CN113010666B - Digest generation method, digest generation device, computer system, and readable storage medium - Google Patents
Digest generation method, digest generation device, computer system, and readable storage medium Download PDFInfo
- Publication number
- CN113010666B CN113010666B CN202110293478.8A CN202110293478A CN113010666B CN 113010666 B CN113010666 B CN 113010666B CN 202110293478 A CN202110293478 A CN 202110293478A CN 113010666 B CN113010666 B CN 113010666B
- Authority
- CN
- China
- Prior art keywords
- hidden layer
- layer sequence
- unstructured
- attribute
- probability
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000012545 processing Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 9
- 230000010076 replication Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 abstract description 25
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Probability & Statistics with Applications (AREA)
- Machine Translation (AREA)
Abstract
The present disclosure provides a summary generation method, including: acquiring text data for describing a target object, wherein the text data comprises a structured knowledge graph and unstructured description text; encoding the structured knowledge graph and the unstructured description text respectively to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured description text; and generating a summary of the text data according to the first encoder hidden layer sequence and the second encoder hidden layer sequence. The present disclosure also provides a digest generation apparatus, a computer system, a readable storage medium, and a computer program product.
Description
Technical Field
The present disclosure relates to the field of computer technology, and more particularly, to a digest generation method, apparatus, computer system, readable storage medium, and computer program product.
Background
Summary generation techniques typically use some refined short text to summarize the ideas of some massive amounts of information. The user can know the meaning of the original information to be expressed by reading the abstract. The abstract generation technology is applied to aspects of our lives, such as extraction of news keywords, search result optimization of a search engine, commodity recommendation of a shopping platform and the like. By utilizing the abstract generation technology, readers can quickly acquire effective information, time is saved, and efficiency is improved.
In the process of implementing the disclosed concept, the inventor finds that at least the following problems exist in the related art: the existing abstract generation method does not fully mine and reference the original information, so that the generated abstract has lower quality.
Disclosure of Invention
In view of this, the present disclosure provides a digest generation method, apparatus, computer system, readable storage medium, and computer program product.
One aspect of the present disclosure provides a digest generation method, including:
acquiring text data for describing a target object, wherein the text data comprises a structured knowledge graph and unstructured description text;
encoding the structured knowledge graph and the unstructured description text respectively to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured description text; and
and generating a summary of the text data according to the first encoder hidden layer sequence and the second encoder hidden layer sequence.
According to an embodiment of the present disclosure, wherein generating the summary of the text data from the first encoder hidden layer sequence and the second encoder hidden layer sequence comprises:
decoding the hidden layer sequence of the first encoder to generate the duplication probability of a first abstract word of the structured knowledge graph;
Decoding the hidden layer sequence of the second encoder to generate the duplication probability of a second abstract word of the unstructured descriptive text and the generation probability of a third abstract word corresponding to the unstructured descriptive text;
obtaining fusion probability based on the replication probability of the first abstract word, the replication probability of the second abstract word and the generation probability of the third abstract word; and
and generating a summary of the text data according to the fusion probability.
According to an embodiment of the present disclosure, decoding the second encoder hidden layer sequence, generating the duplication probability of the second abstract word of the unstructured descriptive text and the generation probability of the third abstract word corresponding to the unstructured descriptive text includes:
processing the second encoder hidden layer sequence to generate a decoder hidden layer sequence and a context vector sequence;
generating a generation probability of a third abstract word corresponding to the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence;
generating an attention weight of a second abstract word of the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence; and
based on the attention weight of the second abstract word, a duplication probability of the second abstract word is generated.
According to an embodiment of the present disclosure, wherein the structured knowledge graph comprises an attribute identification and an attribute value;
the first encoder hidden layer sequence includes an attribute identification hidden layer sequence and an attribute value hidden layer sequence.
According to an embodiment of the present disclosure, decoding the first encoder hidden layer sequence, generating the duplication probability of the first abstract word of the structured knowledge-graph comprises:
based on the decoder hidden layer sequence and the context vector sequence, respectively processing the attribute identification hidden layer sequence and the attribute value hidden layer sequence to generate an attribute identification attention weight corresponding to the attribute identification semantic vector and an attribute value attention weight corresponding to the attribute value semantic vector; and
based on the attribute identification attention weight and the attribute value attention weight, a duplication probability of the first abstract word is generated.
According to an embodiment of the present disclosure, before encoding the structured knowledge-graph and the unstructured descriptive text respectively to generate the first encoder hidden layer sequence corresponding to the structured knowledge-graph and the second encoder hidden layer sequence corresponding to the unstructured descriptive text, the method further includes:
and performing word segmentation processing on the structured knowledge graph and the unstructured description text so as to code the structured knowledge graph and the unstructured description text respectively.
Still another aspect of the present disclosure provides a digest generating apparatus, including:
the acquisition module is used for acquiring text data for describing the target object, wherein the text data comprises a structured knowledge graph and unstructured description text;
the coding module is used for respectively coding the structured knowledge graph and the unstructured description text to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured description text; and
and the generation module is used for generating a summary of the text data according to the first encoder hidden layer sequence and the second encoder hidden layer sequence.
Yet another aspect of the present disclosure provides a computer system comprising:
one or more processors;
a memory for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the digest generation method described above.
Yet another aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the above-described digest generation method.
Yet another aspect of the present disclosure provides a computer program product comprising a computer program comprising computer executable instructions which, when executed, are adapted to carry out the above-described digest generation method.
According to the embodiment of the disclosure, since the acquisition of text data for describing the target object is adopted, the text data comprises a structured knowledge graph and unstructured description text; encoding the structured knowledge graph and the unstructured description text respectively to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured description text; according to the first encoder hidden layer sequence and the second encoder hidden layer sequence, generating a summary of the text data, and simultaneously encoding by combining a structured knowledge graph and an unstructured description text and generating the summary of the text data; therefore, the technical problem that the quality of the generated abstract is low due to the fact that original information is not fully mined and referenced in the prior art is at least partially solved, and the technical effects that the original information is fully mined and referenced to generate the abstract so as to improve the integrity and the quality of abstract generation are achieved.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments thereof with reference to the accompanying drawings in which:
FIG. 1 schematically illustrates an exemplary system architecture to which the summary generation methods and apparatus of the present disclosure may be applied;
FIG. 2 schematically illustrates a flow chart of a summary generation method according to an embodiment of the disclosure;
FIG. 3 schematically illustrates a flow chart of a summary generation method according to another embodiment of the present disclosure;
fig. 4 schematically shows a block diagram of a digest generating apparatus according to an embodiment of the disclosure; and
fig. 5 schematically illustrates a block diagram of a computer system adapted to implement the digest generation method according to an embodiment of the disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.
Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a formulation similar to at least one of "A, B or C, etc." is used, in general such a formulation should be interpreted in accordance with the ordinary understanding of one skilled in the art (e.g. "a system with at least one of A, B or C" would include but not be limited to systems with a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
The embodiment of the disclosure provides a summary generation method. The method comprises the following steps: acquiring text data for describing a target object, wherein the text data comprises a structured knowledge graph and unstructured description text; encoding the structured knowledge graph and the unstructured description text respectively to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured description text; and generating a summary of the text data based on the first encoder hidden layer sequence and the second encoder hidden layer sequence.
Fig. 1 schematically illustrates an exemplary system architecture 100 in which the digest generation methods and apparatus may be applied according to embodiments of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which embodiments of the present disclosure may be applied to assist those skilled in the art in understanding the technical content of the present disclosure, but does not mean that embodiments of the present disclosure may not be used in other devices, systems, environments, or scenarios.
As shown in fig. 1, a system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and/or wireless communication links, and the like.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients and/or social platform software, to name a few.
The terminal devices 101, 102, 103 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that, the summary generating method provided by the embodiments of the present disclosure may be generally executed by the server 105. Accordingly, the summary generating apparatus provided in the embodiments of the present disclosure may be generally disposed in the server 105. The digest generation method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the summary generating apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Alternatively, the digest generation method provided by the embodiment of the present disclosure may be performed by the terminal apparatus 101, 102, or 103, or may be performed by another terminal apparatus other than the terminal apparatus 101, 102, or 103. Accordingly, the summary generating apparatus provided by the embodiments of the present disclosure may also be provided in the terminal device 101, 102, or 103, or in another terminal device different from the terminal device 101, 102, or 103.
For example, text data for describing the target object may be originally stored in any one of the terminal devices 101, 102, or 103 (for example, but not limited to, the terminal device 101), or stored on an external storage device and may be imported into the terminal device 101. Then, the terminal device 101 may transmit text data for describing the target object to other terminal devices, servers, or server clusters, and perform the digest generation method provided by the embodiments of the present disclosure by the other servers, or server clusters, that receive the text data for describing the target object.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Fig. 2 schematically shows a flowchart of a summary generation method according to an embodiment of the present disclosure.
As shown in fig. 2, the method includes operations S210 to S230.
In operation S210, text data for describing a target object is acquired, wherein the text data includes a structured knowledge graph and unstructured description text;
in operation S220, encoding the structured knowledge graph and the unstructured descriptive text, respectively, to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured descriptive text; and
In operation S230, a digest of the text data is generated from the first encoder hidden layer sequence and the second encoder hidden layer sequence.
According to an embodiment of the present disclosure, text data for describing a target object may be, for example, heterogeneous commodity data for describing a certain target commodity; the heterogeneous commodity data comprises a structured knowledge graph and unstructured descriptive text. The structured knowledge graph may be, for example, a structured commodity knowledge graph, such as table data listed with commodity attribute identifiers and commodity attribute values corresponding to the commodity attribute identifiers; the unstructured descriptive text may be, for example, unstructured commodity detailed descriptive text, such as text describing the performance, specifications, etc. of the commodity.
According to the embodiment of the disclosure, the structured knowledge graph and the unstructured descriptive text are respectively encoded, and a summary of text data is generated based on a first encoder hidden layer sequence and a second encoder hidden layer sequence obtained after encoding. The method and the device have the advantages that the technical effects of fully mining and referencing original information to generate the abstract and improving the integrity and quality of abstract generation are achieved.
The method illustrated in fig. 2 is further described below with reference to fig. 3 in conjunction with an exemplary embodiment.
Fig. 3 schematically illustrates a flowchart of a summary generation method according to another embodiment of the present disclosure.
As shown in fig. 3, the digest generation method includes operations S310 to S320, S331, S332, S340 to S350.
In operation S310, text data for describing a target object is acquired, wherein the text data includes a structured knowledge-graph and unstructured description text.
According to the embodiment of the disclosure, the unstructured descriptive text can be a section of detailed descriptive text of the target commodity, and the sequence x= { x is used 1 ，x 2 ，...，x n Represented by each x i Is a word in the unstructured descriptive text.
According to an alternative embodiment of the present disclosure, the structured knowledge graph may include an attribute identification and an attribute value.
Table 1 is a structured knowledge graph of a target commodity according to an embodiment of the present disclosure. As shown in Table 1, the attribute identification may include an attribute description that characterizes the target commodity, such as may be color, altitude, capacity, etc.; the attribute value may be a specific parameter corresponding to the attribute identifier, for example, may be a specific color white, a specific height of 2 meters, a specific capacity of 4 liters, and the like.
TABLE 1
| Commodity name | Color of | Height | Capacity of |
| Bottle (bottle) | White color | 2 meters | 4L |
According to embodiments of the present disclosure, attribute identification (e.g., color, height, volume) in a structured knowledge-graph may be represented by the sequence k= { k 1 ，k 2 ，...，k m -to represent; the attribute values (e.g., white, 2 meters, 4 liters) can be represented by the sequence v= { v 1 ，v 2 ，...，v m And } is represented.
According to an alternative embodiment of the present disclosure, before encoding the structured knowledge-graph and the unstructured description text respectively to generate a first encoder hidden layer sequence corresponding to the structured knowledge-graph and a second encoder hidden layer sequence corresponding to the unstructured description text, word segmentation processing may be performed on the structured knowledge-graph and the unstructured description text, so as to encode the structured knowledge-graph and the unstructured description text respectively.
According to the embodiment of the disclosure, firstly, the structured knowledge graph and the unstructured description text are subjected to word segmentation, so that sequences x, k and v are obtained, and subsequent coding processing is performed. In the embodiment of the present disclosure, the word segmentation processing operation may be completed by using a related word segmentation technique, which is not described herein.
In operation S320, the structured knowledge-graph and the unstructured descriptive text are encoded, respectively, to generate a first encoder hidden layer sequence corresponding to the structured knowledge-graph and a second encoder hidden layer sequence corresponding to the unstructured descriptive text.
According to embodiments of the present disclosure, a structured knowledge-graph and unstructured descriptive text may be encoded separately using a bi-directional LSTM encoder (BiLSTM); however, the method is not limited thereto, and the structured knowledge graph and the unstructured descriptive text may be encoded by using a Transform network as an encoder.
According to the alternative embodiment of the disclosure, the structured knowledge graph and the unstructured description text are respectively encoded by using a bidirectional LSTM encoder (BiLSTM), so that the encoder with good encoding effect can be obtained through training under the condition of small training sample size.
According to an embodiment of the present disclosure, the first encoder hidden layer sequence may include an attribute identification hidden layer sequence and an attribute value hidden layer sequence.
According to an alternative embodiment of the present disclosure, sequences k, v are encoded using a bi-directional LSTM encoder BiLSTM to generate attribute-identifying hidden layer sequences and attribute-value hidden layer sequences hk, hv, respectively, as shown in equations (1) and (2) below.
Wherein i represents an i-th hidden layer.
According to an alternative embodiment of the present disclosure, sequence x is encoded using a bi-directional LSTM encoder BiLSTM, generating a second encoder hidden layer sequence hx as shown in equation (3) below.
Wherein i represents an i-th hidden layer.
In operation S331, the first encoder hidden layer sequence is decoded, and a duplication probability of a first abstract word of the structured knowledge-graph is generated.
In operation S332, the second encoder hidden layer sequence is decoded, and a duplication probability of the second digest word of the unstructured descriptive text and a generation probability of the third digest word corresponding to the unstructured descriptive text are generated.
In operation S340, a fusion probability is obtained based on the duplication probability of the first abstract word, the duplication probability of the second abstract word, and the generation probability of the third abstract word.
In operation S350, a summary of the text data is generated according to the fusion probability.
According to the embodiment of the disclosure, the summary generating method of the embodiment of the disclosure not only uses two encoders to encode the structured knowledge graph and the unstructured description text respectively, but also finally decodes and comprehensively considers the duplication probability of the first summary word appearing in the structured knowledge graph, the duplication probability of the second summary word appearing in the unstructured description text and the generation probability of the third summary word generated according to the semantics of the unstructured description text, thereby realizing the technical effect of generating the summary more accurately on the basis of fully mining the original information.
According to an embodiment of the present disclosure, decoding the second encoder hidden layer sequence, generating the duplication probability of the second digest word of the unstructured descriptive text and the generation probability of the third digest word corresponding to the unstructured descriptive text may include the following operations.
Processing the second encoder hidden layer sequence to generate a decoder hidden layer sequence and a context vector sequence;
generating a generation probability of a third abstract word corresponding to the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence;
generating an attention weight of a second abstract word of the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence; and
based on the attention weight of the second abstract word, a duplication probability of the second abstract word is generated.
According to an alternative embodiment of the present disclosure, the second encoder hidden layer sequence may be decoded using a uni-directional LSTM decoder (UniLSTM), and the attention mechanism employed to ultimately generate the decoder hidden layer sequence and the context vector sequence.
According to an embodiment of the present disclosure, the second encoder hidden layer sequence is processed to generate a decoder hidden layer sequence and a context vector sequence, which can be seen in equations (4) to (7).
Wherein s is t For the decoder hidden layer sequence at time t, y t-1 For the output at time t-1,for the context vector at time t, u a 、W a 、V a Respectively a model parameter matrix.
According to an embodiment of the present disclosure, the generation probability of generating the third digest word corresponding to the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence may be employed as the following formula (8).
Wherein W is c And V c Is a model parameter matrix;is the context vector at time t, s t For the time instant t the decoder conceals the layer sequence.
Keywords in unstructured descriptive text may also be directly copied as abstract words according to embodiments of the present disclosure. The probability of copying the keywords in the unstructured descriptive text directly as the second abstract word can be expressed as the following formula (9).
Wherein,is the attention weight of the second abstract word.
According to the embodiments of the present disclosure, the abstract generating method of the embodiments of the present disclosure not only allows for generating abstract words according to the semantics of unstructured descriptive text, but also allows for directly copying keywords in unstructured descriptive text as abstract words.
According to an alternative embodiment of the present disclosure, keywords in the structured knowledge graph may also be directly copied as abstract words. And directly copying the keywords in the structured knowledge graph as the copying probability of the first abstract word.
According to an embodiment of the present disclosure, wherein decoding the first encoder hidden layer sequence, generating the duplication probability of the first abstract word of the structured knowledge base may include the following operations.
Processing the attribute identification hidden layer sequence and the attribute value hidden layer sequence respectively to generate an attribute identification attention weight corresponding to the attribute identification hidden layer sequence and an attribute value attention weight corresponding to the attribute value hidden layer sequence; and
based on the attribute identification attention weight and the attribute value attention weight, a duplication probability of the first abstract word is generated.
According to an embodiment of the present disclosure, the duplication probability of the first abstract word may be as in formula (10).
According to an embodiment of the present disclosure, the attribute identifies an attention weight as in equation (11); the attribute value attention weight may be as in equation (12).
Wherein,s t for the decoder hidden layer sequence at time t, u a 、W a 、V a Respectively a model parameter matrix.
According to the embodiment of the disclosure, the attribute identification attention weight and the attribute value attention weight are utilized, namely, the secondary attention weight is adopted to obtain the duplication probability of the first abstract word, the identification of the low-frequency keywords is fully considered, and the generated abstract information is fully and critically mastered.
According to an embodiment of the present disclosure, the final fusion probability includes a duplication probability of a first abstract word of the structured knowledge graph, a duplication probability of a second abstract word of the unstructured descriptive text, and a generation probability of a third abstract word corresponding to the unstructured descriptive text, and the aggregate semantic generation probability and keyword duplication probability may specifically be as shown in the formula
In summary, by using the summary generating method of the embodiment of the present disclosure, on one hand, two encoders are used to encode the structured knowledge graph and the unstructured description text respectively, so as to consider the full mining of the original information; on the other hand, a double copying mechanism is adopted, and is matched with coding, so that the copying of keyword information in a structured knowledge graph and an unstructured description text is integrated, and the integrity of the generated abstract is high; in the process of calculating the duplication probability of the structured knowledge graph, the secondary attention weight is adopted, so that the recognition degree of the low-frequency keywords is improved, and the generated abstract is more accurate.
According to other embodiments of the present disclosure, it should be noted that the digest generation method of the embodiments of the present disclosure may generate the digest by constructing an encoding-decoding model. For example, the encoding-decoding model includes two bi-directional LSTM encoders and a uni-directional LSTM decoder, and employs an attention mechanism and a double copy mechanism. The model encoding-decoding is trained based on maximum likelihood, and the loss function is as in equation (13).
Where T is the number of words in the text data.
The training is then performed with text data having a structured knowledge-graph and unstructured descriptive text as training samples.
According to the embodiment of the disclosure, the text data of the structured knowledge graph and the unstructured descriptive text are used as training samples, and training is performed by using maximum likelihood, so that the abstract generated by the finally trained encoding-decoding model is refined, accurate and high in integrity.
Fig. 4 schematically shows a block diagram of a digest generation apparatus according to an embodiment of the disclosure.
As shown in fig. 4, the digest generating apparatus 400 includes an acquisition module 410, an encoding module 420, and a generating module 430.
An obtaining module 410, configured to obtain text data for describing a target object, where the text data includes a structured knowledge graph and unstructured description text;
the encoding module 420 is configured to encode the structured knowledge graph and the unstructured description text, respectively, to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph, and a second encoder hidden layer sequence corresponding to the unstructured description text; and
the generating module 430 is configured to generate a summary of the text data according to the first encoder hidden layer sequence and the second encoder hidden layer sequence.
According to the embodiment of the disclosure, the structured knowledge graph and the unstructured descriptive text are respectively encoded, and a summary of text data is generated based on a first encoder hidden layer sequence and a second encoder hidden layer sequence obtained after encoding. The method and the device have the advantages that the technical effects of fully mining and referencing original information to generate the abstract and improving the integrity and quality of abstract generation are achieved. According to an embodiment of the present disclosure, the generating module 430 includes a first decoding unit, a second decoding unit, a deriving unit, and a generating unit.
The first decoding unit is used for decoding the hidden layer sequence of the first encoder and generating the replication probability of the first abstract word of the structured knowledge graph;
the second decoding unit is used for decoding the hidden layer sequence of the second encoder to generate the duplication probability of the second abstract word of the unstructured descriptive text and the generation probability of the third abstract word corresponding to the unstructured descriptive text;
the obtaining unit is used for obtaining fusion probability based on the replication probability of the first abstract word, the replication probability of the second abstract word and the generation probability of the third abstract word; and
and the generating unit is used for generating the abstract of the text data according to the fusion probability.
According to an embodiment of the present disclosure, the second decoding unit includes a first generating subunit, a second generating subunit, a third generating subunit, and a fourth generating subunit.
A first generation subunit, configured to process the second encoder hidden layer sequence to generate a decoder hidden layer sequence and a context vector sequence;
a second generation subunit, configured to generate, based on the decoder hidden layer sequence and the context vector sequence, a generation probability of a third abstract word corresponding to the unstructured description text;
a third generation subunit for generating an attention weight of a second abstract word of the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence; and
and a fourth generation subunit, configured to generate a duplication probability of the second abstract word based on the attention weight of the second abstract word.
According to an embodiment of the present disclosure, wherein the structured knowledge graph comprises an attribute identification and an attribute value;
the first encoder hidden layer sequence includes an attribute identification hidden layer sequence and an attribute value hidden layer sequence.
According to an embodiment of the present disclosure, the first decoding unit includes a fifth generating subunit and a sixth generating subunit.
A fifth generating subunit, configured to process the attribute identifier hidden layer sequence and the attribute value hidden layer sequence based on the decoder hidden layer sequence and the context vector sequence, respectively, to generate an attribute identifier attention weight corresponding to the attribute identifier semantic vector, and an attribute value attention weight corresponding to the attribute value semantic vector; and
And a sixth generation subunit, configured to generate the duplication probability of the first abstract word based on the attribute identification attention weight and the attribute value attention weight.
According to an embodiment of the present disclosure, the digest generation apparatus 400 further includes a word segmentation module.
And the word segmentation module is used for carrying out word segmentation processing on the structured knowledge graph and the unstructured description text so as to code the structured knowledge graph and the unstructured description text respectively.
Any number of modules, sub-modules, units, sub-units, or at least some of the functionality of any number of the sub-units according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented as split into multiple modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or in any other reasonable manner of hardware or firmware that integrates or encapsulates the circuit, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be at least partially implemented as computer program modules, which when executed, may perform the corresponding functions.
For example, any of the acquisition module 410, the encoding module 420, and the generation module 430 may be combined in one module/unit/sub-unit or any of the modules/units/sub-units may be split into multiple modules/units/sub-units. Alternatively, at least some of the functionality of one or more of these modules/units/sub-units may be combined with at least some of the functionality of other modules/units/sub-units and implemented in one module/unit/sub-unit. According to embodiments of the present disclosure, at least one of the acquisition module 410, the encoding module 420, and the generation module 430 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-a-substrate, a system-on-a-package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or co-components in any other reasonable way of integrating or packaging circuitry, or in any one of, or a suitable combination of, three of software, hardware, and firmware. Alternatively, at least one of the acquisition module 410, the encoding module 420, and the generation module 430 may be at least partially implemented as computer program modules that, when executed, perform the corresponding functions.
It should be noted that, in the embodiments of the present disclosure, the summary generating device portion corresponds to the summary generating method portion of the embodiments of the present disclosure, and the description of the summary generating device portion specifically refers to the summary generating method portion and is not described herein again.
Fig. 5 schematically illustrates a block diagram of a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure. The computer system illustrated in fig. 5 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present disclosure.
As shown in fig. 5, a computer system 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 501 may also include on-board memory for caching purposes. The processor 501 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.
In the RAM 503, various programs and data required for the operation of the system 500 are stored. The processor 501, ROM 502, and RAM 503 are connected to each other by a bus 504. The processor 501 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 502 and/or the RAM 503. Note that the program may be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.
According to an embodiment of the present disclosure, the system 500 may further include an input/output (I/O) interface 505, the input/output (I/O) interface 505 also being connected to the bus 504. The system 500 may also include one or more of the following components connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.
According to embodiments of the present disclosure, the method flow according to embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 509, and/or installed from the removable media 511. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 501. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.
The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to: 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), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 502 and/or RAM 503 and/or one or more memories other than ROM 502 and RAM 503 described above.
Embodiments of the present disclosure also include a computer program product comprising a computer program comprising program code for performing the methods provided by the embodiments of the present disclosure, the program code for causing an electronic device to implement the summary generation methods provided by the embodiments of the present disclosure when the computer program product is run on the electronic device.
The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 501. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.
In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed, and downloaded and installed in the form of a signal on a network medium, and/or installed from a removable medium 511 via the communication portion 509. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be combined in various combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.
The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.
Claims (8)
1. A summary generation method, comprising:
acquiring text data for describing a target object, wherein the text data comprises a structured knowledge graph and an unstructured description text, and the structured knowledge graph comprises an attribute identifier of the target object and an attribute value corresponding to the attribute identifier;
encoding the structured knowledge graph and the unstructured description text respectively to generate a first encoder hidden layer sequence corresponding to the structured knowledge graph and a second encoder hidden layer sequence corresponding to the unstructured description text, wherein the first encoder hidden layer sequence comprises an attribute identification hidden layer sequence and an attribute value hidden layer sequence; and
And generating a summary of the text data according to the attribute identification hidden layer sequence, the attribute value hidden layer sequence and the second encoder hidden layer sequence.
2. The method of claim 1, wherein the generating the summary of the text data from the attribute-identifying hidden layer sequence, the attribute-value hidden layer sequence, and the second encoder hidden layer sequence comprises:
decoding the attribute identification hidden layer sequence and the attribute value hidden layer sequence to generate the replication probability of a first abstract word of the structured knowledge graph;
decoding the hidden layer sequence of the second encoder to generate the duplication probability of a second abstract word of the unstructured descriptive text and the generation probability of a third abstract word corresponding to the unstructured descriptive text;
obtaining a fusion probability based on the replication probability of the first abstract word, the replication probability of the second abstract word and the generation probability of the third abstract word; and
and generating the abstract of the text data according to the fusion probability.
3. The method of claim 2, wherein the decoding the second encoder hidden layer sequence to generate a duplication probability of a second abstract word of the unstructured descriptive text and a generation probability of a third abstract word corresponding to the unstructured descriptive text comprises:
Processing the second encoder hidden layer sequence to generate a decoder hidden layer sequence and a context vector sequence;
generating a generation probability of a third abstract word corresponding to the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence;
generating an attention weight of a second abstract word of the unstructured descriptive text based on the decoder hidden layer sequence and the context vector sequence; and
and generating the duplication probability of the second abstract word based on the attention weight of the second abstract word.
4. The method of claim 3, wherein the decoding the attribute-identifying hidden layer sequence and the attribute-value hidden layer sequence to generate the probability of replication of the first abstract word of the structured-knowledge-graph comprises:
processing the attribute identification hidden layer sequence and the attribute value hidden layer sequence respectively based on the decoder hidden layer sequence and the context vector sequence to generate an attribute identification attention weight corresponding to the attribute identification semantic vector and an attribute value attention weight corresponding to the attribute value semantic vector; and
generating the duplication probability of the first abstract word based on the attribute identification attention weight and the attribute value attention weight.
5. The method of claim 1, the encoding the structured knowledge-graph and the unstructured descriptive text, respectively, prior to generating a first encoder hidden sequence corresponding to the structured knowledge-graph and a second encoder hidden sequence corresponding to the unstructured descriptive text, the method further comprising:
and performing word segmentation processing on the structured knowledge graph and the unstructured description text so as to code the structured knowledge graph and the unstructured description text respectively.
6. A digest generating apparatus comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring text data for describing a target object, the text data comprises a structured knowledge graph and an unstructured description text, and the structured knowledge graph comprises an attribute identifier of the target object and an attribute value corresponding to the attribute identifier;
the coding module is used for respectively coding the structured knowledge graph and the unstructured description text to generate a first coder hidden layer sequence corresponding to the structured knowledge graph and a second coder hidden layer sequence corresponding to the unstructured description text, wherein the first coder hidden layer sequence comprises an attribute identification hidden layer sequence and an attribute value hidden layer sequence; and
And the generation module is used for generating the abstract of the text data according to the attribute identification hidden layer sequence, the attribute value hidden layer sequence and the second encoder hidden layer sequence.
7. A computer system, comprising:
one or more processors;
a memory for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1 to 5.
8. A computer readable storage medium having stored thereon executable instructions which when executed by a processor cause the processor to implement the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110293478.8A CN113010666B (en) | 2021-03-18 | 2021-03-18 | Digest generation method, digest generation device, computer system, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110293478.8A CN113010666B (en) | 2021-03-18 | 2021-03-18 | Digest generation method, digest generation device, computer system, and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113010666A CN113010666A (en) | 2021-06-22 |
| CN113010666B true CN113010666B (en) | 2023-12-08 |
Family
ID=76402760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110293478.8A Active CN113010666B (en) | 2021-03-18 | 2021-03-18 | Digest generation method, digest generation device, computer system, and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113010666B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218932B (en) * | 2021-11-26 | 2024-02-20 | 中国航空综合技术研究所 | Aviation fault text abstract generation method and device based on fault causal map |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9619601B1 (en) * | 2015-01-22 | 2017-04-11 | Xilinx, Inc. | Control and data flow graph generation for hardware description languages |
| JP2018067199A (en) * | 2016-10-20 | 2018-04-26 | 日本電信電話株式会社 | Abstract generating device, text converting device, and methods and programs therefor |
| CN108509413A (en) * | 2018-03-08 | 2018-09-07 | 平安科技（深圳）有限公司 | Digest extraction method, device, computer equipment and storage medium |
| US10402495B1 (en) * | 2016-09-01 | 2019-09-03 | Facebook, Inc. | Abstractive sentence summarization |
| CN111460135A (en) * | 2020-03-31 | 2020-07-28 | 北京百度网讯科技有限公司 | Method and device for generating text abstract |
| CN111666418A (en) * | 2020-04-23 | 2020-09-15 | 北京三快在线科技有限公司 | Text regeneration method and device, electronic equipment and computer readable medium |
| JP2021033995A (en) * | 2019-08-16 | 2021-03-01 | 株式会社Ｎｔｔドコモ | Text processing apparatus, method, device, and computer-readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10942996B2 (en) * | 2018-12-11 | 2021-03-09 | block.one | Digital identity social graph |
-
2021
- 2021-03-18 CN CN202110293478.8A patent/CN113010666B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9619601B1 (en) * | 2015-01-22 | 2017-04-11 | Xilinx, Inc. | Control and data flow graph generation for hardware description languages |
| US10402495B1 (en) * | 2016-09-01 | 2019-09-03 | Facebook, Inc. | Abstractive sentence summarization |
| JP2018067199A (en) * | 2016-10-20 | 2018-04-26 | 日本電信電話株式会社 | Abstract generating device, text converting device, and methods and programs therefor |
| CN108509413A (en) * | 2018-03-08 | 2018-09-07 | 平安科技（深圳）有限公司 | Digest extraction method, device, computer equipment and storage medium |
| JP2021033995A (en) * | 2019-08-16 | 2021-03-01 | 株式会社Ｎｔｔドコモ | Text processing apparatus, method, device, and computer-readable storage medium |
| CN111460135A (en) * | 2020-03-31 | 2020-07-28 | 北京百度网讯科技有限公司 | Method and device for generating text abstract |
| CN111666418A (en) * | 2020-04-23 | 2020-09-15 | 北京三快在线科技有限公司 | Text regeneration method and device, electronic equipment and computer readable medium |
Non-Patent Citations (2)
| Title |
|---|
| 基于子词单元的深度学习摘要生成方法;陈雪雯;;计算机应用与软件(第03期) * |
| 基于深度学习与图数据库构建中文商业知识图谱的探索研究;王仁武;袁毅;袁旭萍;;图书与情报(第01期) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113010666A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11758088B2 (en) | Method and apparatus for aligning paragraph and video | |
| US11665121B2 (en) | Determining topic cohesion between posted and linked content | |
| US20160371244A1 (en) | Collaboratively reconstituting tables | |
| CN111435376A (en) | Information processing method and system, computer system, and computer-readable storage medium | |
| CN116594683A (en) | Code annotation information generation method, device, equipment and storage medium | |
| CN113507419B (en) | Training method of traffic distribution model, traffic distribution method and device | |
| CN113010666B (en) | Digest generation method, digest generation device, computer system, and readable storage medium | |
| CN116155628B (en) | Network security detection method, training device, electronic equipment and medium | |
| CN110852057A (en) | Method and device for calculating text similarity | |
| CN116560661A (en) | Code optimization method, device, equipment and storage medium | |
| CN116069725A (en) | File migration method, device, apparatus, medium and program product | |
| CN116308704A (en) | Product recommendation method, device, electronic equipment, medium and computer program product | |
| CN113935334A (en) | Text information processing method, device, equipment and medium | |
| CN110929512A (en) | Data enhancement method and device | |
| CN114691850A (en) | Method for generating question-answer pairs, training method and device of neural network model | |
| US9251125B2 (en) | Managing text in documents based on a log of research corresponding to the text | |
| US10910014B2 (en) | Method and apparatus for generating video | |
| CN111767391B (en) | Target text generation method, device, computer system and medium | |
| CN116795866A (en) | File processing method, device, equipment and storage medium | |
| CN118152803A (en) | Training data set construction method, training data set construction device, electronic device, training data set construction medium and training data set construction program product | |
| CN116737813A (en) | Service processing method, device, electronic equipment and storage medium | |
| CN116721426A (en) | Text recognition method, device, equipment and storage medium | |
| CN117493519A (en) | Training method of text encoder, text generation method, device and storage medium | |
| CN116450416A (en) | Redundancy check method and device for software test cases, electronic equipment and medium | |
| CN116561258A (en) | Information management method, device, equipment, medium and product |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Technology Holding Co.,Ltd. Address before: Room 221, 2 / F, block C, 18 Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant before: Jingdong Digital Technology Holding Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |