CN111767710A - Indonesia emotion classification method, device, equipment and medium - Google Patents

Indonesia emotion classification method, device, equipment and medium Download PDF

Info

Publication number
CN111767710A
CN111767710A CN202010402298.4A CN202010402298A CN111767710A CN 111767710 A CN111767710 A CN 111767710A CN 202010402298 A CN202010402298 A CN 202010402298A CN 111767710 A CN111767710 A CN 111767710A
Authority
CN
China
Prior art keywords
indonesia
general representation
processed
representation information
emotion classification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010402298.4A
Other languages
Chinese (zh)
Other versions
CN111767710B (en
Inventor
林楠铠
蒋盛益
林晓钿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong University of Foreign Studies
Original Assignee
Guangdong University of Foreign Studies
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong University of Foreign Studies filed Critical Guangdong University of Foreign Studies
Priority to CN202010402298.4A priority Critical patent/CN111767710B/en
Publication of CN111767710A publication Critical patent/CN111767710A/en
Application granted granted Critical
Publication of CN111767710B publication Critical patent/CN111767710B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G06F16/35—Clustering; Classification
    • G06F16/355—Class or cluster creation or modification
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses an emotion classification method for Indonesia, which is characterized by comprising the following steps: acquiring Indonesian sentences to be processed, and determining a domain descriptor corresponding to the Indonesian sentences to be processed; calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the Indonesia sentence to be processed; calculating to obtain general domain representation information according to the domain descriptor and the general representation information; carrying out weighted calculation on the field general representation information in a memory network sample library corresponding to the current field to obtain text characteristic information; and determining a corresponding emotion classification result according to the text characteristic information. The embodiment of the invention also discloses an emotion classification device, equipment and a medium for Indonesia, so that the Indonesia can be subjected to emotion classification in multiple fields.

Description

Indonesia emotion classification method, device, equipment and medium
Technical Field
The invention relates to the technical field of Indonesia emotion classification, in particular to an emotion classification method, device, equipment and medium for Indonesia.
Background
Currently, the sentiment analysis research in Indonesia is mainly divided into two tasks: and constructing an emotion dictionary and text emotion recognition, but the emotion dictionary and text emotion recognition can only be applied to emotion classification tasks in a single field. However, the research development of the existing multi-domain emotion classification task is still limited, and most of the work is concentrated on english research, but the existing multi-domain emotion classification task cannot be directly applied to indonesia due to the large difference between indonesia and english, so that the indonesia in multiple domains cannot be classified.
Disclosure of Invention
The embodiment of the invention provides an emotion classification method, device, equipment and medium for Indonesia, which can be used for carrying out emotion classification on Indonesia in multiple fields.
An embodiment of the present invention provides an emotion classification method for indonesia, including:
acquiring Indonesian sentences to be processed, and determining a domain descriptor corresponding to the Indonesian sentences to be processed;
calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the Indonesia sentence to be processed;
calculating to obtain general domain representation information according to the domain descriptor and the general representation information;
carrying out weighted calculation on the field general representation information in a memory network sample library corresponding to the current field to obtain text characteristic information;
and determining a corresponding emotion classification result according to the text characteristic information.
As an improvement of the above scheme, the calculating the indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the indonesia sentence to be processed specifically includes:
acquiring the n-gram characteristics of the Indonesian sentences to be processed according to the multi-scale convolution kernel;
and calculating the n-gram characteristics according to the BILSTM layer to obtain the general representation information corresponding to the Indonesia sentence to be processed.
As an improvement of the above solution, the calculating to obtain the domain general representation information according to the domain descriptor and the general representation information specifically includes:
calculating similarity according to the domain descriptor and the general representation information;
and performing regression processing according to the similarity and the general representation information to obtain the general representation information of the field.
As an improvement of the above scheme, the performing weighted calculation on the domain general representation information in a memory network sample library corresponding to the current domain to obtain text feature information specifically includes:
and performing weighted calculation on the field general representation information and the general information in the corresponding memory network sample library according to the dot product attribute to obtain text characteristic information.
As an improvement of the above scheme, the determining a corresponding emotion classification result according to the text feature information specifically includes:
mapping the text characteristic information into a corresponding three-dimensional vector through a full connection layer;
regularizing the three-dimensional vector according to a softmax function, and determining a corresponding emotion classification result; wherein, the emotion classification result comprises: positive emotions, neutral emotions, and negative emotions.
As an improvement of the above scheme, the calculating the indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the indonesia sentence to be processed further includes:
and performing countermeasure training on the general representation information according to a preset countermeasure learning method so that the general representation information does not contain the field information.
Another embodiment of the present invention correspondingly provides an emotion classifying apparatus for indonesia, including:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring Indonesia sentences to be processed and determining the corresponding domain descriptors of the Indonesia sentences to be processed;
the first processing module is used for calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the Indonesia sentence to be processed;
the second processing module is used for calculating and obtaining general representation information of the field according to the field descriptor and the general representation information;
the third processing module is used for carrying out weighted calculation on the field general representation information in a memory network sample library corresponding to the current field to obtain text characteristic information;
and the classification module is used for determining a corresponding emotion classification result according to the text characteristic information.
Another embodiment of the present invention provides an emotion classification apparatus for indonesia, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor implements the emotion classification method for indonesia according to the above embodiment of the present invention when executing the computer program.
Another embodiment of the present invention provides a storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, a device where the computer-readable storage medium is located is controlled to execute the emotion classification method for indonesia according to the above-described embodiment of the present invention.
Compared with the prior art, the sentiment classification method, the device, the equipment and the medium for Indonesia disclosed by the embodiment of the invention have the advantages that by acquiring Indonesia sentences to be processed and determining the corresponding domain descriptors of the Indonesia sentences to be processed; calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the Indonesia sentence to be processed; calculating to obtain general domain representation information according to the domain descriptor and the general representation information; carrying out weighted calculation on the domain general representation information in a memory network sample library corresponding to the domain descriptor to obtain text characteristic information; and determining a corresponding emotion classification result according to the text characteristic information. The general representation of Indonesia can be applied to multiple domains, so that Indonesia can be classified emotionally in multiple domains.
Drawings
FIG. 1 is a flowchart illustrating an emotion classification method for Indonesia according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an emotion classification apparatus for Indonesia according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an emotion classification apparatus for indonesia according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of an emotion classification method for indonesia according to an embodiment of the present invention.
An embodiment of the present invention provides an emotion classification method for indonesia, including:
s10, acquiring Indonesia sentences to be processed, and determining the corresponding domain descriptor of the Indonesia sentences to be processed.
S20, calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain the general representation information corresponding to the Indonesia sentence to be processed.
And S30, calculating the general representation information of the domain according to the domain descriptor and the general representation information.
And S40, performing weighted calculation on the domain general representation information in a memory network sample library corresponding to the current domain to obtain text characteristic information.
And S50, determining a corresponding emotion classification result according to the text feature information.
It should be noted that, in the classification process, each indonesian sentence to be processed corresponds to one field, and thus a field descriptor can be obtained. It is understood that the domain may be directly set by the user, or may be identified according to a domain classifier. In this embodiment, the fields include: hotels, restaurants, etc.
When the model is trained, the Indonesia sentence to be trained is identified according to the domain classifier, and the model is continuously trained, so that the domain descriptor can be more accurately acquired through the domain classifier. In this embodiment, self-attribute is used for training, and the domain descriptors of similar domains are updated.
In summary, by identifying the descriptor in the indonesia and combining the descriptor with the general information to obtain the domain descriptor, the general representation of the indonesia can be applied to multiple domains, so that the indonesia can be classified in multiple domains.
In the foregoing embodiment, preferably, the step S20 includes calculating the indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the indonesia sentence to be processed, and specifically:
and acquiring the n-gram characteristics of the Indonesian sentences to be processed according to the multi-scale convolution kernel.
Specifically, in the convolution operation of CNN, there are a plurality of convolution kernels of different scales to perform feature extraction on a text at the same time, so as to extract n-gram features of different granularities.
And calculating the n-gram characteristics according to the BILSTM layer to obtain the general representation information corresponding to the Indonesia sentence to be processed.
Specifically, let the input sentence matrix be C, where the dimension of each word is d (including d)wWord vector representation of dimension and dpA position vector of the dimension). To obtain a characteristic representation of the input sentence, a model initialization window size k filter is used for the convolution operation, which is wideThe degree is consistent with the word vector dimension. The convolution operation is as follows:
Figure BDA0002489954760000061
wherein, ". represents a point product, σ represents a sigmoid activation function, C [ i: i + k ]]Representing the i to i + k word vector sequences, HkA convolution kernel of width k, and b a bias parameter. In order to ensure that the feature graph lengths extracted by different convolution kernels are consistent, the SAME padding strategy is adopted to ensure that the feature output and input sequence lengths with different granularities are consistent. In order to better capture the overall information among the feature sequences, the BilSTM is placed in the CNN, the context of the feature sequences is captured through the BilSTM, and the output is as follows after passing through a BilSTM layer:
Figure BDA0002489954760000062
wherein
Figure BDA0002489954760000063
Is a hidden representation (i.e. output) of BiLSTM,
Figure BDA0002489954760000064
representing the sum operation of the corresponding values between the two hidden states.
As an improvement of the above solution, the step S30 specifically includes the step of calculating general representation information of the domain according to the domain descriptor and the general representation information, and includes:
calculating similarity according to the domain descriptor and the general representation information;
and performing regression processing according to the similarity and the general representation information to obtain the general representation information of the field.
Specifically, the use of dot product attention is adopted in self-attention
Figure BDA0002489954760000065
Calculating NiAnd each domain descriptor, the dot-product values are normalized using the softmax function,
Figure BDA0002489954760000066
the summed values are weighted for all domain descriptors.
Figure BDA0002489954760000067
For weighted representation of a generic representation (generic representation) of the output of the text representation layer.
Domain descriptor is used to capture domain features, the dimension of which is N ∈ R2K*mEach field descriptor is 2K in length for each column in N. The matrix is also synchronously and automatically updated and trained in the training process.
During training, an input is given
Figure BDA0002489954760000068
We adopt the embedding layer and the CNN-BilSTM to obtain a general representation of the input
Figure BDA0002489954760000069
And use the corresponding domain descriptor NiWeighting to obtain a domain-specific representation, and calculating as follows:
Figure BDA0002489954760000071
Figure BDA0002489954760000072
Figure BDA0002489954760000073
Figure BDA0002489954760000074
representing a domain identifier NiAnd general representation
Figure BDA0002489954760000075
Degree of similarity P ∈ R4K*2K、Q∈R4K*2K、v∈R4KFor addiveattention parameters, P and Q are N, respectivelyiAnd
Figure BDA0002489954760000076
linearly projecting to a hidden layer, and regularizing by adopting a Softmax function
Figure BDA0002489954760000077
As an improvement of the above scheme, the step S40 specifically includes performing weighted calculation on the domain general representation information in a memory network sample library corresponding to the current domain to obtain text feature information:
and performing weighted calculation on the field general representation information and the general information in the corresponding memory network sample library according to the dot product attribute to obtain text characteristic information. Wherein the memory network sample library is a memorynetwork.
Specifically, one is adopted
Figure BDA0002489954760000078
(DiFor training samples of the ith domain) to capture a domain-specific representation of the training samples of the ith domain
Figure BDA0002489954760000079
Is provided with
Figure BDA00024899547600000710
Is MiColumn j of (1), then
Figure BDA00024899547600000711
Given an input
Figure BDA00024899547600000712
Generating a text feature vector (i.e. text feature information)
Figure BDA00024899547600000713
By using
Figure BDA00024899547600000714
De-computation
Figure BDA00024899547600000715
And MiAnd regularized using a Softmax function. The obtained text feature vector is MiAnd performing weighted summation on each column of the matrix to obtain text characteristic information.
It should be noted that, during training, the text feature information is stored in the memory network sample library.
Specifically, the text characteristic information is stored in a memory network sample library, so that the memorynetwork can be trained continuously, and the obtained text characteristic information is more accurate.
As an improvement of the above scheme, the determining a corresponding emotion classification result according to the text feature information specifically includes:
and mapping the text characteristic information into a corresponding three-dimensional vector through a full connection layer.
Regularizing the three-dimensional vector according to a softmax function, and determining a corresponding emotion classification result; wherein, the emotion classification result comprises: positive emotions, negative emotions, and neutral emotions.
Specifically, the text feature information is that the text feature vector is mapped to a three-dimensional vector through a full connection layer, and is regularized by adopting a softmax function, so that a final emotion classification result is obtained.
As an improvement of the above scheme, the calculating the indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the indonesia sentence to be processed further includes:
and performing countermeasure training on the general representation information according to a preset countermeasure learning method so that the general representation information does not contain the field information.
In particular, the input sequence is predicted
Figure BDA0002489954760000081
Probability from each field i, we will sample from field i
Figure BDA0002489954760000082
Is defined as the cross-entropy loss of
Figure BDA0002489954760000083
Data D for Domain iiMinimizing its loss
Figure BDA0002489954760000084
Maximizing loss of domain classifiers
Figure BDA0002489954760000085
And weighted with λ:
Figure BDA0002489954760000086
θdsparameters for each domain, including domain descriptor, attribute weight, and Softmax parameter. The countermeasure portion is by updating thetadcTo maximize the loss:
Figure BDA0002489954760000087
the two portions are iteratively executed to generate a domain-invariant representation to enhance the generic representation.
Fig. 2 is a schematic structural diagram of an emotion classification apparatus for indonesia according to an embodiment of the present invention.
Another embodiment of the present invention correspondingly provides an emotion classifying apparatus for indonesia, including:
an obtaining module 10, configured to obtain an indonesia sentence to be processed, and determine a domain descriptor corresponding to the indonesia sentence to be processed.
The first processing module 20 is configured to calculate the indonesia sentence to be processed according to a preset CNN-BILSTM model, so as to obtain general representation information corresponding to the indonesia sentence to be processed.
And a second processing module 30, configured to calculate, according to the domain descriptor and the general representation information, domain general representation information.
And the third processing module 40 is configured to perform weighted calculation on the domain general representation information in a memory network sample library corresponding to the current domain to obtain text feature information.
And the classification module 50 is configured to determine a corresponding emotion classification result according to the text feature information.
According to the sentiment classification device for Indonesia provided by the embodiment of the invention, the descriptor in the Indonesia is identified, and then the descriptor is combined with the general information to obtain the domain descriptor, so that the general representation of the Indonesia can be suitable for multiple fields, and the Indonesia can be subjected to sentiment classification in multiple fields.
Fig. 3 is a schematic diagram of an emotion classification apparatus for indonesia according to an embodiment of the present invention. The emotion classification apparatus in indonesia of this embodiment includes: a processor 11, a memory 12 and a computer program stored in said memory 12 and executable on said processor 11. The processor 11 implements the steps in the embodiments of the syntax error correction method for indonesia described above when executing the computer program. Alternatively, the processor 11 implements the functions of the modules/units in the above-described device embodiments when executing the computer program.
Illustratively, the computer program may be divided into one or more modules/units, which are stored in the memory 12 and executed by the processor 11 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the sentiment classification device of Indonesia.
The sentiment classification device of Indonesian can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The sentiment classification device of Indonesia can include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of an emotion classification apparatus in Indonesia and does not constitute a limitation of the emotion classification apparatus in Indonesia, and may include more or fewer components than those shown, or some components in combination, or different components, for example, the emotion classification apparatus in Indonesia may also include input output devices, network access devices, buses, etc.
The Processor 11 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center for the sentiment classification device in indonesia, with various interfaces and lines connecting the various parts of the entire sentiment classification device in indonesia.
The memory 12 may be used to store the computer programs and/or modules, and the processor may implement the various functions of the sentiment classification device in indonesia by running or executing the computer programs and/or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein, the module/unit integrated by the sentiment classification device of Indonesia can be stored in a computer readable storage medium if the module/unit is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.

Claims (9)

1. A sentiment classification method for Indonesia is characterized by comprising the following steps:
acquiring Indonesian sentences to be processed, and determining a domain descriptor corresponding to the Indonesian sentences to be processed;
calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the Indonesia sentence to be processed;
calculating to obtain general domain representation information according to the domain descriptor and the general representation information;
carrying out weighted calculation on the field general representation information in a memory network sample library corresponding to the current field to obtain text characteristic information;
and determining a corresponding emotion classification result according to the text characteristic information.
2. The emotion classification method for indonesia according to claim 1, wherein the calculating the indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain the general representation information corresponding to the indonesia sentence to be processed specifically includes:
acquiring the n-gram characteristics of the Indonesian sentences to be processed according to the multi-scale convolution kernel;
and calculating the n-gram characteristics according to the BILSTM layer to obtain the general representation information corresponding to the Indonesia sentence to be processed.
3. The emotion classification method for Indonesia as claimed in claim 1, wherein the calculating of domain general representation information from the domain descriptor and the general representation information specifically comprises:
calculating similarity according to the domain descriptor and the general representation information;
and performing regression processing according to the similarity and the general representation information to obtain the general representation information of the field.
4. The emotion classification method for indonesia according to claim 1, wherein the weighting calculation of the domain general representation information in the memory network sample library corresponding to the current domain is performed to obtain text feature information, and specifically includes:
and performing weighted calculation on the field general representation information and the general information in the corresponding memory network sample library according to the dot product attribute to obtain text characteristic information.
5. The emotion classification method of indonesia according to claim 1, wherein the determining of the corresponding emotion classification result according to the text feature information specifically includes:
mapping the text characteristic information into a corresponding three-dimensional vector through a full connection layer;
regularizing the three-dimensional vector according to a softmax function, and determining a corresponding emotion classification result; wherein, the emotion classification result comprises: positive emotions, neutral emotions, and negative emotions.
6. The emotion classification method of indonesia as claimed in claim 1, wherein the computing is performed on the indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain the general representation information corresponding to the indonesia sentence to be processed, and then further comprising:
and performing countermeasure training on the general representation information according to a preset countermeasure learning method so that the general representation information does not contain the field information.
7. An emotion classification device for Indonesia, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring Indonesia sentences to be processed and determining the corresponding domain descriptors of the Indonesia sentences to be processed;
the first processing module is used for calculating the Indonesia sentence to be processed according to a preset CNN-BILSTM model to obtain general representation information corresponding to the Indonesia sentence to be processed;
the second processing module is used for calculating and obtaining general representation information of the field according to the field descriptor and the general representation information;
the third processing module is used for carrying out weighted calculation on the field general representation information in a memory network sample library corresponding to the current field to obtain text characteristic information;
and the classification module is used for determining a corresponding emotion classification result according to the text characteristic information.
8. An emotion classification apparatus for Indonesia, comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the emotion classification method for Indonesia as claimed in any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the emotion classification method for indonesia according to any one of claims 1 to 6.
CN202010402298.4A 2020-05-13 2020-05-13 Indonesia emotion classification method, device, equipment and medium Active CN111767710B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010402298.4A CN111767710B (en) 2020-05-13 2020-05-13 Indonesia emotion classification method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010402298.4A CN111767710B (en) 2020-05-13 2020-05-13 Indonesia emotion classification method, device, equipment and medium

Publications (2)

Publication Number Publication Date
CN111767710A true CN111767710A (en) 2020-10-13
CN111767710B CN111767710B (en) 2023-03-28

Family

ID=72719067

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010402298.4A Active CN111767710B (en) 2020-05-13 2020-05-13 Indonesia emotion classification method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN111767710B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657446A (en) * 2021-07-13 2021-11-16 广东外语外贸大学 Processing method, system and storage medium of multi-label emotion classification model

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180165554A1 (en) * 2016-12-09 2018-06-14 The Research Foundation For The State University Of New York Semisupervised autoencoder for sentiment analysis
CN110678881A (en) * 2017-05-19 2020-01-10 易享信息技术有限公司 Natural language processing using context-specific word vectors

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180165554A1 (en) * 2016-12-09 2018-06-14 The Research Foundation For The State University Of New York Semisupervised autoencoder for sentiment analysis
CN110678881A (en) * 2017-05-19 2020-01-10 易享信息技术有限公司 Natural language processing using context-specific word vectors

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
AQSATH RASYID NARADHIPA ET AL.: "Sentiment Classification for Indonesian Message in Social Media", 《2011 INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING AND INFORMATICS》 *
YITAO CAI ET AL.: "Multi-Domain Sentiment Classification Based on Domain-Aware Embedding and Attention", 《PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-19)》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657446A (en) * 2021-07-13 2021-11-16 广东外语外贸大学 Processing method, system and storage medium of multi-label emotion classification model

Also Published As

Publication number Publication date
CN111767710B (en) 2023-03-28

Similar Documents

Publication Publication Date Title
CN108351984B (en) Hardware-efficient deep convolutional neural network
US10621971B2 (en) Method and device for extracting speech feature based on artificial intelligence
CN109471944B (en) Training method and device of text classification model and readable storage medium
CN109684476B (en) Text classification method, text classification device and terminal equipment
CN111831826B (en) Training method, classification method and device of cross-domain text classification model
CN109117474B (en) Statement similarity calculation method and device and storage medium
EP3620982B1 (en) Sample processing method and device
CN113722438A (en) Sentence vector generation method and device based on sentence vector model and computer equipment
CN111460806A (en) Loss function-based intention identification method, device, equipment and storage medium
CN109637529A (en) Voice-based functional localization method, apparatus, computer equipment and storage medium
CN113011531A (en) Classification model training method and device, terminal equipment and storage medium
CN110377708B (en) Multi-scene conversation switching method and device
CN112560463B (en) Text multi-labeling method, device, equipment and storage medium
CN111767710B (en) Indonesia emotion classification method, device, equipment and medium
CN111859933B (en) Training method, recognition method, device and equipment for maleic language recognition model
CN116680401A (en) Document processing method, document processing device, apparatus and storage medium
CN110765917A (en) Active learning method, device, terminal and medium suitable for face recognition model training
CN112419249B (en) Special clothing picture conversion method, terminal device and storage medium
CN111159403B (en) Intelligent classroom perception method and system
CN112036183A (en) Word segmentation method and device based on BilSTM network model and CRF model, computer device and computer storage medium
CN111368083A (en) Text classification method, device and equipment based on intention confusion and storage medium
CN111382246A (en) Text matching method, matching device and terminal
Loong et al. Image‐based structural analysis for education purposes: A proof‐of‐concept study
CN113553841B (en) Word characterization method, word characterization device, electronic equipment and storage medium
CN112347196B (en) Entity relation extraction method and device based on neural network

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