CN109408829B - Method, device, equipment and medium for determining readability of article - Google Patents
Method, device, equipment and medium for determining readability of article Download PDFInfo
- Publication number
- CN109408829B CN109408829B CN201811331517.3A CN201811331517A CN109408829B CN 109408829 B CN109408829 B CN 109408829B CN 201811331517 A CN201811331517 A CN 201811331517A CN 109408829 B CN109408829 B CN 109408829B
- Authority
- CN
- China
- Prior art keywords
- sentence
- inter
- model
- readability
- similarity
- 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
Images
Classifications
-
- 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
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for determining readability of an article, and relates to the field of text readability analysis. The method comprises the following steps: detecting a target article based on an inter-sentence model, an intra-sentence model and a similarity model to obtain inter-sentence probability, a perplexity of sentences and an inter-sentence similarity; determining readability scores of the target articles through a dynamic classification model according to the inter-sentence probability, the confusion degree of the sentences and the inter-sentence similarity; the training process of the dynamic classification model is as follows: respectively inputting sample documents in a training document set into the inter-sentence model, the intra-sentence model and the similarity model which are trained, and obtaining the inter-sentence probability, the confusion and the inter-sentence similarity of the sample documents; and inputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample document as sample characteristics into a dynamic classification model for training. The method, the device, the equipment and the medium for determining the readability of the article, provided by the embodiment of the invention, realize the accurate determination of the readability of the article.
Description
Technical Field
The embodiment of the invention relates to the field of text readability analysis, in particular to a method, a device, equipment and a medium for determining readability of an article.
Background
In this era of internet information explosion, millions of articles are produced each day. It is well known that a well readable article can bring great economic significance to the reader.
However, there are cases where sentences or paragraphs are inconsistent and where wrongly written characters exist in sentences or paragraphs that are directly generated. Both of these situations can lead to the problem of article logic confusion and text incoherence. These problems directly affect the readability of the article, so that the number of articles with good real readability (logical legibility and text consistency) is much smaller.
Therefore, how to select and push the article with good readability to readers becomes a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a medium for determining readability of an article, so that the readability of the article can be accurately determined.
In a first aspect, an embodiment of the present invention provides an article readability determining method, where the method includes:
detecting a target article based on an inter-sentence model, an intra-sentence model and a similarity model to obtain inter-sentence probability, a perplexity of sentences and inter-sentence similarity;
determining readability scores of the target articles through a dynamic classification model according to the inter-sentence probability, the confusion degree of the sentences and the inter-sentence similarity;
wherein:
the intra-sentence model is obtained by training a neural network language model for determining sentence puzzleness, and the inter-sentence model is obtained by training a cross-sentence language model for determining inter-sentence probability;
wherein the training process of the dynamic classification model is as follows:
respectively inputting the sample documents in the training document set into the inter-sentence model, the intra-sentence model and the similarity model which are trained, and obtaining the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample documents;
and inputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample document as sample characteristics into a dynamic classification model for training.
In a second aspect, an embodiment of the present invention further provides an article readability determining apparatus, where the apparatus includes:
the characteristic determining module is used for detecting a target article based on the inter-sentence model, the intra-sentence model and the similarity model to obtain inter-sentence probability, the perplexity of sentences and the inter-sentence similarity;
the readability determining module is used for determining readability scores of the target articles through the dynamic classification model according to the inter-sentence probability, the perplexity of the sentences and the inter-sentence similarity;
wherein:
the intra-sentence model is obtained by training a neural network language model for determining sentence puzzleness, and the inter-sentence model is obtained by training a cross-sentence language model for determining inter-sentence probability;
wherein the training process of the dynamic classification model is as follows:
respectively inputting the sample documents in the training document set into the inter-sentence model, the intra-sentence model and the similarity model which are trained, and obtaining the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample documents;
and inputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample document as sample characteristics into a dynamic classification model for training.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
a storage device to store one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the article readability determination method according to any of the embodiments of the present invention.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for determining readability of an article according to any one of the embodiments of the present invention.
The readability score of the target article is determined according to the sentence characteristics and/or the paragraph characteristics in the target article. Therefore, readability of the article with the sentence or paragraph being incoherent and the sentence or paragraph having wrongly written characters is scored. And further selecting the article with good readability and pushing the article to the reader.
Drawings
Fig. 1 is a flowchart of an article readability determining method according to an embodiment of the present invention;
fig. 2 is a flowchart of an article readability determining method according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an article readability model according to a second embodiment of the present invention;
fig. 4 is a flowchart of an article readability determining method according to a third embodiment of the present invention;
FIG. 5 is a structural diagram of an article readability model according to a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of an article readability determining apparatus according to a fourth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an article readability determining method according to an embodiment of the present invention. The embodiment can be applied to the condition of readability detection of the produced article. The method may be performed by an article readability determining apparatus, which may be implemented in software and/or hardware. Referring to fig. 1, the method for determining readability of an article provided in this embodiment includes:
s110, sentences and/or paragraphs in the target article are detected, and sentence features of each sentence and/or paragraph features of each paragraph are determined.
Specifically, the sentence features include: inter-sentence correlations and/or intra-sentence correlations. Paragraph features include dependencies between titles and paragraphs and/or between paragraphs.
Further, the inter-sentence correlation includes: inter-sentence similarity and/or inter-sentence probability between adjacent sentences; the intra-sentence correlations include: confusion of each sentence.
Where the inter-sentence probability represents the probability of generating the next sentence from the current sentence.
The confusion (ppl) is used for indicating whether the language of the sentence is smooth or not, whether the sentence accords with the speaking logic of the person or not, and can also be understood as the probability of the person speaking.
In particular, both inter-sentence probability and confusion may be determined from a pre-trained language model.
And S120, determining the readability score of the target article according to the determined sentence characteristics of each sentence and/or the paragraph characteristics of each paragraph.
Specifically, the determined sentence features of each sentence and/or the paragraph features of each paragraph may be weighted and summed to determine the readability score of the target article.
Typically, the determining the readability score of the target article according to the determined sentence characteristics of each sentence and/or the paragraph characteristics of each paragraph includes:
and inputting the sentence characteristics of each sentence and/or the paragraph characteristics of each paragraph into a pre-trained dynamic classification model, and outputting the readability score of the target article.
Alternatively, the dynamic classification model may be any one of a dynamic Recurrent Neural Network (RNN), a dynamic Long-Short Term Memory (LSTM), and a dynamic Gated Recurrent Unit (GRU).
Because the number of paragraphs in the target article, and the number of sentences in the paragraphs, is variable. The number of constructed paragraph or sentence-based features is also variable.
And the dynamic classification model can be used for supplementing the features according to the feature quantity when the features are input, and inputting the supplemented features into the model. When the loss is calculated by using the loss function in the dynamic classification model, the loss is calculated only based on the processing result of the real feature, and the loss calculation is not performed on the processing result of the supplemented feature, so that the interference of the supplemented feature on the model is avoided. Therefore, classification of sentence features or paragraph features with unfixed feature length is realized by using the dynamic classification model.
According to the technical scheme of the embodiment of the invention, the readability score of the target article is determined according to the sentence characteristics and/or the paragraph characteristics in the target article. Therefore, readability of the article with the sentence or paragraph being incoherent and the sentence or paragraph having wrongly written characters is scored. And further selecting the article with good readability and pushing the article to the reader.
Example two
Fig. 2 is a flowchart of an article readability determining method according to a second embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 2, the method for readability of an article provided in this embodiment includes:
s210, detecting paragraphs in the target article, and determining the correlation between each paragraph and the title and the correlation between the paragraphs.
S220, inputting the determined correlation between each paragraph and the title and the correlation between the paragraphs into a pre-trained readability model based on a dynamic neural network, and outputting a readability score of the target article.
Referring to fig. 3, the relevance between paragraphs and a title extracted from a target article, and the relevance between paragraphs are taken as features and input into a readability model based on a dynamic neural network, wherein the model includes a weighted average layer and a full link layer. And finally, outputting the readability score of the target article.
According to the technical scheme of the embodiment of the invention, the readability model based on the dynamic neural network is input by taking the correlation between each paragraph and the title and the correlation between the paragraphs as characteristics, and the readability score of the article is output. Thereby enabling readability detection based on paragraph features.
EXAMPLE III
Fig. 4 is a flowchart of an article readability determining method according to a third embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 4, the method for determining readability of an article provided in this embodiment includes:
inputting a large number of high-quality documents into a neural network language model for determining sentence puzzlement, training to obtain an intra-sentence model, inputting a large number of high-quality documents into a cross-sentence language model for determining inter-sentence probability, and training to obtain an inter-sentence model.
And inputting the sample documents in the training document set into the trained inter-sentence model, intra-sentence model and similarity model, and outputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample documents.
And inputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the output sample document as sample characteristics into a dynamic classification model for training to obtain a readability model based on the sentence characteristics.
And inputting the target document into the readability model, and outputting the readability score of the target document.
Referring to fig. 5, the feature extraction layer takes the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sentences in the extracted target document as features to be input into the feature layer; the feature layer inputs the features into a dynamic classification network (any one of RNN, LSTM and GRU) layer, which outputs target document readability scores.
According to the technical scheme of the embodiment of the invention, an article readability model is constructed by constructing the inter-sentence correlation characteristic and the intra-sentence coherence characteristic and combining the dynamic classifier. The model can automatically judge the readability of the article and select the high-quality article.
It should be noted that, through the technical teaching of the present embodiment, a person skilled in the art may motivate a combination of any one of the implementations described in the above embodiments to achieve the determination of the readability of the article.
Example four
Fig. 6 is a schematic structural diagram of an article readability determining apparatus according to a fourth embodiment of the present invention. Referring to fig. 6, the article readability determining apparatus provided in the present embodiment includes: a feature determination module 10 and a readability determination module 20.
The feature determination module 10 is configured to detect sentences and/or paragraphs in a target article, and determine sentence features of each sentence and/or paragraph features of each paragraph;
and a readability determining module 20, configured to determine a readability score of the target article according to the determined sentence features of each sentence and/or the paragraph features of each paragraph.
According to the technical scheme of the embodiment of the invention, the readability score of the target article is determined according to the sentence characteristics and/or the paragraph characteristics in the target article. Therefore, the readability of the article with sentences or paragraphs which are inconsistent and wrongly written characters is scored. And further selecting the article with good readability and pushing the article to the reader.
Further, the sentence features include: inter-sentence correlations and/or intra-sentence correlations.
Further, the inter-sentence correlation includes: inter-sentence similarity and/or inter-sentence probability between adjacent sentences;
the intra-sentence correlations include: confusion of each sentence.
Further, the readability determination module, comprising: readability determining unit.
The readability determining unit is used for inputting the sentence characteristics of each sentence and/or the paragraph characteristics of each paragraph into a pre-trained dynamic classification model and outputting the readability score of the target article.
The article readability determining apparatus provided by the embodiment of the present invention can execute the article readability determining method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the executing method.
EXAMPLE five
Fig. 7 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention. Fig. 7 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 7 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present invention.
As shown in FIG. 7, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing the article readability determination method provided by the embodiment of the present invention.
EXAMPLE six
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for determining readability of an article according to any one of the embodiments of the present invention, where the method includes:
detecting sentences and/or paragraphs in the target article, and determining sentence characteristics of each sentence and/or paragraph characteristics of each paragraph;
and determining the readability score of the target article according to the determined sentence characteristics of each sentence and/or the paragraph characteristics of each paragraph.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having 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. In the context of this document, 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.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in some detail by the above embodiments, the invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the invention, and the scope of the invention is determined by the scope of the appended claims.
Claims (4)
1. A method for determining readability of an article, comprising:
detecting a target article based on an inter-sentence model, an intra-sentence model and a similarity model to obtain inter-sentence probability, a perplexity of sentences and inter-sentence similarity;
determining readability scores of the target articles through a dynamic classification model according to the inter-sentence probability, the perplexity of the sentences and the inter-sentence similarity;
wherein:
the intra-sentence model is obtained by training a neural network language model for determining sentence puzzleness, and the inter-sentence model is obtained by training a cross-sentence language model for determining inter-sentence probability;
wherein the training process of the dynamic classification model is as follows:
respectively inputting the sample documents in the training document set into the inter-sentence model, the intra-sentence model and the similarity model which are trained, and obtaining the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample documents;
and inputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample document as sample characteristics into a dynamic classification model for training.
2. An article readability determination apparatus, comprising:
the characteristic determining module is used for detecting a target article based on the inter-sentence model, the intra-sentence model and the similarity model to obtain inter-sentence probability, the perplexity of sentences and the inter-sentence similarity;
the readability determining module is used for determining readability scores of the target articles through the dynamic classification model according to the inter-sentence probability, the perplexity of the sentences and the inter-sentence similarity;
wherein:
the intra-sentence model is obtained by training a neural network language model for determining sentence puzzleness, and the inter-sentence model is obtained by training a cross-sentence language model for determining inter-sentence probability;
wherein the training process of the dynamic classification model is as follows:
respectively inputting the sample documents in the training document set into the inter-sentence model, the intra-sentence model and the similarity model which are trained, and obtaining the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample documents;
and inputting the inter-sentence probability, the confusion degree and the inter-sentence similarity of the sample document as sample characteristics into a dynamic classification model for training.
3. An apparatus, characterized in that the apparatus comprises:
one or more processors;
a storage device for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the article readability determination method of claim 1.
4. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the article readability determination method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811331517.3A CN109408829B (en) | 2018-11-09 | 2018-11-09 | Method, device, equipment and medium for determining readability of article |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811331517.3A CN109408829B (en) | 2018-11-09 | 2018-11-09 | Method, device, equipment and medium for determining readability of article |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109408829A CN109408829A (en) | 2019-03-01 |
| CN109408829B true CN109408829B (en) | 2022-06-24 |
Family
ID=65472685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811331517.3A Active CN109408829B (en) | 2018-11-09 | 2018-11-09 | Method, device, equipment and medium for determining readability of article |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109408829B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390032B (en) * | 2019-07-26 | 2021-08-17 | 江苏曲速教育科技有限公司 | Method and system for reading handwritten composition |
| CN110852087B (en) * | 2019-09-23 | 2022-02-22 | 腾讯科技（深圳）有限公司 | Chinese error correction method and device, storage medium and electronic device |
| CN110750979B (en) * | 2019-10-17 | 2023-07-25 | 科大讯飞股份有限公司 | Method for determining continuity of chapters and detection device |
| CN110795538B (en) * | 2019-10-30 | 2023-09-26 | 腾讯科技（深圳）有限公司 | Text scoring method and related equipment based on artificial intelligence |
| CN110874313B (en) * | 2019-11-18 | 2023-07-25 | 北京百度网讯科技有限公司 | Writing tool testing method and device |
| CN113408295B (en) * | 2021-06-22 | 2023-02-28 | 深圳证券信息有限公司 | Text readability evaluation method, computer device and computer storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654945A (en) * | 2015-10-29 | 2016-06-08 | 乐视致新电子科技（天津）有限公司 | Training method of language model, apparatus and equipment thereof |
| CN107967257A (en) * | 2017-11-20 | 2018-04-27 | 哈尔滨工业大学 | A kind of tandem type composition generation method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MXPA03006566A (en) * | 2001-01-23 | 2004-10-15 | Educational Testing Service | Methods for automated essay analysis. |
| US7720675B2 (en) * | 2003-10-27 | 2010-05-18 | Educational Testing Service | Method and system for determining text coherence |
| US9081760B2 (en) * | 2011-03-08 | 2015-07-14 | At&T Intellectual Property I, L.P. | System and method for building diverse language models |
| CN107766324B (en) * | 2017-09-25 | 2020-09-01 | 浙江大学 | Text consistency analysis method based on deep neural network |
| CN107977449A (en) * | 2017-12-14 | 2018-05-01 | 广东外语外贸大学 | A kind of linear model approach estimated for simplified form of Chinese Character readability |
-
2018
- 2018-11-09 CN CN201811331517.3A patent/CN109408829B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654945A (en) * | 2015-10-29 | 2016-06-08 | 乐视致新电子科技（天津）有限公司 | Training method of language model, apparatus and equipment thereof |
| CN107967257A (en) * | 2017-11-20 | 2018-04-27 | 哈尔滨工业大学 | A kind of tandem type composition generation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109408829A (en) | 2019-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109408829B (en) | Method, device, equipment and medium for determining readability of article | |
| CN107992596B (en) | Text clustering method, text clustering device, server and storage medium | |
| CN109670029B (en) | Method, apparatus, computer device and storage medium for determining answers to questions | |
| CN107908635B (en) | Method and device for establishing text classification model and text classification | |
| CN107832662B (en) | Method and system for acquiring image annotation data | |
| CN106940788B (en) | Intelligent scoring method and device, computer equipment and computer readable medium | |
| CN111428507A (en) | Entity chain finger method, device, equipment and storage medium | |
| CN107423278B (en) | Evaluation element identification method, device and system | |
| CN109614625B (en) | Method, device and equipment for determining title text relevancy and storage medium | |
| CN109599095B (en) | Method, device and equipment for marking voice data and computer storage medium | |
| CN109783490B (en) | Data fusion method and device, computer equipment and storage medium | |
| CN109918513B (en) | Image processing method, device, server and storage medium | |
| CN109034203B (en) | Method, device, equipment and medium for training expression recommendation model and recommending expression | |
| CN107909088B (en) | Method, apparatus, device and computer storage medium for obtaining training samples | |
| CN107301248B (en) | Word vector construction method and device of text, computer equipment and storage medium | |
| CN109325108B (en) | Query processing method, device, server and storage medium | |
| CN111950279A (en) | Entity relationship processing method, device, equipment and computer readable storage medium | |
| CN112214595A (en) | Category determination method, device, equipment and medium | |
| CN109657127B (en) | Answer obtaining method, device, server and storage medium | |
| CN111125550A (en) | Interest point classification method, device, equipment and storage medium | |
| CN111460224B (en) | Comment data quality labeling method, comment data quality labeling device, comment data quality labeling equipment and storage medium | |
| CN112883218A (en) | Image-text combined representation searching method, system, server and storage medium | |
| CN111738791A (en) | Text processing method, device, equipment and storage medium | |
| CN115525750A (en) | Robot phonetics detection visualization method and device, electronic equipment and storage medium | |
| CN111552780B (en) | Medical scene search processing method and device, storage medium and electronic equipment |
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 |