CN112100376A - Mutual enhancement conversion network for fine-grained emotion analysis - Google Patents

Mutual enhancement conversion network for fine-grained emotion analysis Download PDF

Info

Publication number
CN112100376A
CN112100376A CN202010951154.4A CN202010951154A CN112100376A CN 112100376 A CN112100376 A CN 112100376A CN 202010951154 A CN202010951154 A CN 202010951154A CN 112100376 A CN112100376 A CN 112100376A
Authority
CN
China
Prior art keywords
attribute
word
representation
layer
bidirectional
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
CN202010951154.4A
Other languages
Chinese (zh)
Other versions
CN112100376B (en
Inventor
蒋斌
侯静
杨超
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.)
Hunan University
Original Assignee
Hunan University
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 Hunan University filed Critical Hunan University
Priority to CN202010951154.4A priority Critical patent/CN112100376B/en
Publication of CN112100376A publication Critical patent/CN112100376A/en
Application granted granted Critical
Publication of CN112100376B publication Critical patent/CN112100376B/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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Machine Translation (AREA)

Abstract

The invention relates to a mutual enhancement conversion network for fine-grained emotion analysis, belonging to a fine-grained emotion analysis task aiming at determining the emotion polarity of each specific attribute in a given sentence. The invention provides a mutual enhancement conversion network for fine-grained emotion analysis. First, the attribute enhancement module in the network refines the attribute characterization learning by semantic features extracted from sentences to give richer information to the attributes. Second, the network iteratively enhances the representation of attributes and contexts using a hierarchy to achieve more accurate emotion prediction. The invention is effective for fine-grained emotion analysis tasks and performs well in both single-attribute sentences and multi-attribute sentences.

Description

Mutual enhancement conversion network for fine-grained emotion analysis
Technical Field
The invention relates to a mutual enhancement conversion network for fine-grained emotion analysis, and belongs to the technical field of fine-grained emotion analysis tasks.
Background
The fine-grained sentiment analysis task comprises two subtasks, namely attribute extraction and attribute sentiment classification. The invention assumes that the attributes are known and focuses only on the attribute emotion classification task. In the fine-grained emotion analysis task, multiple attributes may appear in one sentence. Other attributes and related words become noisy when predicting the emotion of the current attribute. Therefore, how to efficiently model semantic relationships between a given attribute and words in a sentence is an important challenge.
The traditional method mainly depends on the characteristics of manual design, and the characterization mode almost reaches the performance bottleneck. With the development of deep learning technology, especially the proposal of attention mechanism, the above problems are well solved, and many neural attention models are proposed. In these works, the model typically first takes a representation of the attributes, and then applies an attention mechanism to extract contextual features that are relevant to the given attributes for emotion prediction. Attention machines, however, have some drawbacks. When a sentence contains multiple attributes and they have different emotional tendencies, the viewpoint modifiers of the other attributes are noise information for the current attribute. However, attention mechanisms have difficulty learning different perspective modifiers that distinguish multiple attributes, and this directly affects the final prediction result. For example, in the sentence "I like coming back to Mac OS but this is a stitch is lacking in the spoke quality compensated to my $400old HP lap", the attention force mechanism should pay more attention to the opinion word "like" with positive emotional tendency for the attribute "Mac OS". However, attention mechanisms typically involve unrelated opinion words, such as the opinion word "lacing" with negative emotional tendencies, which can interfere with emotion prediction for the attribute "Mac OS". To this end, researchers have proposed some work to ameliorate the drawbacks of the attention mechanism. However, most work has been directed to designing complex neural networks to improve the characterization learning of context. Little work has been focused on improving the characterization learning of attributes.
Disclosure of Invention
The invention provides a mutual enhancement conversion network for fine-grained emotion analysis, which aims to determine the emotion polarity of each specific attribute in a given sentence.
The invention comprises a BERT layer, a bidirectional enhanced conversion layer and a convolution characteristic extractor which are connected in sequence;
the BERT layer generates a word representation of the sequence using pre-trained BERT;
the bidirectional enhancement conversion layer comprises a bidirectional LSTM layer, an attribute enhancement module and a group of word conversion units, wherein the bidirectional LSTM layer is respectively connected with the attribute enhancement module and the word conversion units;
the bidirectional LSTM layer is used for capturing long dependency relationship and position information between texts, and the encoding result has two directions, one is an attribute enhancement module, and the other is a word conversion unit;
the attribute enhancement module receives the attribute representation and the average of the bidirectional LSTM layer coding result, and finally outputs an enhanced attribute representation which is input into the word conversion unit;
the attribute enhancement module utilizes the extracted context characteristics to enhance the attributes;
the word conversion unit receives the encoding result from the bidirectional LSTM layer and the enhanced attribute representation from the attribute enhancement module;
the convolutional feature extractor receives attribute information using a GCAE network to control the transfer of the emotional features of the sentence, which further enhances the link between the attributes and the context, and furthermore, introduces relative position information to better extract the emotional features.
The process of reasoning and training through the mutual enhancement conversion network for fine-grained emotion analysis is as follows:
step 1, a BERT layer, which uses pre-trained BERT to generate word representation of a sequence, supposing that a sentence contains m words and an attribute contains n words, vector representation of the sentence can be obtained through the BERT layer
Figure BDA0002676980070000021
Vector representation of sum attribute a ═ a1,a2,...,an}∈Rn×dWhere d represents the dimension of the BERT output layer.
And 2, bidirectional enhancement conversion layers, wherein each bidirectional enhancement conversion layer comprises three parts, namely a bidirectional LSTM layer, an attribute enhancement module and a group of character conversion units. The bi-directional LSTM layer first generates a contextualized word representation from the input. The attribute enhancement module then uses the word representations to enhance the attribute representations. Finally, the word conversion unit generates an attribute-specific word representation based on the contextualized word representation and the enhanced attribute representation.
And S21, learning the context dependence relationship of the text through the bidirectional LSTM layer. As shown in fig. 1, the bidirectional enhancement translation layer is repeated a plurality of times through the hierarchical structure. The input of the bi-directional LSTM in the lowest bi-directional enhancement conversion layer is a contextual representation of the BERT layer output. The input to the bi-directional LSTM in the next bi-directional enhancement conversion layer is from the output of the word conversion unit in the previous bi-directional enhancement conversion layer.
The word representation of the bidirectional LSTM output may be represented as
Figure BDA0002676980070000022
Forward LSTM outputs a set of hidden state vectors
Figure BDA0002676980070000023
Wherein d ishIndicating the number of hidden units. Similarly, backward LSTM also outputs a set of hidden state vectors
Figure BDA0002676980070000024
Finally, the word representation of the bidirectional LSTM output is obtained by connecting the two hidden state lists
Figure BDA0002676980070000025
Wherein
Figure BDA0002676980070000026
S22, attribute enhancing module, before the first attribute enhancing operation, obtaining the initial attribute representation. Specifically, the attribute vector a output by BERT is first set to { a ═ a }1,a2,...,an}∈Rn×dInput into another bi-directional LSTM, and then apply to the obtained hidden state vector
Figure BDA0002676980070000027
Using an averaging pooling methodFinally, an initial attribute representation is obtained
Figure BDA0002676980070000028
Taking the lowest bi-directional enhancement translation layer as an example, after obtaining the initial attribute representation, the contextualized word vector h is output based on the bi-directional LSTM(1)We obtain a vector by averaging the pooling layers
Figure BDA0002676980070000029
This is referred to as a context vector. The context vectors are then fused into the initial attribute representation using a basic feature fusion method (point-by-bit addition), which can be expressed as
Figure BDA0002676980070000031
This is an enhancement operation that acts on the attribute. And so on, the final attribute representation is
Figure BDA0002676980070000032
This formula expands as follows:
Figure BDA0002676980070000033
wherein
Figure BDA0002676980070000034
Representing the context vector in the ith dyad conversion layer. According to equation (1), the attributes are enhanced by different context vectors in multiple dyads. Attribute vector
Figure BDA0002676980070000035
There are two destinations, one destination being a word conversion unit in the same dyad and the other destination being a property enhancement module in the next dyad.
S23, a word conversion unit, which uses the same structure as the CPT module in the TNet model. The unit will attribute the vector
Figure BDA0002676980070000036
And the word represents
Figure BDA0002676980070000037
As an input, wherein
Figure BDA0002676980070000038
Is represented by the ith word level of the bi-directional LSTM layer output,
Figure BDA0002676980070000039
is the enhanced attribute vector. Specifically, firstly, the
Figure BDA00026769800700000310
And
Figure BDA00026769800700000311
is input to a full connection layer to obtain an ith attribute-specific word representation
Figure BDA00026769800700000312
Figure BDA00026769800700000313
Where g (—) is a non-linear activation function and ": means a vector join operation.
Figure BDA00026769800700000314
And
Figure BDA00026769800700000315
respectively weight matrix and bias. There is an information protection mechanism to ensure that context dependent information captured from the bi-directional LSTM layer is not lost. This information protection mechanism enhances the delivery and use of features, which can be expressed as:
Figure BDA00026769800700000316
wherein
Figure BDA00026769800700000317
Is the output of the word conversion unit.
Step 3, a convolution feature extractor is introduced to a variable piTo measure the relative position information between the ith word and the current attribute word in the context, piIs calculated as follows:
Figure BDA00026769800700000318
where k is the index of the first word in the attribute, C is a pre-specified constant, and n is the length of the attribute phrase. When a sentence is filled, the index i may be larger than the actual length m of the sentence. Then, p is addediThe word output by the ith word conversion unit in the Lth bidirectional enhanced conversion layer is multiplied by the weight to represent that:
Figure BDA00026769800700000319
x at this timeiIs a word representation that incorporates location information.
Then, the sentence with the position information is expressed with X ═ X1,x2,...,xmAnd the final attribute vector
Figure BDA0002676980070000041
Inputting into a gated convolution network to generate a feature map c:
Figure BDA0002676980070000042
si＝tanh(WsXi:i+k-1+bs) (7)
ci＝si×ai (8)
where k is the convolution kernel size, Wa，Va，ba，WsAnd bsAre all learnable parameters, ciIs one item in the feature map c, siIs a calculated emotional feature, aiIs the calculated attribute feature; x denotes element-by-element multiplication. Then, the sentence representation z is obtained by s convolution kernels and applying the maximum pooling method:
z＝{max(c1),...,max(cs)} (9)
where max is a function of the maximum. Finally, z is input to a fully connected layer for final emotion prediction:
Figure BDA0002676980070000043
wherein softmax is a normalized exponential function, WfAnd bfAre learnable parameters.
Step 4, the mutually enhanced transformation network for fine-grained sentiment analysis referred to herein can be trained in an end-to-end manner within a supervised learning framework to optimize all parameters Θ. With L2The cross entropy of the regularization term is used as a loss function, defined as:
Figure BDA0002676980070000044
wherein y isiRepresenting the true probability that a given sentence is labeled as each emotion,
Figure BDA0002676980070000045
representing the estimated probability that a given sentence is labeled as each emotion, O representing the number of classes of emotion polarity, and λ being L2Parameters of the regularization term.
The method has the advantages of improving the attribute characterization learning and realizing the iterative interactive learning between the attribute and the context. The attribute enhancement module in the network improves the attribute characterization learning through semantic features extracted from sentences so as to endow the attributes with richer information. Second, the network iteratively enhances the representation of attributes and contexts using a hierarchy to achieve more accurate emotion prediction.
Drawings
FIG. 1 is an overall architecture of a mutually enhanced conversion network for fine-grained sentiment analysis.
Fig. 2 is a structural diagram of the first bidirectional enhanced conversion module.
Fig. 3 is a block diagram of a word conversion unit.
Detailed Description
In the following, preferred embodiments of the present invention will be further explained with reference to fig. 1 to 3, wherein the dashed arrows in fig. 1 represent the conversion of attributes, and the solid arrows represent the conversion of sentences.
The invention comprises a BERT layer, a bidirectional enhanced conversion layer and a convolution characteristic extractor which are connected in sequence;
the BERT layer generates a word representation of the sequence using pre-trained BERT; BERT is an english abbreviation expressed by the bidirectional coder of the transform model, which is a common abbreviation of those skilled in the art.
The bidirectional enhancement conversion layer comprises a bidirectional LSTM layer, an attribute enhancement module and a group of word conversion units, wherein the bidirectional LSTM layer is respectively connected with the attribute enhancement module and the word conversion units; iterative interactive learning of attributes and contexts is realized by adopting a hierarchical structure, and each computing layer is a bidirectional enhancement conversion component; attribute information is added in the process of extracting emotional characteristics through GCAE, wherein the GCAE is an English abbreviation of a gated convolution network with embedded attributes and is a common abbreviation for a person skilled in the art; the relation between the attribute and the context is further enhanced, and relative position information is introduced to better provide emotional characteristics; compared with the prior art, the feature extractor is replaced by GCAE from CNN; CNN is an english abbreviation of convolutional neural network, which is commonly abbreviated by those skilled in the art.
The bidirectional LSTM layer is used for capturing long dependency relationship and position information between texts, and the encoding result has two directions, one is an attribute enhancement module, and the other is a word conversion unit;
the attribute enhancement module receives the attribute representation and the average of the bidirectional LSTM layer coding result, and finally outputs an enhanced attribute representation which is input into the word conversion unit;
the attribute enhancement module utilizes the extracted context characteristics to enhance the attributes;
the word conversion unit receives the encoding result from the bi-directional LSTM layer and the enhanced attribute representation from the attribute enhancement module.
The convolutional feature extractor receives attribute information using a GCAE network to control the transfer of emotional features of the sentence, which further enhances the link between the attribute and the context, and furthermore, introduces relative position information to better extract the emotional features, and GCAE is an english abbreviation of gated convolutional network with embedded attribute, which is commonly abbreviated by those skilled in the art.
The process of reasoning and training of the invention is as follows:
step 1, a BERT layer, which uses pre-trained BERT to generate word representation of a sequence, supposing that a sentence contains m words and an attribute contains n words, vector representation of the sentence can be obtained through the BERT layer
Figure BDA0002676980070000051
Vector representation of sum attribute a ═ a1,a2,...,an}∈Rn×dWhere d represents the dimension of the BERT output layer.
And 2, bidirectional enhancement conversion layers, wherein each bidirectional enhancement conversion layer comprises three parts, namely a bidirectional LSTM layer, an attribute enhancement module and a group of character conversion units. The bi-directional LSTM layer first generates a contextualized word representation from the input. The attribute enhancement module then uses the word representations to enhance the attribute representations. Finally, the word conversion unit generates an attribute-specific word representation based on the contextualized word representation and the enhanced attribute representation.
And S21, learning the context dependence relationship of the text through the bidirectional LSTM layer. As shown in fig. 1, the bidirectional enhancement translation layer is repeated a plurality of times through the hierarchical structure. The input of the bi-directional LSTM in the lowest bi-directional enhancement conversion layer is a contextual representation of the BERT layer output. The input to the bi-directional LSTM in the next bi-directional enhancement conversion layer is from the output of the word conversion unit in the previous bi-directional enhancement conversion layer.
The word representation of the bidirectional LSTM output may be represented as
Figure BDA0002676980070000061
Forward LSTM outputs a set of hidden state vectors
Figure BDA0002676980070000062
Wherein d ishIndicating the number of hidden units. Similarly, backward LSTM also outputs a set of hidden state vectors
Figure BDA0002676980070000063
Finally, the word representation of the bidirectional LSTM output is obtained by connecting the two hidden state lists
Figure BDA0002676980070000064
Wherein
Figure BDA0002676980070000065
S22, attribute enhancing module, before the first attribute enhancing operation, obtaining the initial attribute representation. Specifically, the attribute vector a output by BERT is first set to { a ═ a }1,a2,...,an}∈Rn×dInput into another bi-directional LSTM, and then apply to the obtained hidden state vector
Figure BDA0002676980070000066
Applying an average pooling method to obtain an initial attribute representation
Figure BDA0002676980070000067
Taking the lowest bi-directional enhancement translation layer as an example, after obtaining the initial attribute representation, the contextualized word vector h is output based on the bi-directional LSTM(1)We obtain by averaging the pooling layersA vector
Figure BDA0002676980070000068
This is referred to as a context vector. The context vectors are then fused into the initial attribute representation using a basic feature fusion method (point-by-bit addition), which can be expressed as
Figure BDA0002676980070000069
This is an enhancement operation that acts on the attribute. And so on, the final attribute representation is
Figure BDA00026769800700000610
This formula expands as follows:
Figure BDA00026769800700000611
wherein
Figure BDA00026769800700000612
Representing the context vector in the ith dyad conversion layer. According to equation (1), the attributes are enhanced by different context vectors in multiple dyads. Attribute vector
Figure BDA00026769800700000613
There are two destinations, one destination being a word conversion unit in the same dyad and the other destination being a property enhancement module in the next dyad.
S23, a word conversion unit, which uses the same structure as the CPT module in the TNet model. TNet is an english abbreviation for attribute-oriented transition network, which is commonly abbreviated by those skilled in the art; CPT is an english abbreviation of context protection mechanism, which is a common shorthand for those skilled in the art; the unit will attribute the vector
Figure BDA0002676980070000071
And the word represents
Figure BDA0002676980070000072
As an input, wherein
Figure BDA0002676980070000073
Is represented by the ith word level output by the bidirectional LSTM layer, LSTM is an english abbreviation of long-short term memory network, which is commonly abbreviated by those skilled in the art,
Figure BDA0002676980070000074
is the enhanced attribute vector. Specifically, firstly, the
Figure BDA0002676980070000075
And
Figure BDA0002676980070000076
is input to a full connection layer to obtain an ith attribute-specific word representation
Figure BDA0002676980070000077
Figure BDA0002676980070000078
Where g (—) is a non-linear activation function and ": means a vector join operation.
Figure BDA0002676980070000079
And
Figure BDA00026769800700000710
respectively weight matrix and bias. There is an information protection mechanism to ensure that context dependent information captured from the bi-directional LSTM layer is not lost. This information protection mechanism enhances the delivery and use of features, which can be expressed as:
Figure BDA00026769800700000711
wherein
Figure BDA00026769800700000712
Is the output of the word conversion unit.
Step 3, a convolution feature extractor is introduced to a variable piTo measure the relative position information between the ith word and the current attribute word in the context, piIs calculated as follows:
Figure BDA00026769800700000713
where k is the index of the first word in the attribute, C is a pre-specified constant, and n is the length of the attribute phrase. When a sentence is filled, the index i may be larger than the actual length m of the sentence. Then, p is addediThe word output by the ith word conversion unit in the Lth bidirectional enhanced conversion layer is multiplied by the weight to represent that:
Figure BDA00026769800700000714
x at this timeiIs a word representation that incorporates location information.
Expressing the sentence integrated with the position information as X ═ X1,x2,...,xmAnd the final attribute vector
Figure BDA00026769800700000715
Inputting into a gated convolution network to generate a feature map c:
Figure BDA00026769800700000716
si＝tanh(WsXi:i+k-1+bs) (7)
ci＝si×ai (8)
where k is the convolution kernel size, Wa，Va，ba，WsAnd bsAre all learnable parameters, ciIs one item in the feature map c, siIs a calculated emotional feature, aiIs the calculated attribute feature; x denotes element-by-element multiplication. Then, the sentence representation z is obtained by s convolution kernels and applying the maximum pooling method:
z＝{max(c1),...,max(cs)} (9)
where max is a function of the maximum. Finally, z is input to a fully connected layer for final emotion prediction:
Figure BDA0002676980070000081
wherein softmax is a normalized exponential function, WfAnd bfAre learnable parameters.
Step 4, the mutually enhanced transformation network for fine-grained sentiment analysis referred to herein can be trained in an end-to-end manner within a supervised learning framework to optimize all parameters Θ. With L2The cross entropy of the regularization term is used as a loss function, defined as:
Figure BDA0002676980070000082
wherein y isiRepresenting the true probability that a given sentence is labeled as each emotion,
Figure BDA0002676980070000083
representing the estimated probability that a given sentence is labeled as each emotion, O representing the number of classes of emotion polarity, and λ being L2Parameters of the regularization term.

Claims (2)

1. The mutual enhancement conversion network for fine-grained emotion analysis is characterized in that:
the device comprises a BERT layer, a bidirectional enhanced conversion layer and a convolution feature extractor which are connected in sequence;
the BERT layer generates a word representation of the sequence using pre-trained BERT;
the bidirectional enhancement conversion layer comprises a bidirectional LSTM layer, an attribute enhancement module and a group of word conversion units, wherein the bidirectional LSTM layer is respectively connected with the attribute enhancement module and the word conversion units;
the bidirectional LSTM layer is used for capturing long dependency relationship and position information between texts, and the encoding result has two directions, one is an attribute enhancement module, and the other is a word conversion unit;
the attribute enhancement module receives the attribute representation and the average of the bidirectional LSTM layer coding result, and finally outputs an enhanced attribute representation which is input into the word conversion unit;
the attribute enhancement module utilizes the extracted context characteristics to enhance the attributes;
the word conversion unit receives the encoding result from the bidirectional LSTM layer and the enhanced attribute representation from the attribute enhancement module;
the convolutional feature extractor receives attribute information using a GCAE network to control the transfer of the emotional features of the sentence, which further enhances the link between the attributes and the context, and furthermore, introduces relative position information to better extract the emotional features.
2. The mutual enhancement conversion network for fine-grained emotion analysis is characterized in that the reasoning and training process comprises the following steps:
step 1, a BERT layer, which uses pre-trained BERT to generate word representation of a sequence, supposing that a sentence contains m words and an attribute contains n words, vector representation of the sentence can be obtained through the BERT layer
Figure FDA0002676980060000011
Vector representation of sum attribute a ═ a1,a2,...,an}∈Rn×dWherein d represents the dimension of the BERT output layer;
step 2, a bidirectional enhanced conversion layer, wherein a bidirectional LSTM layer generates contextualized word representation according to input; the attribute enhancement module then further enhances the attribute representation with these word representations; finally, the word conversion unit generates an attribute-specific word representation based on the contextualized word representation and the enhanced attribute representation;
s21, learning the context dependency relationship of the text through the bidirectional LSTM layer; the bidirectional enhancement conversion layer is repeated a plurality of times through the hierarchical structure, and the input of the bidirectional LSTM in the bottommost bidirectional enhancement conversion layer is the context representation of the output of the BERT layer;
the input of the bidirectional LSTM in the next bidirectional enhancement conversion layer is from the output of the word conversion unit in the previous bidirectional enhancement conversion layer;
the word representation of the bidirectional LSTM output may be represented as
Figure FDA0002676980060000012
Forward LSTM outputs a set of hidden state vectors
Figure FDA0002676980060000013
Wherein d ishIndicating the number of hidden units; backward LSTM also outputs a set of hidden state vectors
Figure FDA0002676980060000021
Connecting the two hidden state lists results in a word representation of the bi-directional LSTM output
Figure FDA0002676980060000022
Wherein
Figure FDA0002676980060000023
S22, an attribute enhancement module, before the first attribute enhancement operation, obtaining the initial attribute representation; first, the attribute vector a output by BERT is ═ a1,a2,...,an}∈Rn×dInput into another bi-directional LSTM, and then apply to the obtained hidden state vector
Figure FDA0002676980060000024
Applying an average pooling method to obtain an initial attribute representation
Figure FDA0002676980060000025
Contextualized word vector h based on bi-directional LSTM output after initial attribute representation is obtained(1)Obtaining a vector by averaging the pooling layers
Figure FDA0002676980060000026
It is referred to as a context vector; the context vectors are then fused into the initial attribute representation using a point-by-point bitwise additive feature fusion method, resulting in an enhanced operation on the attributes, represented as
Figure FDA0002676980060000027
The final attribute representation is obtained
Figure FDA0002676980060000028
The formula expands as follows:
Figure FDA0002676980060000029
wherein
Figure FDA00026769800600000210
i∈[1,L]Representing a context vector in an ith bi-directional enhancement conversion layer;
according to formula (1), the attributes are reinforced by different context vectors in a plurality of bidirectional enhancement conversion layers;
attribute vector
Figure FDA00026769800600000211
There are two destinations, one destination being a word conversion unit in the same dyad and the other destination being a genus in the next dyadA sexual enhancement module;
s23, word conversion unit, converting attribute vector
Figure FDA00026769800600000212
And the word represents
Figure FDA00026769800600000213
As an input, wherein
Figure FDA00026769800600000214
Is represented by the ith word level of the bi-directional LSTM layer output,
Figure FDA00026769800600000215
is the enhanced attribute vector;
firstly, the method is carried out
Figure FDA00026769800600000216
And
Figure FDA00026769800600000217
is input to a full connection layer to obtain an ith attribute-specific word representation
Figure FDA00026769800600000218
Figure FDA00026769800600000219
Wherein g () is a non-linear activation function, ": indicates a vector join operation;
Figure FDA00026769800600000220
and
Figure FDA00026769800600000221
respectively, weight matrix and bias; using information protection mechanisms to ensure context-dependent information captured from a bi-directional LSTM layerInformation is not lost, and the information protection mechanism enhances the delivery and use of features, expressed as:
Figure FDA00026769800600000222
wherein
Figure FDA0002676980060000031
Is the output of the word conversion unit;
step 3, a convolution feature extractor is introduced to a variable piTo measure the relative position information between the ith word and the current attribute word in the context, piIs calculated as follows:
Figure FDA0002676980060000032
wherein k is the index of the first word in the attribute, C is a pre-specified constant, and n is the length of the attribute phrase; when a sentence is filled, the index i may be larger than the actual length m of the sentence;
p is to beiThe word output by the ith word conversion unit in the Lth bidirectional enhanced conversion layer is multiplied by the weight to represent that:
Figure FDA0002676980060000033
x at this timeiIs a word representation that incorporates location information.
Then, the sentence with the position information is expressed with X ═ X1,x2,...,xmAnd the final attribute vector
Figure FDA0002676980060000034
Inputting into a gated convolution network to generate a feature map c:
Figure FDA0002676980060000035
si＝tanh(WsXi:i+k-1+bs) (7)
ci＝si×ai (8)
where k is the convolution kernel size, Wa，Va，ba，WsAnd bsAre all learned parameters, x represents element-by-element multiplication; c. CiIs one item in the feature map c, siIs a calculated emotional feature, aiIs the calculated attribute feature;
the sentence representation z is obtained by s convolution kernels and applying the maximum pooling method:
z＝{max(c1),...,max(cs)} (9)
where max is a function of the maximum. Finally, z is input to a fully connected layer for final emotion prediction:
Figure FDA0002676980060000036
wherein softmax is a normalized exponential function, WfAnd bfAre learnable parameters;
step 4, the mutually enhanced transformation network for fine-grained sentiment analysis referred to herein can be trained in an end-to-end manner within a supervised learning framework to optimize all parameters Θ, with L2The cross entropy of the regularization term is used as a loss function, defined as:
Figure FDA0002676980060000041
wherein y isiRepresenting the true probability that a given sentence is labeled as each emotion,
Figure FDA0002676980060000042
representing the estimated probability that a given sentence is labeled as each emotion, O representing the number of classes of emotion polarity, and λ being L2Parameters of the regularization term.
CN202010951154.4A 2020-09-11 2020-09-11 Mutual enhancement conversion method for fine-grained emotion analysis Active CN112100376B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010951154.4A CN112100376B (en) 2020-09-11 2020-09-11 Mutual enhancement conversion method for fine-grained emotion analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010951154.4A CN112100376B (en) 2020-09-11 2020-09-11 Mutual enhancement conversion method for fine-grained emotion analysis

Publications (2)

Publication Number Publication Date
CN112100376A true CN112100376A (en) 2020-12-18
CN112100376B CN112100376B (en) 2022-02-08

Family

ID=73752087

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010951154.4A Active CN112100376B (en) 2020-09-11 2020-09-11 Mutual enhancement conversion method for fine-grained emotion analysis

Country Status (1)

Country Link
CN (1) CN112100376B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113705197A (en) * 2021-08-30 2021-11-26 北京工业大学 Fine-grained emotion analysis method based on position enhancement
CN118013962A (en) * 2024-04-09 2024-05-10 华东交通大学 Chinese chapter connective word recognition method based on two-way sequence generation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170046797A1 (en) * 2003-04-07 2017-02-16 10Tales, Inc. Method, system and software for associating attributes within digital media presentations
CN110489554A (en) * 2019-08-15 2019-11-22 昆明理工大学 Property level sensibility classification method based on the mutual attention network model of location aware
CN111414476A (en) * 2020-03-06 2020-07-14 哈尔滨工业大学 Attribute-level emotion analysis method based on multi-task learning

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170046797A1 (en) * 2003-04-07 2017-02-16 10Tales, Inc. Method, system and software for associating attributes within digital media presentations
CN110489554A (en) * 2019-08-15 2019-11-22 昆明理工大学 Property level sensibility classification method based on the mutual attention network model of location aware
CN111414476A (en) * 2020-03-06 2020-07-14 哈尔滨工业大学 Attribute-level emotion analysis method based on multi-task learning

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113705197A (en) * 2021-08-30 2021-11-26 北京工业大学 Fine-grained emotion analysis method based on position enhancement
CN113705197B (en) * 2021-08-30 2024-04-02 北京工业大学 Fine granularity emotion analysis method based on position enhancement
CN118013962A (en) * 2024-04-09 2024-05-10 华东交通大学 Chinese chapter connective word recognition method based on two-way sequence generation

Also Published As

Publication number Publication date
CN112100376B (en) 2022-02-08

Similar Documents

Publication Publication Date Title
CN110119467B (en) Project recommendation method, device, equipment and storage medium based on session
CN110598779B (en) Abstract description generation method and device, computer equipment and storage medium
CN109934261B (en) Knowledge-driven parameter propagation model and few-sample learning method thereof
CN109582956B (en) Text representation method and device applied to sentence embedding
CN112633010B (en) Aspect-level emotion analysis method and system based on multi-head attention and graph convolution network
CN110046248B (en) Model training method for text analysis, text classification method and device
CN109947912A (en) A kind of model method based on paragraph internal reasoning and combined problem answer matches
CN109919221B (en) Image description method based on bidirectional double-attention machine
CN111897957B (en) Capsule neural network integrating multi-scale feature attention and text classification method
CN112527966B (en) Network text emotion analysis method based on Bi-GRU neural network and self-attention mechanism
CN112100376B (en) Mutual enhancement conversion method for fine-grained emotion analysis
CN110851491A (en) Network link prediction method based on multiple semantic influences of multiple neighbor nodes
CN113673535B (en) Image description generation method of multi-modal feature fusion network
CN113626589A (en) Multi-label text classification method based on mixed attention mechanism
CN112131886A (en) Method for analyzing aspect level emotion of text
CN115408517A (en) Knowledge injection-based multi-modal irony recognition method of double-attention network
CN114676332A (en) Network API recommendation method facing developers
CN114510576A (en) Entity relationship extraction method based on BERT and BiGRU fusion attention mechanism
CN110321565B (en) Real-time text emotion analysis method, device and equipment based on deep learning
CN115422388B (en) Visual dialogue method and system
CN116150334A (en) Chinese co-emotion sentence training method and system based on UniLM model and Copy mechanism
CN113705197B (en) Fine granularity emotion analysis method based on position enhancement
US11941508B2 (en) Dialog system with adaptive recurrent hopping and dual context encoding
CN115169348A (en) Event extraction method based on hybrid neural network
CN114610862A (en) Conversation recommendation method for enhancing context sequence of graph

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