelligence and electronic data analysis, and the method comprises the steps: S1, data collection: collecting text data from a mobile phone, a computer and social platform equipment, and obtaining source data; through semantic understanding and dynamic antagonism analysis of a large language model, deep mining of evidence values is realized, specific meanings of anaphora relationships can be accurately analyzed, key information omission is avoided, potential intentions and emotional tendencies implied in texts are analyzed, real purposes under surface characters are revealed, and the method and the system have a good application prospect. According to the method, contradictory points of different evidences in timelines, fact declaration and logic can be automatically identified, misjudgment caused by inconsistency in an evidence chain is effectively avoided, analysis work is converted into active and deep logical reasoning and verification from passive and shallow information retrieval, and the insight and accuracy of evidence analysis are greatly improved.

The application discloses a text analysis method and device, a storage medium and a program product, relates to the technical field of artificial intelligence, and comprises the following steps: performing character mention (character proper noun, third person pronoun and character generic phrase) detection on a target text, performing coreference resolution on the detected character mention to determine character mentions that point to the same role; for each quotation in the target text, identifying whether the quotation belongs to dialogue content based on a text sequence containing the quotation and context before and after the quotation, and identifying the speaker and the listener of the quotation when the quotation belongs to the dialogue content; if the quotation belongs to the dialogue content, identifying the first person pronoun and the second person pronoun in the quotation, pointing the identified first person pronoun to the same role as the speaker of the quotation, and pointing the identified second person pronoun to the same role as the listener of the quotation. The application improves the accuracy of role identification.

This invention discloses a method for generating multi-dimensional event profiles across multiple texts. For a given event type, it searches for relevant texts describing that type of event and segments each text into sentence blocks, identifying text blocks such as basic information, event sequence, causes and effects, and comments from various parties. Next, it extracts events from the text blocks describing basic information, obtaining basic elements such as event type, occurrence / end time, location, and actors. Then, it identifies sub-events from the text blocks describing the event sequence and sorts them chronologically to form an event timeline. Finally, it performs coreference resolution on events from different texts to form a complete event profile. This method can correlate and fuse event information distributed across multiple texts, extract complex elements such as causes and effects, and comments from various parties, and can discover sub-events such as the early developments, main processes, and subsequent actions of an event, enabling the analysis of various elements and the evolution of major events.

The application relates to the technical field of natural language processing, and proposes a causal inference method fusing co-reference relations and external knowledge enhancement, which comprises the following steps: extracting event words in a text as mask target words and performing a mask operation on non-event words, using an improved BERT model to predict the masked event words by context reconstruction in a pre-training stage; extracting co-reference event pairs of cause events and result events to obtain co-reference features of the co-reference events; extracting potential indirect events associated with the cause / result events from an external knowledge base to construct an external knowledge base causal graph, constructing a structured semantic graph, and performing node feature fusion; performing nonlinear transformation on the co-reference features and the fused node features; fusing the context semantic features and the external knowledge base features to obtain comprehensive feature representation; and inputting the comprehensive feature representation into a prediction layer to obtain the final prediction result of the event pair relation.

The present application relates to the technical field of natural language processing, in particular to a contract clause risk review method and system, comprising the following steps: obtaining a to-be-reviewed contract text, deconstructing the sentences of each contract clause to obtain a clause analysis feature set. The present application extracts the feature details of the syntactic tree depth, the reference distance, the logical nesting layer number and the professional term density by disassembling the contract clauses into basic semantic units sentence by sentence, uses the four types of index combinations in the clause analysis feature set to realize the measurement of the single clause analysis complexity score, and further aggregates the clause analysis complexity score to form specific indexes capable of quantifying the overall understandability risk of the contract. Meanwhile, the to-be-reviewed contract and the standard contract text library are executed for theme clustering and semantic weight distribution to clearly understand the actual focus of each theme, and the themes with larger semantic deviation are marked as missing risks.

A coreference resolution method, and a method and apparatus for training a coreference resolution model are provided. The coreference resolution method includes: acquiring a current utterance to be processed; inputting the current utterance into a coreference resolution detection sub-model to obtain a predicted insertion position where there is a semantic absence of the current utterance and / or a predicted deletion position of a word to be replaced; and inputting the predicted insertion position and / or the predicted deletion position of the current utterance, and a historical conversation corresponding to the current utterance into a resolution completion sub-model of the coreference resolution model to obtain a predicted position in the historical utterance of a word corresponding to the semantic absence at the predicted insertion position and / or a predicted position in the historical utterance of a replacement word corresponding to the word to be replaced at the predicted deletion position.

The present disclosure provides a text correction model training method, a text correction method and a device, and relates to the technical field of computers, in particular to the field of natural language processing. The text correction model training method comprises: obtaining a sample sentence and an actual reference object of a pronoun in the sample sentence, and obtaining a historical sentence of the sample sentence; performing a first specified length mask on the pronoun in the sample sentence; the first specified length is determined based on the character length of the candidate noun in the historical sentence; and training the text correction model based on the sample sentence, the historical sentence, the masked sample sentence and the actual reference object of the pronoun until the text correction model converges. The technical solution of the present disclosure can obtain a text correction model with high precision, thereby improving the accuracy of text correction and improving the user experience.

The invention provides a text rewriting method and device for multiple rounds of dialogues, a medium and equipment. In the method, keywords in each dialogue text can be dynamically tracked in multiple rounds of dialogues between a customer service and a user, and a preset basic keyword list is updated and maintained, so that contents omitted or referred in a to-be-rewritten text can be provided for rewriting the to-be-rewritten text through the basic keyword list, and the rewriting efficiency of the to-be-rewritten text is improved. Therefore, the problems of omission and anaphora resolution under long dependence can be solved, and the accuracy of rewriting the to-be-rewritten text is improved. Meanwhile, index entries on which the keywords depend can be marked during keyword tracking, so that the farthest upper text index entry which needs to depend can be used as an upper bound during text rewriting, and a dependent text used for text rewriting is intercepted from historical dialogue texts of multiple rounds of dialogues between a customer service and a user; therefore, the context understanding complexity of the text generation model can be reduced, and irrelevant information noise is reduced.

Systems and techniques for linguistically-driven automated text formatting are described herein. Data representing the linguistic structure of input text may be received from Natural Language Processing (NLP) Services, including but not limited to constituents, dependencies, and coreference relationships. A text model of the input text may be built using the linguistic components and relationships. Cascade rules may be applied to the text model to generate a cascaded text data structure. Cascaded data may be displayed on a range of media, including a phone, tablet, laptop, monitor, VR / AR devices. Cascaded data may be presented in dual screen formats to promote more accurate and efficient reading comprehension, greater ease in teaching native and foreign language grammatical structures, and tools for remediation of reading-related disabilities.

The invention discloses an anaphora resolution method and device.The anaphora resolution method comprises the steps that a to-be-processed text is obtained, and the positions of pronouns and entity words in the to-be-processed text are marked in the to-be-processed text; for each pronoun in the to-be-processed text, executing the following processing: based on the to-be-processed text, obtaining a mask matrix of a substitute word, the mask matrix including information of a preceding word of the pronoun in the to-be-processed text, and the preceding word being any entity word in front of the pronoun in the to-be-processed text; based on the mask matrix, obtaining distance information between the substitute word and each preceding word; and determining entity words referred by the pronouns in the to-be-processed text based on the word vectors and the distance information of the to-be-processed text.

A natural language processing method, system, device, and computer readable medium using abstract meaning representation (AMR) coreference resolution. The method can include receiving an input representation, wherein the input representation can include an AMR graph. The method can further include encoding the input representation via a variational graph autoencoder (VGAE). In addition, the method can include determining one or more concept identifiers from the encoded VGAE input representation and determining one or more coreference clusters from the determined concept identifiers. In addition, the method can include determining one or more first embedding values for one or more nodes of the input representation. Further, the step of encoding the input representation can further include encoding one or more nodes of the input representation into a first representation having contextual information via a local graph encoder.

Systems and techniques for linguistically-driven automated text formatting are described herein. Data representing the linguistic structure of input text may be received from Natural Language Processing (NLP) Services, including but not limited to constituents, dependencies, and coreference relationships. A text model of the input text may be built using the linguistic components and relationships. Cascade rules may be applied to the text model to generate a cascaded text data structure. Cascaded data may be displayed on a range of media, including a phone, tablet, laptop, monitor, VR / AR devices. Cascaded data may be presented in dual screen formats to promote more accurate and efficient reading comprehension, greater ease in teaching native and foreign language grammatical structures, and tools for remediation of reading-related disabilities.

The application discloses a kind of reference resolution method and device, it is related to natural semantic processing technical field.The specific embodiment of the method includes obtaining the current sentence containing target pronoun, constructs the first matrix corresponding to current sentence;At least one previous sentence of current sentence is obtained, and the second matrix corresponding to at least one previous sentence is constructed;According to the first matrix and the second matrix, the feature matrix corresponding to current sentence is generated, and the feature matrix is used to represent the correlation degree of each first word in current sentence and second word in previous sentence;Feature matrix is input into semantic segmentation model, and the semantic segmentation result corresponding to feature matrix is obtained;According to semantic segmentation result, determine the reference word corresponding to target pronoun.The embodiment can accurately carry out reference resolution, effectively improve the fluency of man-machine interactive dialogue.

The invention discloses a context anaphora resolution method and system based on dialogue structure perception, and relates to the field of natural language processing, and the method comprises the steps: obtaining multiple rounds of dialogue corpora, storing dialogue entities in a shared memory pool and a private memory pool respectively, clearly distinguishing entities with effective individual cognition and global common-known entities, and obtaining an entity with effective individual cognition and a global common-known entity; therefore, anaphora ambiguity caused by confusion of knowledge ranges of different speakers is eliminated; when anaphora resolution is carried out, through multi-layer structure signal fusion such as a significance recursion updating mechanism driven by a dialogue structure, semantic role consistency judgment and round correlation attenuation modeling, an interpretable cognitive compatibility scoring system is established, and an entity selection mechanism jointly constrained by multi-dimensional information is formed. Therefore, by introducing a dialogue structure perceived double-domain entity memory modeling mechanism, pronoun forepointing accuracy and robustness in complex scenes such as long dialogue, cross-speaker and multi-round interaction are effectively improved.

A natural language processing method, system, device, and computer readable medium using abstract meaning representation (AMR) coreference resolution. The method can include receiving an input representation, wherein the input representation can include an AMR graph. The method can further include encoding the input representation via a variational graph autoencoder (VGAE). In addition, the method can include determining one or more concept identifiers from the encoded VGAE input representation and determining one or more coreference clusters from the determined concept identifiers. In addition, the method can include determining one or more first embedding values for one or more nodes of the input representation. Further, the step of encoding the input representation can further include encoding one or more nodes of the input representation into a first representation having contextual information via a local graph encoder.

The present application relates to the field of intelligent dialogue, and relates to a multi-task learning dialogue method supporting anaphora resolution and polysemy, wherein an anaphora resolution model, a polysemy model and a multi-task learning model are trained through training corpus, historical dialogue and current dialogue are spliced into context representation text, anaphors, zero pronouns and anaphora in the text are labeled through the anaphora resolution model, the anaphora probability of the anaphors and the anaphora probability of the zero pronouns and the anaphora are calculated, and whether the anaphora can be resolved is judged according to a set threshold, if the anaphora can be resolved, the anaphors or the zero pronouns are replaced or supplemented into corresponding anaphora to form a replacement text, the intent key components in the replacement text are extracted through the polysemy model, the domain, intent and slot of each intent key component are obtained through the multi-task learning model, and are sent into a dialogue management module to obtain the dialogue action at this moment, so that the intent can be accurately understood.

The invention belongs to the technical field of man-machine dialogue, and particularly relates to an intelligent dialogue management method and system based on context understanding, a reference relation confirmation mechanism is introduced after semantic analysis, comprehensive matching is carried out by utilizing vocabulary overlapping proportion and entity category consistency, and historical entities pointed by fuzzy expression are accurately recognized; and further judging whether the current request continues the existing intention or not by comparing the consistency of the operation action and the historical target demand and combining the semantic matching degree of weighted accumulation. According to the method, cross-round semantic accurate association and intention continuity judgment are realized, the problems of unknown anaphora and intention misjudgment caused by information splitting in multiple rounds of dialogues are effectively solved, and the context understanding ability and interaction naturalness of a system are remarkably improved.