CN113590776A - Text processing method and device based on knowledge graph, electronic equipment and medium - Google Patents
Text processing method and device based on knowledge graph, electronic equipment and medium Download PDFInfo
- Publication number
- CN113590776A CN113590776A CN202110698838.2A CN202110698838A CN113590776A CN 113590776 A CN113590776 A CN 113590776A CN 202110698838 A CN202110698838 A CN 202110698838A CN 113590776 A CN113590776 A CN 113590776A
- Authority
- CN
- China
- Prior art keywords
- answers
- questions
- current round
- text
- viewpoint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000002372 labelling Methods 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 13
- 239000000126 substance Substances 0.000 claims 1
- 238000005065 mining Methods 0.000 abstract description 23
- 230000000694 effects Effects 0.000 abstract description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000013135 deep learning Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008451 emotion Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 239000000969 carrier Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010225 co-occurrence analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a method, a device, electronic equipment and a medium for processing texts based on a knowledge graph, and relates to the technical fields of deep learning and the knowledge graph in the technical field of artificial intelligence. The specific implementation scheme is as follows: the method comprises the steps of obtaining a text to be mined and a plurality of preset viewpoint elements, wherein the viewpoint elements correspond to multiple rounds of questions one by one, generating query words corresponding to the current round of questions according to the viewpoint elements corresponding to the current round of questions, generating answers corresponding to the current round of questions according to the text to be mined, the query words corresponding to the current round of questions and a reading understanding model, and generating viewpoint element labeling results corresponding to the text to be mined according to the query words and the answers corresponding to the multiple rounds of questions. According to the text processing method based on the knowledge graph, the one-to-one corresponding viewpoint element labeling results among the viewpoint elements of the text to be mined can be obtained according to the multi-turn multi-answer reading understanding model, the problem that the viewpoint elements cannot correspond to each other under the use scene of multiple viewpoints, particularly nested viewpoints, included in the text is solved, and the viewpoint mining effect is improved.
Description
Technical Field
The present disclosure relates to the field of deep learning and knowledge graph technology in the field of artificial intelligence technology, and in particular, to a method, an apparatus, an electronic device, and a medium for processing a text based on a knowledge graph.
Background
Viewpoint mining, i.e., recognizing the viewpoint from the text, includes a viewpoint holder (whose viewpoint may be a person, an organization, etc.), a viewpoint target (for what viewpoint may be a person, an organization, an event, etc.), a viewpoint issue time, and the like.
In the related art, viewpoint mining is generally formalized as a sequence labeling task, semantic role labeling is performed on a text by adopting a sequence labeling model, and based on the semantic role labeling, which segments in the text are viewpoint holders and viewpoint targets can be determined. However, when a text contains a plurality of viewpoints, particularly nested viewpoints, the above method cannot further determine which viewpoint target corresponds to which viewpoint holder, and the like, and the mining effect is poor.
Disclosure of Invention
A method, an apparatus, an electronic device and a medium for processing a text based on a knowledge graph are provided.
According to a first aspect, there is provided a method of knowledge-graph based text processing, comprising: acquiring a text to be mined and a plurality of preset viewpoint elements, wherein the viewpoint elements correspond to a plurality of rounds of questions and answers one by one; generating query words corresponding to the current round of questions and answers according to the viewpoint elements corresponding to the current round of questions and answers; generating answers corresponding to the current round of questions and answers according to the text to be mined, the query words corresponding to the current round of questions and answers and a reading understanding model; and generating a viewpoint element labeling result corresponding to the text to be mined according to the plurality of query words and the plurality of answers corresponding to the plurality of rounds of queries.
According to a second aspect, there is provided a knowledge-graph based text processing apparatus comprising: the system comprises an acquisition module, a search module and a search module, wherein the acquisition module is used for acquiring a text to be mined and a plurality of preset viewpoint elements, and the viewpoint elements correspond to a plurality of rounds of questions and answers one by one; the first generation module is used for generating query words corresponding to the current round of questions and answers according to the viewpoint elements corresponding to the current round of questions and answers; the second generation module is used for generating answers corresponding to the current round of questions and answers according to the text to be mined, the query words corresponding to the current round of questions and the reading understanding model; and the third generation module is used for generating a viewpoint element labeling result corresponding to the text to be mined according to the plurality of query words and the plurality of answers corresponding to the plurality of rounds of queries and answers.
According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of knowledge-graph based text processing of the first aspect of the disclosure.
According to a fourth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of knowledge-graph based text processing according to the first aspect of the present disclosure.
According to a fifth aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method of knowledge-graph based text processing according to the first aspect of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic flow diagram of a method of knowledge-graph based text processing according to a first embodiment of the present disclosure;
FIG. 2 is a flow diagram of a method of knowledge-graph based text processing according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a multi-turn multi-answer reading understanding model of the method for processing a knowledge-graph-based text according to the embodiment of the disclosure;
FIG. 4 is a diagram illustrating a multi-task learning framework principle of a method for knowledge-graph based text processing according to an embodiment of the present disclosure;
FIG. 5 is a block diagram of a knowledge-graph based text processing apparatus according to a first embodiment of the present disclosure;
FIG. 6 is a block diagram of a knowledge-graph based text processing apparatus according to a second embodiment of the present disclosure;
FIG. 7 is a block diagram of an electronic device for implementing the knowledge-graph based text processing method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence. At present, the AI technology has the advantages of high automation degree, high accuracy and low cost, and is widely applied.
Deep Learning (DL) is a new research direction in the field of Machine Learning (ML), and learns the intrinsic rules and representation levels of sample data, and information obtained in the Learning process is helpful for interpreting data such as text, images, and sound. The final aim of the method is to enable the machine to have the analysis and learning capability like a human, and to recognize data such as characters, images and sounds. As for specific research content, the method mainly comprises a neural network system based on convolution operation, namely a convolution neural network; a multilayer neuron based self-coding neural network; and pre-training in a multilayer self-coding neural network mode, and further optimizing the deep confidence network of the neural network weight by combining the identification information. Deep learning has achieved many achievements in search technology, data mining, machine learning, machine translation, natural language processing, multimedia learning, speech, recommendation and personalization technologies, and other related fields. The deep learning enables the machine to imitate human activities such as audio-visual and thinking, solves a plurality of complex pattern recognition problems, and makes great progress on the artificial intelligence related technology.
Knowledge map (KG) is known as Knowledge domain visualization or Knowledge domain mapping map in the book intelligence world, and is a series of different graphs displaying the relationship between the Knowledge development process and the structure, and the Knowledge resources and the carriers thereof are described by using visualization technology, and Knowledge and the mutual relation between the Knowledge resources, the Knowledge resources and the carriers are mined, analyzed, constructed, drawn and displayed. The knowledge graph is a modern theory which achieves the aim of multi-discipline fusion by combining theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology introduction analysis, co-occurrence analysis and the like and utilizing the visualized graph to vividly display the core structure, development history, frontier field and overall knowledge framework of the subjects, and can provide practical and valuable reference for subject research.
Opinion Mining (OM), also called text Opinion Mining or emotion analysis, is to mine and analyze emotion information such as the subject, Opinion holder, subjective and objective properties, emotion attitude, etc. of text information, and further identify the emotional tendency of subjective text. Opinion mining provides significant value in many areas.
The method, apparatus, electronic device, and medium for processing a text based on a knowledge graph according to embodiments of the present disclosure are described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method of knowledge-graph based text processing according to a first embodiment of the present disclosure.
As shown in fig. 1, the method for processing a text based on a knowledge-graph according to the embodiment of the present disclosure may specifically include the following steps:
s101, acquiring a text to be mined and a plurality of preset viewpoint elements, wherein the viewpoint elements correspond to a plurality of rounds of questions and answers one by one.
Specifically, the executing body of the method for processing text based on a knowledge graph according to the embodiments of the present disclosure may be the text processing apparatus based on a knowledge graph provided by the embodiments of the present disclosure, and the text processing apparatus based on a knowledge graph may be a hardware device having a data information processing capability and/or software necessary for driving the hardware device to operate. Alternatively, the execution body may include a workstation, a server, a computer, a user terminal, and other devices. The user terminal includes, but is not limited to, a mobile phone, a computer, an intelligent voice interaction device, an intelligent household appliance, a vehicle-mounted terminal, and the like.
In the embodiment of the present disclosure, text to be mined is text waiting for a viewpoint element to be mined. The text to be mined can be acquired through image recognition, network transmission and other modes. For example, when a text to be mined is acquired by adopting an image recognition mode, the equipment is provided with an image acquisition device and a text recognition device, the image acquisition device can be a camera and the like, and the text recognition device performs text recognition on an image acquired by the image acquisition device to obtain the text to be mined. Or, when the text to be mined is acquired by adopting a network transmission mode, the equipment is provided with a networking device, and network transmission can be carried out with other equipment or a server through the networking device. What viewpoint elements to be mined are preset, that is, a plurality of viewpoint elements are preset, and a user can set the viewpoint elements as required.
Acquiring a text to be mined and a plurality of preset viewpoint elements, wherein the plurality of viewpoint elements specifically include but are not limited to at least two of the following elements: view owner, view target, view publication time, etc. The plurality of viewpoint elements and the plurality of rounds of questions and answers are in one-to-one correspondence, namely the viewpoint elements and the target information of the corresponding questions and answers are consistent, and specific corresponding information can be obtained through one round of questions and answers. For example, the viewpoint elements for the first round of question answering are viewpoint holders, the viewpoint elements for the second round of question answering are viewpoint targets, and the viewpoint elements for the third round of question answering are viewpoint posting time.
And S102, generating the query words corresponding to the current round of questions according to the viewpoint elements corresponding to the current round of questions.
Specifically, before each round of question answering, the query word query corresponding to the current round of question answering is generated according to the viewpoint elements corresponding to the current round of question answering.
S103, generating answers corresponding to the current round of questions and answers according to the texts to be mined, the query words corresponding to the current round of questions and answers and the reading understanding model.
Specifically, the text to be mined obtained in step S101 and the query word query corresponding to the current round of question and answer generated in step S102 are input into the corresponding reading understanding model, and the reading understanding model outputs the answer corresponding to the current round of question and answer.
And S104, generating a viewpoint element labeling result corresponding to the text to be mined according to the plurality of query words and the plurality of answers corresponding to the plurality of rounds of queries.
Specifically, information fusion is performed on the query words corresponding to the multiple rounds of questions and answers generated in step S102, and a viewpoint element labeling result corresponding to the text to be mined is generated. For example, the query word corresponding to the first round of questions and answers is the viewpoint holder, the answers corresponding to the first round of questions and answers is viewpoint holder 1, viewpoint holder 2, … …, the query word corresponding to the ith reading understanding model of the second round of questions and answers is viewpoint target 1, viewpoint target 2, … …, the query word corresponding to the kth reading understanding model of the third round of questions and answers is viewpoint publishing time 1, viewpoint publishing time 2, … … of the viewpoint holder i, the viewpoint element tagging result corresponding to the generated text to be mined may be: the viewpoint issuing time of the viewpoint holder 1 with respect to the viewpoint target j is the viewpoint issuing time m, … ….
In summary, in the text processing method based on the knowledge graph according to the embodiment of the disclosure, a text to be mined and a plurality of preset viewpoint elements are obtained, the viewpoint elements correspond to a plurality of rounds of questions and answers one to one, a query word corresponding to the current round of questions and answers is generated according to the viewpoint elements corresponding to the current round of questions and answers, an answer corresponding to the current round of questions and answers is generated according to the text to be mined, the query word corresponding to the current round of questions and a reading understanding model, and a viewpoint element labeling result corresponding to the text to be mined is generated according to the query words and the answers corresponding to the plurality of rounds of questions and answers. According to the text processing method based on the knowledge graph, the one-to-one corresponding viewpoint element labeling results among the viewpoint elements of the text to be mined can be obtained according to the multi-turn multi-answer reading understanding model, the problem that the viewpoint elements cannot correspond to each other under the use scene of multiple viewpoints, particularly nested viewpoints, included in the text is solved, and the viewpoint mining effect is improved.
FIG. 2 is a flow diagram of a method of knowledge-graph based text processing according to a second embodiment of the present disclosure.
As shown in fig. 2, based on the embodiment shown in fig. 1, the method for processing a text based on a knowledge-graph according to the embodiment of the present disclosure may specifically include the following steps:
s201, acquiring a text to be mined and a plurality of preset viewpoint elements, wherein the viewpoint elements correspond to a plurality of rounds of questions and answers one by one.
Specifically, step S201 in this embodiment is the same as step S101 in the above embodiment, and is not described again here.
The step S102 "generating the query word corresponding to the current round answer from the viewpoint element corresponding to the current round answer" in the above embodiment may specifically include the following steps S202 and S203.
And S202, if the current round of question answering is the first round of question answering, determining the viewpoint elements corresponding to the current round of question answering as the question words corresponding to the current round of question answering.
Specifically, before each round of question answering, whether the current round of question answering is the first round of question answering or not is judged, and if the current round of question answering is the first round of question answering, the viewpoint elements corresponding to the current round of question answering are determined as the question words corresponding to the current round of question answering. For example, if the current round of answers is the first round of answers, the viewpoint element "viewpoint holder" of the current round of answers (i.e., the first round of answers) is determined as the query word of the current round of answers (i.e., the first round of answers), i.e., the query word of the first round of answers is "viewpoint holder".
And S203, if the current round of question answering is not the first round of question answering, generating the question words corresponding to the current round of question answering according to the answer corresponding to the previous round of question answering, the question words corresponding to the previous round of question answering and the viewpoint elements corresponding to the current round of question answering.
Specifically, if the current round of answers is not the first round of answers, the query word corresponding to the current round of answers cannot be determined only according to the view point elements, information corresponding to the previous round of answers, that is, the answer corresponding to the previous round of answers and the query word corresponding to the previous round of answers, needs to be obtained, and the query word corresponding to the current round of answers is generated according to the answer corresponding to the previous round of answers, the query word corresponding to the previous round of answers and the view point elements corresponding to the current round of answers. For example, if the current round of answers is the second round of answers, the viewpoint target of the viewpoint holder i is generated from the answer "viewpoint holder 1, viewpoint holder 2, … …" corresponding to the first round of answers, the query word "viewpoint holder" corresponding to the first round of answers, and the viewpoint element "viewpoint target" corresponding to the second round of answers, which is the current round of answers. For another example, if the current round of questions is the third round of questions, the question word "the viewpoint issue time of the viewpoint holder i to the viewpoint target j" corresponding to the current round of questions is generated from the answer "the viewpoint target 1, the viewpoint target 2, … …" corresponding to the second round of questions which is the previous round of questions, the viewpoint target of the viewpoint holder i "corresponding to the second round of questions which is the previous round of questions, and the viewpoint element" the viewpoint issue time "corresponding to the third round of questions which is the current round of questions.
And S204, generating a semantic role labeling result according to the text to be mined and the sequence labeling model.
Specifically, semantic role labeling and view mining have strong relation on task form and task content, so that a semantic role labeling task can be introduced, and view mining and semantic role labeling are trained together in a multi-task learning mode. Inputting the text to be mined acquired in step S201 into the sequence annotation model, and outputting a semantic role annotation result by the sequence annotation model, where the semantic role annotation result specifically includes but is not limited to: verb, subject, object, time, etc.
Step S103 "generating the answer corresponding to the current round of question and answer according to the text to be mined, the query word corresponding to the current round of question and the reading understanding model" in the above embodiment may specifically include the following step S205.
And S205, generating answers corresponding to the current round of questions and answers according to the semantic role labeling result, the text to be mined, the query words corresponding to the current round of questions and answers and the reading understanding model.
Specifically, the semantic role labeling result obtained in step S204 and the text to be mined obtained in step S101 are subjected to vector representation cascade, and are input to the corresponding reading understanding model together with the query word corresponding to the current round of question generated in step S102, and the reading understanding model outputs the answer corresponding to the current round of question, that is, the semantic role labeling result obtained in step S204 is used as the input of each round of question, so that the effect of viewpoint mining is further improved.
And S206, generating a viewpoint element labeling result corresponding to the text to be mined according to the plurality of query words and the plurality of answers corresponding to the plurality of rounds of queries.
Specifically, step S206 in this embodiment is the same as step S104 in the above embodiment, and is not described here again.
In summary, in the text processing method based on the knowledge graph according to the embodiment of the disclosure, a text to be mined and a plurality of preset viewpoint elements are obtained, the viewpoint elements correspond to a plurality of rounds of questions and answers one to one, a query word corresponding to the current round of questions and answers is generated according to the viewpoint elements corresponding to the current round of questions and answers, an answer corresponding to the current round of questions and answers is generated according to the text to be mined, the query word corresponding to the current round of questions and a reading understanding model, and a viewpoint element labeling result corresponding to the text to be mined is generated according to the query words and the answers corresponding to the plurality of rounds of questions and answers. According to the text processing method based on the knowledge graph, the one-to-one corresponding viewpoint element labeling results among the viewpoint elements of the text to be mined can be obtained according to the multi-turn multi-answer reading understanding model, the problem that the viewpoint elements cannot correspond to each other under the use scene of multiple viewpoints, particularly nested viewpoints, included in the text is solved, and the viewpoint mining effect is improved. Meanwhile, the viewpoint mining and the semantic role labeling are trained together in a multi-task learning mode, so that the viewpoint mining effect is further improved.
For clarity of explanation of the method for processing a knowledge-graph based text according to the embodiment of the present disclosure, the following description is made in detail with reference to fig. 3 to 4.
Fig. 3 is a schematic diagram of a multi-turn multi-answer reading understanding model principle of a knowledge-graph-based text processing method according to an embodiment of the present disclosure. As shown in fig. 3, three rounds of questions and answers are taken as an example. In the first round of question and answer, the input text to be mined is the original input text, the query word query is a viewpoint holder, and the answer is a viewpoint holder 1 and a viewpoint holder 2. In the second round of question answering, a reading understanding model is constructed for each answer of the first round of question answering, the text to be mined input by the ith reading understanding model is still the original text, the query word query is the viewpoint target of a viewpoint holder i, and the answers are a viewpoint target 1 and a viewpoint target 2. The third round of question answering is analogized. According to the multi-round and multi-answer reading understanding model, one-to-one corresponding viewpoint element labeling results among viewpoint elements of the text to be mined can be obtained, the problem that the viewpoint elements cannot correspond to each other under the use scene of multiple viewpoints, particularly nested viewpoints, included in the text is solved, and the viewpoint mining effect is improved.
Fig. 4 is a schematic diagram of a multi-task learning framework principle of a knowledge-graph-based text processing method according to an embodiment of the present disclosure, and as shown in fig. 4, viewpoint mining and semantic role labeling are trained together in a multi-task learning manner, and simultaneously, a vector representation of a semantic role labeling result output by the semantic role labeling task is input to each round of question and answer of the viewpoint mining task, and is cascaded with a vector representation of a text to be mined, and is input to a reading understanding model corresponding to each round of question and answer together with a query word query corresponding to each round of question and answer in step, a viewpoint element labeling result corresponding to the text to be mined is output, and viewpoint mining and semantic role labeling are trained together in a multi-task learning manner, so that an effect of viewpoint mining is further improved.
Fig. 5 is a block diagram of a knowledge-graph based text processing apparatus according to a first embodiment of the present disclosure.
As shown in fig. 5, a knowledge-graph based text processing apparatus 500 according to an embodiment of the present disclosure includes: an acquisition module 501, a first generation module 502, a second generation module 503, and a third generation module 504.
An obtaining module 501, configured to obtain a text to be mined and a plurality of preset viewpoint elements; the plurality of viewpoint elements correspond to the plurality of rounds of questions and answers one by one.
The first generating module 502 is configured to generate query words corresponding to the current round of answers according to the viewpoint elements corresponding to the current round of answers.
The second generating module 503 is configured to generate an answer corresponding to the current round of question and answer according to the text to be mined, the query word corresponding to the current round of question and answer, and the reading understanding model.
The third generating module 504 is configured to generate a viewpoint element labeling result corresponding to the text to be mined according to the multiple query words and the multiple answers corresponding to the multiple rounds of queries and answers.
It should be noted that the above explanation of the embodiment of the method for processing a text based on a knowledge graph is also applicable to the apparatus for processing a text based on a knowledge graph in the embodiment of the present disclosure, and the specific process is not described herein again.
In summary, the knowledge graph-based text processing apparatus according to the embodiment of the present disclosure obtains a text to be mined and a plurality of preset viewpoint elements, where the viewpoint elements correspond to a plurality of rounds of questions and answers one to one, generates a query word corresponding to the current round of questions and answers according to the viewpoint elements corresponding to the current round of questions and answers, generates an answer corresponding to the current round of questions and answers according to the text to be mined, the query word corresponding to the current round of questions and a reading understanding model, and generates a viewpoint element labeling result corresponding to the text to be mined according to the query words and answers corresponding to the plurality of rounds of questions and answers. According to the knowledge graph-based text processing device, the one-to-one corresponding viewpoint element labeling results among the viewpoint elements of the text to be mined can be obtained according to the multi-round and multi-answer reading understanding model, the problem that the viewpoint elements cannot correspond to each other under the use scene of multiple viewpoints, particularly nested viewpoints, included in the text is solved, and the viewpoint mining effect is improved.
Fig. 6 is a block diagram of a knowledge-graph based text processing apparatus according to a second embodiment of the present disclosure.
As shown in fig. 6, a knowledge-graph based text processing apparatus 600 according to an embodiment of the present disclosure includes: an acquisition module 601, a first generation module 602, a second generation module 603, and a third generation module 6046.
The obtaining module 601 has the same structure and function as the obtaining module 701 in the previous embodiment; the first generation module 602 has the same structure and function as the first generation module 702 in the previous embodiment. The second generating module 603 has the same structure and function as the second generating module 703 in the previous embodiment. The third generation module 604 has the same structure and function as the third generation module 704 in the previous embodiment.
Further, the first generating module 602 may specifically include: the determining unit 6021 is configured to determine, when the current round of questions is the first round of questions, the viewpoint element corresponding to the current round of questions as a question word corresponding to the current round of questions.
Further, the first generating module 602 may specifically include: the first generating unit 6022 is configured to generate the query word corresponding to the current round of answers according to the answer corresponding to the previous round of answers, the query word corresponding to the previous round of answers, and the viewpoint element corresponding to the current round of answers if the current round of answers is not the first round of answers.
Further, the apparatus 600 for processing text based on a knowledge-graph according to the embodiment of the present disclosure may further include: the fourth generation module is used for generating semantic role labeling results according to the text to be mined and the sequence labeling model; the second generating module 603 may specifically include: and the second generation unit is used for generating answers corresponding to the current round of questions and answers according to the semantic role labeling result, the text to be mined, the query words corresponding to the current round of questions and the reading understanding model.
Further, the second generating unit may specifically include: and the input subunit is used for inputting the semantic role labeling result, the text to be mined and the query words corresponding to the current round of questions and answers to the reading understanding model to obtain the answers corresponding to the current round of questions and answers.
Wherein the plurality of perspective elements include, but are not limited to, at least two of the following elements: view holder, view target, and view publication time.
It should be noted that the above explanation of the embodiment of the method for processing a text based on a knowledge graph is also applicable to the apparatus for processing a text based on a knowledge graph in the embodiment of the present disclosure, and the specific process is not described herein again.
In summary, the knowledge graph-based text processing apparatus according to the embodiment of the present disclosure obtains a text to be mined and a plurality of preset viewpoint elements, where the viewpoint elements correspond to a plurality of rounds of questions and answers one to one, generates a query word corresponding to the current round of questions and answers according to the viewpoint elements corresponding to the current round of questions and answers, generates an answer corresponding to the current round of questions and answers according to the text to be mined, the query word corresponding to the current round of questions and a reading understanding model, and generates a viewpoint element labeling result corresponding to the text to be mined according to the query words and answers corresponding to the plurality of rounds of questions and answers. According to the knowledge graph-based text processing device, the one-to-one corresponding viewpoint element labeling results among the viewpoint elements of the text to be mined can be obtained according to the multi-round and multi-answer reading understanding model, the problem that the viewpoint elements cannot correspond to each other under the use scene of multiple viewpoints, particularly nested viewpoints, included in the text is solved, and the viewpoint mining effect is improved. Meanwhile, the viewpoint mining and the semantic role labeling are trained together in a multi-task learning mode, so that the viewpoint mining effect is further improved.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the electronic device 700 includes a computing unit 701, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
A number of components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.
According to an embodiment of the present disclosure, there is also provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of knowledge-graph based text processing shown according to the above-described embodiment of the present disclosure.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (15)
1. A method for processing text based on knowledge graph includes:
acquiring a text to be mined and a plurality of preset viewpoint elements, wherein the viewpoint elements correspond to a plurality of rounds of questions and answers one by one;
generating query words corresponding to the current round of questions and answers according to the viewpoint elements corresponding to the current round of questions and answers;
generating answers corresponding to the current round of questions and answers according to the text to be mined, the query words corresponding to the current round of questions and answers and a reading understanding model; and
and generating a viewpoint element labeling result corresponding to the text to be mined according to the plurality of query words and the plurality of answers corresponding to the plurality of rounds of queries.
2. The text processing method according to claim 1, wherein the generating of the query word corresponding to the current round of answers from the viewpoint elements corresponding to the current round of answers includes:
and if the current round of questions and answers is the first round of questions and answers, determining the viewpoint elements corresponding to the current round of questions and answers as the question words corresponding to the current round of questions and answers.
3. The text processing method according to claim 1 or 2, wherein the generating of the query word corresponding to the current round of answers from the viewpoint elements corresponding to the current round of answers includes:
and if the current round of question answering is not the first round of question answering, generating the question words corresponding to the current round of question answering according to the answer corresponding to the previous round of question answering, the question words corresponding to the previous round of question answering and the viewpoint elements corresponding to the current round of question answering.
4. The text processing method according to claim 1, wherein the plurality of viewpoint elements include at least two of the following elements:
view holder, view target, and view publication time.
5. The text processing method of claim 1, further comprising:
generating a semantic role labeling result according to the text to be mined and the sequence labeling model;
generating answers corresponding to the current round of questions and answers according to the text to be mined, the query words corresponding to the current round of questions and the reading understanding model, wherein the generating of the answers corresponding to the current round of questions and answers comprises the following steps:
and generating an answer corresponding to the current round of question and answer according to the semantic role labeling result, the text to be mined, the query words corresponding to the current round of question and answer and the reading understanding model.
6. The text processing method according to claim 5, wherein the generating of the answer corresponding to the current round of questions and answers according to the semantic role labeling result, the text to be mined, the query words corresponding to the current round of questions and the reading understanding model comprises:
and inputting the semantic role labeling result, the text to be mined and the query words corresponding to the current round of questions and answers to the reading understanding model to obtain answers corresponding to the current round of questions and answers.
7. A knowledge-graph based text processing apparatus comprising:
the acquisition module is used for acquiring a text to be mined and a plurality of preset viewpoint elements; the plurality of viewpoint elements correspond to a plurality of rounds of questions and answers one by one;
the first generation module is used for generating query words corresponding to the current round of questions and answers according to the viewpoint elements corresponding to the current round of questions and answers;
the second generation module is used for generating answers corresponding to the current round of questions and answers according to the text to be mined, the query words corresponding to the current round of questions and the reading understanding model; and
and the third generation module is used for generating a viewpoint element labeling result corresponding to the text to be mined according to the plurality of query words and the plurality of answers corresponding to the plurality of rounds of queries and answers.
8. The text processing apparatus of claim 7, wherein the first generating module comprises:
and the determining unit is used for determining the viewpoint elements corresponding to the current round of questions and answers as the query words corresponding to the current round of questions and answers if the current round of questions and answers is the first round of questions and answers.
9. The text processing apparatus according to claims 7 and 8, wherein the first generating module comprises:
and the first generating unit is used for generating the query words corresponding to the current round of answers according to the answers corresponding to the previous round of answers, the query words corresponding to the previous round of answers and the viewpoint elements corresponding to the current round of answers if the current round of answers is not the first round of answers.
10. The text processing apparatus according to claim 7, wherein the plurality of viewpoint elements include at least two of the following elements:
view holder, view target, and view publication time.
11. The text processing apparatus of claim 7, further comprising:
the fourth generation module is used for generating a semantic role labeling result according to the text to be mined and the sequence labeling model;
wherein the second generating module comprises:
and the second generating unit is used for generating answers corresponding to the current round of questions and answers according to the semantic role labeling result, the text to be mined, the query words corresponding to the current round of questions and the reading understanding model.
12. The text processing apparatus according to claim 11, wherein the second generating unit includes:
and the input subunit is used for inputting the semantic role labeling result, the text to be mined and the query words corresponding to the current round of questions and answers to the reading understanding model to obtain answers corresponding to the current round of questions and answers.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110698838.2A CN113590776B (en) | 2021-06-23 | 2021-06-23 | Knowledge graph-based text processing method and device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110698838.2A CN113590776B (en) | 2021-06-23 | 2021-06-23 | Knowledge graph-based text processing method and device, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113590776A true CN113590776A (en) | 2021-11-02 |
| CN113590776B CN113590776B (en) | 2023-12-12 |
Family
ID=78244422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110698838.2A Active CN113590776B (en) | 2021-06-23 | 2021-06-23 | Knowledge graph-based text processing method and device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590776B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836273A (en) * | 2021-11-23 | 2021-12-24 | 天津汇智星源信息技术有限公司 | Legal consultation method based on complex context and related equipment |
| CN114330718A (en) * | 2021-12-23 | 2022-04-12 | 北京百度网讯科技有限公司 | Method and device for extracting causal relationship and electronic equipment |
| CN114490986A (en) * | 2022-01-25 | 2022-05-13 | 北京百度网讯科技有限公司 | Computer-implemented data mining method, computer-implemented data mining device, electronic device, and storage medium |
| CN114757209A (en) * | 2022-06-13 | 2022-07-15 | 天津大学 | Man-machine interaction instruction analysis method and device based on multi-mode semantic role recognition |
| CN115309910A (en) * | 2022-07-20 | 2022-11-08 | 首都师范大学 | Language piece element and element relation combined extraction method and knowledge graph construction method |
| CN116257613A (en) * | 2023-02-10 | 2023-06-13 | 北京百度网讯科技有限公司 | Data production method, device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002342069A (en) * | 2001-05-14 | 2002-11-29 | Nippon Telegr & Teleph Corp <Ntt> | Distributed sorting method, system, device, process and recording medium |
| JP2008269041A (en) * | 2007-04-17 | 2008-11-06 | Konica Minolta Medical & Graphic Inc | Database system and program |
| US20150309988A1 (en) * | 2014-04-29 | 2015-10-29 | International Business Machines Corporation | Evaluating Crowd Sourced Information Using Crowd Sourced Metadata |
| JP2017220238A (en) * | 2016-06-07 | 2017-12-14 | 株式会社Ｎｔｔドコモ | Method and device for providing answer in question answering system |
| CN109446306A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | A kind of intelligent answer method of more wheels dialogue of task based access control driving |
| CN111522914A (en) * | 2020-04-20 | 2020-08-11 | 北大方正集团有限公司 | Method and device for acquiring marking data, electronic equipment and storage medium |
| CN112417104A (en) * | 2020-12-04 | 2021-02-26 | 山西大学 | Machine reading understanding multi-hop inference model and method with enhanced syntactic relation |
| CN112732942A (en) * | 2021-01-16 | 2021-04-30 | 江苏网进科技股份有限公司 | User-oriented multi-turn question-answer legal document entity relationship extraction method |
| WO2021109690A1 (en) * | 2020-06-17 | 2021-06-10 | 平安科技（深圳）有限公司 | Multi-type question smart answering method, system and device, and readable storage medium |
-
2021
- 2021-06-23 CN CN202110698838.2A patent/CN113590776B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002342069A (en) * | 2001-05-14 | 2002-11-29 | Nippon Telegr & Teleph Corp <Ntt> | Distributed sorting method, system, device, process and recording medium |
| JP2008269041A (en) * | 2007-04-17 | 2008-11-06 | Konica Minolta Medical & Graphic Inc | Database system and program |
| US20150309988A1 (en) * | 2014-04-29 | 2015-10-29 | International Business Machines Corporation | Evaluating Crowd Sourced Information Using Crowd Sourced Metadata |
| JP2017220238A (en) * | 2016-06-07 | 2017-12-14 | 株式会社Ｎｔｔドコモ | Method and device for providing answer in question answering system |
| CN109446306A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | A kind of intelligent answer method of more wheels dialogue of task based access control driving |
| CN111522914A (en) * | 2020-04-20 | 2020-08-11 | 北大方正集团有限公司 | Method and device for acquiring marking data, electronic equipment and storage medium |
| WO2021109690A1 (en) * | 2020-06-17 | 2021-06-10 | 平安科技（深圳）有限公司 | Multi-type question smart answering method, system and device, and readable storage medium |
| CN112417104A (en) * | 2020-12-04 | 2021-02-26 | 山西大学 | Machine reading understanding multi-hop inference model and method with enhanced syntactic relation |
| CN112732942A (en) * | 2021-01-16 | 2021-04-30 | 江苏网进科技股份有限公司 | User-oriented multi-turn question-answer legal document entity relationship extraction method |
Non-Patent Citations (5)
| Title |
|---|
| "情报学报 第34卷 2015 总目录", 情报学报, no. 12 * |
| 周小强;王晓龙;陈清财;: "交互式问答的关系结构体系及标注", 中文信息学报, no. 05 * |
| 唐琴;宋锐;林鸿飞;: "基于Chunk-CRF的情感问答研究", 智能系统学报, no. 06 * |
| 阎丽;: "侧向掩蔽模型", 医疗保健器具, no. 11 * |
| 陈锋;: "细颗粒度观点挖掘中的观点句识别与要素抽取研究综述", 数字图书馆论坛, no. 10 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836273A (en) * | 2021-11-23 | 2021-12-24 | 天津汇智星源信息技术有限公司 | Legal consultation method based on complex context and related equipment |
| CN114330718A (en) * | 2021-12-23 | 2022-04-12 | 北京百度网讯科技有限公司 | Method and device for extracting causal relationship and electronic equipment |
| CN114330718B (en) * | 2021-12-23 | 2023-03-24 | 北京百度网讯科技有限公司 | Method and device for extracting causal relationship and electronic equipment |
| CN114490986A (en) * | 2022-01-25 | 2022-05-13 | 北京百度网讯科技有限公司 | Computer-implemented data mining method, computer-implemented data mining device, electronic device, and storage medium |
| CN114490986B (en) * | 2022-01-25 | 2024-02-20 | 北京百度网讯科技有限公司 | Computer-implemented data mining method, device, electronic equipment and storage medium |
| CN114757209A (en) * | 2022-06-13 | 2022-07-15 | 天津大学 | Man-machine interaction instruction analysis method and device based on multi-mode semantic role recognition |
| CN115309910A (en) * | 2022-07-20 | 2022-11-08 | 首都师范大学 | Language piece element and element relation combined extraction method and knowledge graph construction method |
| CN116257613A (en) * | 2023-02-10 | 2023-06-13 | 北京百度网讯科技有限公司 | Data production method, device, electronic equipment and storage medium |
| CN116257613B (en) * | 2023-02-10 | 2024-02-06 | 北京百度网讯科技有限公司 | Data production method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113590776B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113590776B (en) | Knowledge graph-based text processing method and device, electronic equipment and medium | |
| CN112487173B (en) | Man-machine conversation method, device and storage medium | |
| CN112560496A (en) | Training method and device of semantic analysis model, electronic equipment and storage medium | |
| CN114548110A (en) | Semantic understanding method and device, electronic equipment and storage medium | |
| EP4113357A1 (en) | Method and apparatus for recognizing entity, electronic device and storage medium | |
| CN112579727A (en) | Document content extraction method and device, electronic equipment and storage medium | |
| US20230008897A1 (en) | Information search method and device, electronic device, and storage medium | |
| CN114090755A (en) | Reply sentence determination method and device based on knowledge graph and electronic equipment | |
| CN113221565A (en) | Entity recognition model training method and device, electronic equipment and storage medium | |
| CN112560461A (en) | News clue generation method and device, electronic equipment and storage medium | |
| CN112528146B (en) | Content resource recommendation method and device, electronic equipment and storage medium | |
| CN112926308A (en) | Method, apparatus, device, storage medium and program product for matching text | |
| CN116049370A (en) | Information query method and training method and device of information generation model | |
| CN113268575B (en) | Entity relationship identification method and device and readable medium | |
| CN113792230B (en) | Service linking method, device, electronic equipment and storage medium | |
| CN113222414B (en) | Model stability evaluation method and device, electronic equipment and storage medium | |
| CN113886543A (en) | Method, apparatus, medium, and program product for generating an intent recognition model | |
| CN114817476A (en) | Language model training method and device, electronic equipment and storage medium | |
| CN114048315A (en) | Method and device for determining document tag, electronic equipment and storage medium | |
| CN113641724A (en) | Knowledge tag mining method and device, electronic equipment and storage medium | |
| CN112541346A (en) | Abstract generation method and device, electronic equipment and readable storage medium | |
| CN116226478B (en) | Information processing method, model training method, device, equipment and storage medium | |
| CN113705206B (en) | Emotion prediction model training method, device, equipment and storage medium | |
| CN114255427B (en) | Video understanding method, device, equipment and storage medium | |
| CN116257611B (en) | Question-answering model training method, question-answering processing device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |