CN116151241A - Entity identification method and device - Google Patents

Entity identification method and device Download PDF

Info

Publication number
CN116151241A
CN116151241A CN202310417766.9A CN202310417766A CN116151241A CN 116151241 A CN116151241 A CN 116151241A CN 202310417766 A CN202310417766 A CN 202310417766A CN 116151241 A CN116151241 A CN 116151241A
Authority
CN
China
Prior art keywords
vector
span
character
unit
entity
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
CN202310417766.9A
Other languages
Chinese (zh)
Other versions
CN116151241B (en
Inventor
邓正秋
何亮
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 Malanshan Video Advanced Technology Research Institute Co ltd
Original Assignee
Hunan Malanshan Video Advanced Technology Research Institute Co ltd
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 Malanshan Video Advanced Technology Research Institute Co ltd filed Critical Hunan Malanshan Video Advanced Technology Research Institute Co ltd
Priority to CN202310417766.9A priority Critical patent/CN116151241B/en
Publication of CN116151241A publication Critical patent/CN116151241A/en
Application granted granted Critical
Publication of CN116151241B publication Critical patent/CN116151241B/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
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • 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
    • G06F16/353—Clustering; Classification into predefined classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention provides an entity recognition method and a device, wherein the entity recognition method performs character embedding on an input text and generates unique vector representation for each character; determining potential entity areas and corresponding context areas in the text by enumerating span units in the input sequence; jointly modeling potential entity regions and context regions using a graph convolution network and a multi-headed attention layer; the result of the joint modeling determines the entity class of the potential entity region via a classifier. The entity identification method can efficiently and accurately identify the contained entity information from the unstructured sequence text. When the invention recognizes whether the character sequence in the text is an entity, the semantic information of the sequence is considered, the context information formed by the residual characters is fully modeled, and the entity recognition precision is effectively improved.

Description

Entity identification method and device
Technical Field
The present invention relates to the field of natural language processing technologies, and in particular, to a method and apparatus for entity identification.
Background
Natural text is typically propagated and recorded in unstructured sequences, where there is a large amount of entity information, such as names of people, places, organizations, and institutions, that express specific concepts, as shown in fig. 1. The rapid and accurate identification of entity information in unstructured sequence text is one of the key technologies for constructing question-answering systems and recommendation systems.
The entity identification in the unstructured sequence text is most complex, characteristics such as syntax, semantics and context are required to be considered at the same time, and the traditional rule-based information extraction method is difficult to meet the entity identification requirement of the unstructured sequence text. Human beings can read and acquire entity information in unstructured sequence texts, but entity identification of massive data is not enough for work.
Disclosure of Invention
Aiming at the technical problems in the related art, the invention provides an entity identification method, which comprises the following steps:
s1, performing character embedding on an input text, and generating a unique vector representation for each character to obtain a vector sequence of the input text
Figure SMS_1
；
S2, inputting a text vector sequence by enumeration
Figure SMS_2
The span unit in the text obtaining unit obtains the span set of the input text
Figure SMS_3
；
S3, collecting the spans
Figure SMS_4
Input semantic feature vector of bidirectional convolution generation span region +.>
Figure SMS_5
；
S4, the semantic feature vector is processed
Figure SMS_6
Inputting the two-way long-short-period memory network to obtain the context information +.>
Figure SMS_7
；
S5, the context information is processed
Figure SMS_8
Obtaining the joint modeling result of the semantic features and the contextual features of the span units by nonlinear transformation>
Figure SMS_9
；
S6, modeling the indicated combination results
Figure SMS_10
The input classifier obtains the entity class.
Specifically, the step S1 includes: s11, randomly initializing a feature matrix
Figure SMS_11
An embedding matrix as a character, wherein->
Figure SMS_12
Is the length of the character table, < >>
Figure SMS_13
Representing the embedding dimension of each character;
s12, for each character in the input text, the character is extracted from the feature matrix according to the id of the character in the character table
Figure SMS_14
The middle cables lead to respective vector representations.
Specifically, the step S3 includes:
s31, reconstructing a span sequence of the chain structure into a graph structure;
s32, constructing each node characteristic in the two-way graph convolution layer aggregation graph;
s33, accumulating and averaging all nodes in the feature map, and calculating semantic feature representation of the span unit
Figure SMS_15
。
Specifically, the step S4 includes:
s41, using feature vectors
Figure SMS_16
Replacing vector sequences of span units in the original input vector sequence, i.e.
Figure SMS_17
Become->
Figure SMS_18
;
S42, constructing two-way long-short-term memory network modeling
Figure SMS_19
Is a sequence feature of (2);
s43, aggregating sequences based on self-attention mechanisms
Figure SMS_20
Midspan characteristics->
Figure SMS_21
And contextual characteristics->
Figure SMS_22
The dependency relationship exists, and the calculation formula is as follows:
Figure SMS_23
，
wherein ,
Figure SMS_25
is of dimension +.>
Figure SMS_27
Is a normalized exponential function;
Figure SMS_29
is a feature vector of a span unit with dimension +.>
Figure SMS_24
；/>
Figure SMS_28
Is a feature matrix formed by state feature vectors of a two-way long-short-term memory network, and the dimension is +.>
Figure SMS_30
；/>
Figure SMS_31
As a joint modeling output of span semantic features and context features, the vector dimension is +.>
Figure SMS_26
。
Specifically, the step S5 includes:
s51, repeatlSub-step S4, depth modeling semantic and contextual features, the output feature vectors of which are expressed as
Figure SMS_32
；
S52, feature vectors
Figure SMS_33
The most input is output via the following way>
Figure SMS_34
Combined modeling result of semantic features and contextual features +.>
Figure SMS_35
。
In a second aspect, another embodiment of the present invention discloses an entity recognition apparatus, including:
an input text vector generation unit for character embedding the input text, generating a unique vector representation for each character to obtain a vector sequence of the input text
Figure SMS_36
；
A span set generating unit for inputting text for enumerating the input text vector sequence
Figure SMS_37
The span unit in (1) obtaining the span set of the input text +.>
Figure SMS_38
；
A semantic feature vector generation unit for aggregating the spans
Figure SMS_39
Input semantic feature vector of bidirectional convolution generation span region +.>
Figure SMS_40
；
A context information generating unit for generating the semantic feature vector
Figure SMS_41
Inputting the two-way long-short-period memory network to obtain the context information +.>
Figure SMS_42
；/>
A joint modeling result generation unit of semantic features and context features for generating the context information
Figure SMS_43
Obtaining the joint modeling result of the semantic features and the contextual features of the span units by nonlinear transformation>
Figure SMS_44
；
An entity acquisition unit for modeling the results of the joint modeling
Figure SMS_45
The input classifier obtains the entity class.
Specifically, the input text vector generation unit includes: an embedded matrix initializing unit for randomly initializing a feature matrix
Figure SMS_46
As charactersIs embedded in matrix->
Figure SMS_47
Is the length of the character table, < >>
Figure SMS_48
Representing the embedding dimension of each character;
a vector generation unit for generating a character matrix for each character in the input text based on its id in the character table
Figure SMS_49
The middle cables lead to respective vector representations.
Specifically, the semantic feature vector generating unit includes:
a graph structure reconstructing unit for reconstructing the span sequence of the chain structure into a graph structure;
the bidirectional graph convolution construction unit is used for constructing each node characteristic in the bidirectional graph convolution layer aggregation graph;
a semantic feature representation calculation unit for calculating semantic feature representation of the span unit by cumulatively averaging each node in the feature map
Figure SMS_50
。
Specifically, the context information generating unit includes:
a first vector replacement unit for using feature vectors
Figure SMS_51
Replacement of vector sequences of span units in the original input vector sequence, i.e. +.>
Figure SMS_52
Become->
Figure SMS_53
;
Two-way long-short-term memory network construction unit for constructing two-way long-short-term memory network modeling
Figure SMS_54
Is a sequence feature of (2);
a first joint modeling unit for aggregating sequences based on a self-attention mechanism
Figure SMS_55
Midspan characteristics->
Figure SMS_56
And contextual characteristics->
Figure SMS_57
The dependency relationship exists, and the calculation formula is as follows:
Figure SMS_58
，
wherein ,
Figure SMS_60
is of dimension +.>
Figure SMS_62
Is a normalized exponential function;
Figure SMS_64
is a feature vector of a span unit with dimension +.>
Figure SMS_61
；/>
Figure SMS_63
Is a feature matrix formed by state feature vectors of a two-way long-short-term memory network, and the dimension is +.>
Figure SMS_65
；/>
Figure SMS_66
As a joint modeling output of span semantic features and context features, the vector dimension is +.>
Figure SMS_59
。
Specifically, the unit for generating the joint modeling result of the semantic features and the contextual features comprises:
a first execution unit for repeatedly executinglA secondary context information generating unit for modeling semantic features and context feature depth, the output feature vector of which is expressed as
Figure SMS_67
；/>
A second modeling unit for modeling the feature vector
Figure SMS_68
The most input is output via the following way>
Figure SMS_69
Combined modeling result of semantic features and contextual features +.>
Figure SMS_70
。
In a third aspect, another embodiment of the present invention discloses a nonvolatile memory having instructions stored thereon, which when executed by a processor, are configured to implement an entity identification method as described above.
The entity recognition method of the invention performs character embedding on an input text, and generates unique vector representation for each character; determining potential entity areas and corresponding context areas in the text by enumerating span units in the input sequence; jointly modeling potential entity regions and context regions using a graph convolution network and a multi-headed attention layer; the result of the joint modeling determines the entity class of the potential entity region via a classifier. The entity identification method can efficiently and accurately identify the contained entity information from the unstructured sequence text. When the invention recognizes whether the character sequence in the text is an entity, the semantic information of the sequence is considered, the context information formed by the residual characters is fully modeled, and the entity recognition precision is effectively improved. According to the method and the device, through an enumeration mode, all character subsequences in the text are considered to be potential entities, and overlapped entity information in the text can be well identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of unstructured text provided by an embodiment of the present invention;
FIG. 2 is a flowchart of a method for entity identification according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a text embedding process provided by an embodiment of the present invention;
FIG. 4 is a span enumeration schematic of input text of length 4 provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram of joint modeling of span semantic features and context features provided by an embodiment of the present invention;
FIG. 6 is a schematic diagram of a two-way long and short term memory network according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an entity identification device according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a seed entity identification device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the invention, fall within the scope of protection of the invention.
Example 1
Referring to fig. 2, the embodiment discloses an entity identification method, which includes the following steps:
s1, character embedding is carried out on an input text, and a unique direction is generated for each characterVector sequence for quantity representation to obtain input text
Figure SMS_71
；
The computer cannot directly perform calculations on text characters, and this embodiment requires that characters in the input text be mapped to vector space first.
The specific step S1 includes: s11, randomly initializing a feature matrix
Figure SMS_72
An embedding matrix as a character, wherein->
Figure SMS_73
Is the length of the character table, < >>
Figure SMS_74
Representing the embedding dimension of each character.
Specifically, the character table of the embodiment may be obtained by counting the number of different characters in the corpus. In another embodiment the character table may also be pre-set.
S12, for each character in the input text, the character is extracted from the feature matrix according to the id of the character in the character table
Figure SMS_75
The middle cables lead to respective vector representations.
Referring to fig. 3, fig. 3 is a schematic diagram of a process of text character embedding. In the embodiment, a corpus is firstly obtained, and my love my ancestor is expected to exist in the corpus, …, and my love my hometown; and (5) corpus waiting. The characters in the expected library are then counted and a character table is obtained, which includes i am, love, ancestor, state … home, county. And each character in the character table has a unique id, such as: i am (1), love (2), 3, ancestor (4), state (5), … families (V-1), county (V).
Assume that the character sequence of the input text is
Figure SMS_76
，nRepresenting the character length of the input text. The input text can be represented as a vector sequence +.>
Figure SMS_77
, wherein />
Figure SMS_78
Is of dimension ofdIs a character vector of (a).
Referring to FIG. 3, for the character "love" in "I love my our country" in the input text, the vector sequence it generates
Figure SMS_79
。
S2, inputting a text vector sequence by enumeration
Figure SMS_80
The span unit in (1) obtaining the span set of the input text +.>
Figure SMS_81
；
Wherein the span set represents a potential entity region of the input text and a corresponding context region;
the present embodiment defines arbitrary length contiguous subsequences in the input text as a Span unit (Span), each Span unit being considered a potential entity area to be identified. Specifically, assuming that the length of the input text sequence is N, one can enumerate
Figure SMS_82
And the subsequent neural network model models all enumerated span units and judges whether the span units are entities or belong to which type of entity. Fig. 4 is a span enumeration schematic of an input text of length 4, wherein a total of 10 span units may be enumerated.
Assume that the vector sequence of the input text is
Figure SMS_83
Then the span set can be obtained after enumeration
Figure SMS_84
, wherein />
Figure SMS_85
。
S3, collecting the spans
Figure SMS_86
Input semantic feature vector of bidirectional convolution generation span region +.>
Figure SMS_87
；
The neural network model designed in this embodiment models span sets by jointly modeling span semantic features and context featuresSEach span unit of (a)
Figure SMS_88
Generating unique characteristic representation->
Figure SMS_89
. The specific operation process is shown in fig. 5, and mainly comprises the following three steps:
s3, collecting the spans
Figure SMS_90
Input semantic feature vector of bidirectional convolution generation span region +.>
Figure SMS_91
；
S4, the semantic feature vector is processed
Figure SMS_92
Inputting the two-way long-short-period memory network to obtain the context information +.>
Figure SMS_93
；
S5, the context information is processed
Figure SMS_94
Acquiring semantic features of span units by nonlinear transformationCombined modeling of contextual features>
Figure SMS_95
；
The present embodiment takes a span unit of i=k=3 as an example, and details the modeling process of the present embodiment:
wherein step S3 comprises:
s31, reconstructing the span sequence of the chain structure into a graph structure.
In the reconstruction process, the character vector in the span unit is used as a node characteristic, and the node with the front time sequence can point to the subsequent node. As shown in fig. 4, the span unit
Figure SMS_96
There are three nodes, wherein->
Figure SMS_97
Can point to +.>
Figure SMS_98
and />
Figure SMS_99
，/>
Figure SMS_100
Can only point to +.>
Figure SMS_101
;
S32, constructing each node characteristic in a two-way graph convolution (BiGCN) layer aggregation graph.
In particular using a non-linear function ReLU and three sets of characteristic parameters
Figure SMS_102
、/>
Figure SMS_103
and />
Figure SMS_104
And carrying out nonlinear transformation on the characteristics of the neighborhood nodes to update the characteristic vector of each node, wherein the mathematical expression is as follows:
Figure SMS_105
，
Figure SMS_106
，
Figure SMS_107
，
therein, wherein
Figure SMS_109
Is of dimension +.>
Figure SMS_112
Parameter matrix of>
Figure SMS_114
Is of dimension +.>
Figure SMS_110
Parameter matrix of>
Figure SMS_111
Is of dimension +.>
Figure SMS_113
Is used for the parameter vector of (a). />
Figure SMS_115
，/>
Figure SMS_108
Is a vector concatenation operation.
Operation example: [1,2,3]
Figure SMS_116
[4,5,6]=[1,2,3,4,5,6]The method comprises the steps of carrying out a first treatment on the surface of the Let->
Figure SMS_117
Then
Figure SMS_118
。
S33, accumulating and averaging all nodes in the feature map, and calculating semantic feature representation of the span unit
Figure SMS_119
：
Figure SMS_120
，
wherein
Figure SMS_121
Representing accumulation operations, e.g.)>
Figure SMS_122
。
The step S4 specifically includes:
s41, using feature vectors
Figure SMS_123
Replacing vector sequences of span units in the original input vector sequence, i.e.
Figure SMS_124
Become->
Figure SMS_125
;
S42, constructing a two-way long-short-term memory network (BiLSTM) model
Figure SMS_126
Is a sequence feature of (2);
the structure of the network is shown in FIG. 6, in which
Figure SMS_127
For the input feature vector at the current time, +.>
Figure SMS_128
The two feature vectors are respectively output at the previous moment, and t represents the position of a character in the input text.
The specific calculation formula is as follows:
Figure SMS_129
，
Figure SMS_130
，
Figure SMS_131
，
Figure SMS_132
，
Figure SMS_133
，
Figure SMS_134
，
wherein
Figure SMS_137
Representation->
Figure SMS_140
Feature vector at middle t position, +.>
Figure SMS_143
From the previous moment ∈>
Figure SMS_138
And (5) calculating.
Figure SMS_141
Is of dimension +.>
Figure SMS_144
Parameter matrix of>
Figure SMS_146
Is of dimension +.>
Figure SMS_136
Is used for the parameter vector of (a). />
Figure SMS_139
，
Figure SMS_142
Is a vector concatenation operation. />
Figure SMS_145
Multiplication of corresponding elements in the representative vector, i.e.
Figure SMS_135
。
The present embodiment uses a two-way long short-term memory network (BiLSTM) to output a state vector at each time t
Figure SMS_147
Constitution of
Figure SMS_148
Is expressed as +.>
Figure SMS_149
。/>
S43, aggregating sequences based on self-attention mechanisms
Figure SMS_150
Midspan characteristics->
Figure SMS_151
Is { about the contextual characteristics>
Figure SMS_152
The dependency relationship exists between the two, and the calculation formula is as follows:
Figure SMS_153
，
wherein ,
Figure SMS_154
is of dimension +.>
Figure SMS_157
Parameter matrix of (2)Softmax is a normalized exponential function. />
Figure SMS_158
Is a feature vector of a span unit with dimension +.>
Figure SMS_156
。/>
Figure SMS_159
Is a feature matrix formed by state feature vectors of a two-way long-short-term memory network, and the dimension is +.>
Figure SMS_160
。/>
Figure SMS_161
As a joint modeling output of span semantic features and context features, the vector dimension is +.>
Figure SMS_155
。
The step S5 specifically includes:
s51, repeatlSub-step S4, depth modeling semantic and contextual features, the output feature vectors of which are expressed as
Figure SMS_162
；
S52, feature vectors
Figure SMS_163
The most input is output via the following way>
Figure SMS_164
Combined modeling result of semantic features and contextual features +.>
Figure SMS_165
：
Figure SMS_166
wherein
Figure SMS_167
Is of dimension +.>
Figure SMS_168
Parameter matrix of>
Figure SMS_169
Is of dimension +.>
Figure SMS_170
The output of max (x, y) is the larger of x and y. />
Figure SMS_171
Maximum spanning Unit->
Figure SMS_172
And carrying out entity recognition by a subsequent classifier on the joint modeling result in the text D to output entity categories.
S6, modeling the indicated combination results
Figure SMS_173
The input classifier obtains the entity class.
Constructing a linear classifier and calculating the span unit from the normalized exponential function softmax
Figure SMS_174
Probability distribution of the belonging entity class:
Figure SMS_175
，
wherein
Figure SMS_177
Is of dimension +.>
Figure SMS_179
Parameter matrix of>
Figure SMS_181
Is of dimension +.>
Figure SMS_176
Parameter vector of>
Figure SMS_180
Equal to the number +1 of entity categories in the corpus (non-entities are set as a class of entities). Output of classifier->
Figure SMS_182
Is of dimension of
Figure SMS_183
Wherein each dimension represents a stride element +.>
Figure SMS_178
The represented character sequence belongs to the probability value of a certain class of entity.
The embodiment takes
Figure SMS_186
Entity class corresponding to the dimension with the largest probability value in the text is used as the input textDMid span unit->
Figure SMS_187
Entity recognition results of the represented character sequence. For example, there are 4 entities in the corpus altogether, if +.>
Figure SMS_189
Span unit->
Figure SMS_185
Represented character sequence->
Figure SMS_188
Belonging to a second class of entities; if->
Figure SMS_190
Span unit->
Figure SMS_191
Represented character sequence->
Figure SMS_184
Belongs to non-entity.
The entity recognition method of the embodiment performs character embedding on an input text, and generates unique vector representation for each character; determining potential entity areas and corresponding context areas in the text by enumerating span units in the input sequence; jointly modeling potential entity regions and context regions using a graph convolution network and a multi-headed attention layer; the result of the joint modeling determines the entity class of the potential entity region via a classifier. The entity identification method can efficiently and accurately identify the contained entity information from the unstructured sequence text. When the character sequence in the text is identified as the entity, the embodiment considers the semantic information of the sequence, fully models the context information formed by the residual characters, and effectively improves the accuracy of entity identification. In this embodiment, by means of enumeration, all character sub-sequences in the text are considered to be potential entities, so that overlapping entity information in the text can be well identified. For example, "Wuhan Yangtze bridge" is an entity, and "Wuhan" included therein is also an entity.
Example two
Referring to fig. 7, the present embodiment discloses an entity recognition apparatus, which includes the following units:
an input text vector generation unit for character embedding the input text, generating a unique vector representation for each character to obtain a vector sequence of the input text
Figure SMS_192
；
The computer cannot directly perform calculations on text characters, and this embodiment requires that characters in the input text be mapped to vector space first.
The specific input text vector generation unit includes: an embedded matrix initializing unit for randomly initializing a feature matrix
Figure SMS_193
Embedding matrix as characterWherein->
Figure SMS_194
Is the length of the character table, < >>
Figure SMS_195
Representing the embedding dimension of each character.
Specifically, the character table of the embodiment may be obtained by counting the number of different characters in the corpus. In another embodiment the character table may also be pre-set.
A vector generation unit for generating a character matrix for each character in the input text based on its id in the character table
Figure SMS_196
The middle cables lead to respective vector representations.
Referring to fig. 3, fig. 3 is a schematic diagram of a process of text character embedding. In the embodiment, a corpus is firstly obtained, and my love my ancestor is expected to exist in the corpus, …, and my love my hometown; and (5) corpus waiting. The characters in the expected library are then counted and a character table is obtained, which includes i am, love, ancestor, state … home, county. And each character in the character table has a unique id, such as: i am (1), love (2), 3, ancestor (4), state (5), … families (V-1), county (V).
Assume that the character sequence of the input text is
Figure SMS_197
，nRepresenting the character length of the input text. The input text can be represented as a vector sequence +.>
Figure SMS_198
, wherein />
Figure SMS_199
Is of dimension ofdIs a character vector of (a).
Referring to FIG. 3, for the character "love" in "I love my our country" in the input text, the vector sequence it generates
Figure SMS_200
。
A span set generating unit for inputting text for enumerating the input text vector sequence
Figure SMS_201
The span unit in (1) obtaining the span set of the input text +.>
Figure SMS_202
；
Wherein the span set represents a potential entity region of the input text and a corresponding context region;
the present embodiment defines arbitrary length contiguous subsequences in the input text as a Span unit (Span), each Span unit being considered a potential entity area to be identified. Specifically, assuming that the length of the input text sequence is N, one can enumerate
Figure SMS_203
And the subsequent neural network model models all enumerated span units and judges whether the span units are entities or belong to which type of entity. Fig. 4 is a span enumeration schematic of an input text of length 4, wherein a total of 10 span units may be enumerated.
Assume that the vector sequence of the input text is
Figure SMS_204
Then the span set can be obtained after enumeration
Figure SMS_205
, wherein />
Figure SMS_206
。
A semantic feature vector generation unit for aggregating the spans
Figure SMS_207
Language input with bidirectional graph convolution to generate span regionSense eigenvector->
Figure SMS_208
；
A context information generating unit for generating the semantic feature vector
Figure SMS_209
Inputting the two-way long-short-period memory network to obtain the context information +.>
Figure SMS_210
；
A joint modeling result generation unit of semantic features and context features for generating the context information
Figure SMS_211
Obtaining the joint modeling result of the semantic features and the contextual features of the span units by nonlinear transformation>
Figure SMS_212
；
The present embodiment takes a span unit of i=k=3 as an example, and details the modeling process of the present embodiment:
wherein the semantic feature vector generating unit includes:
and the diagram structure reconstruction unit is used for reconstructing the span sequence of the chain structure into a diagram structure.
In the reconstruction process, the character vector in the span unit is used as a node characteristic, and the node with the front time sequence can point to the subsequent node. As shown in fig. 4, the span unit
Figure SMS_213
There are three nodes, wherein->
Figure SMS_214
Can point to +.>
Figure SMS_215
and />
Figure SMS_216
，/>
Figure SMS_217
Can only point to +.>
Figure SMS_218
;
And the bidirectional graph convolution construction unit is used for constructing each node characteristic in the bidirectional graph convolution (BiGCN) layer aggregation graph.
In particular using a non-linear function ReLU and three sets of characteristic parameters
Figure SMS_219
、/>
Figure SMS_220
and />
Figure SMS_221
And carrying out nonlinear transformation on the characteristics of the neighborhood nodes to update the characteristic vector of each node, wherein the mathematical expression is as follows:
Figure SMS_222
，
Figure SMS_223
，
Figure SMS_224
，
therein, wherein
Figure SMS_226
Is of dimension +.>
Figure SMS_228
Parameter matrix of>
Figure SMS_230
Is of dimension +.>
Figure SMS_227
Parameter matrix of>
Figure SMS_229
Is of dimension +.>
Figure SMS_231
Is used for the parameter vector of (a). />
Figure SMS_232
，/>
Figure SMS_225
Is a vector concatenation operation.
Operation example: [1,2,3]
Figure SMS_233
[4,5,6]=[1,2,3,4,5,6]The method comprises the steps of carrying out a first treatment on the surface of the Let->
Figure SMS_234
Then
Figure SMS_235
。
A semantic feature representation calculation unit for calculating semantic feature representation of the span unit by cumulatively averaging each node in the feature map
Figure SMS_236
：
Figure SMS_237
wherein
Figure SMS_238
Representing accumulation operations, e.g.)>
Figure SMS_239
。
The context information generation unit specifically includes:
a first vector replacement unit for using feature vectors
Figure SMS_240
Replacement of vector sequences of span units in the original input vector sequence, i.e. +.>
Figure SMS_241
Become->
Figure SMS_242
;
Two-way long-short-term memory network construction unit for constructing two-way long-short-term memory network (BiLSTM) modeling
Figure SMS_243
Is a sequence feature of (2);
the structure of the network is shown in FIG. 6, in which
Figure SMS_244
For the input feature vector at the current time, +.>
Figure SMS_245
The two feature vectors are respectively output at the previous moment, and t represents the position of a character in the input text.
The specific calculation formula is as follows:
Figure SMS_246
，
Figure SMS_247
，
Figure SMS_248
，
Figure SMS_249
，
Figure SMS_250
，
Figure SMS_251
，
wherein
Figure SMS_253
Representation->
Figure SMS_257
Feature vector at middle t position, +.>
Figure SMS_260
From the previous moment ∈>
Figure SMS_254
And (5) calculating.
Figure SMS_258
Is of dimension +.>
Figure SMS_261
Parameter matrix of>
Figure SMS_263
Is of dimension +.>
Figure SMS_252
Is used for the parameter vector of (a). />
Figure SMS_256
，
Figure SMS_259
Is a vector concatenation operation. />
Figure SMS_262
Multiplication of corresponding elements in the representative vector, i.e. +.>
Figure SMS_255
。
The present embodiment uses a two-way long short-term memory network (BiLSTM) to output a state vector at each time t
Figure SMS_264
Constitution of
Figure SMS_265
Is expressed as +.>
Figure SMS_266
。
A first joint modeling unit for aggregating sequences based on a self-attention mechanism
Figure SMS_267
Midspan characteristics->
Figure SMS_268
Is { about the contextual characteristics>
Figure SMS_269
The dependency relationship exists between the two, and the calculation formula is as follows:
Figure SMS_270
wherein ,
Figure SMS_272
is of dimension +.>
Figure SMS_275
Is a normalized exponential function. />
Figure SMS_277
Is a feature vector of a span unit with dimension +.>
Figure SMS_273
。/>
Figure SMS_274
Is a feature matrix formed by state feature vectors of a two-way long-short-term memory network, and the dimension is +.>
Figure SMS_276
。/>
Figure SMS_278
As a joint modeling output of span semantic features and context features, the vector dimension is +.>
Figure SMS_271
。
The generation unit of the joint modeling result of the semantic features and the contextual features specifically comprises:
a first execution unit for repeatedly executinglA secondary context information generating unit for modeling semantic features and context feature depth, the output feature vector of which is expressed as
Figure SMS_279
；
A second modeling unit for modeling the feature vector
Figure SMS_280
The most input is output via the following way>
Figure SMS_281
Combined modeling result of semantic features and contextual features +.>
Figure SMS_282
：
Figure SMS_283
，
wherein
Figure SMS_284
Is of dimension +.>
Figure SMS_285
Parameter matrix of>
Figure SMS_286
Is of dimension +.>
Figure SMS_287
The output of max (x, y) is the larger of x and y. />
Figure SMS_288
Maximum spanning Unit->
Figure SMS_289
In textAnd D, carrying out entity recognition by a subsequent classifier on the joint modeling result in the step D to output entity categories.
An entity acquisition unit for modeling the results of the joint modeling
Figure SMS_290
The input classifier obtains the entity class.
Constructing a linear classifier and calculating the span unit from the normalized exponential function softmax
Figure SMS_291
Probability distribution of the belonging entity class:
Figure SMS_292
，
wherein
Figure SMS_294
Is of dimension +.>
Figure SMS_298
Parameter matrix of>
Figure SMS_300
Is of dimension +.>
Figure SMS_295
Parameter vector of>
Figure SMS_296
Equal to the number +1 of entity categories in the corpus (non-entities are set as a class of entities). Output of classifier->
Figure SMS_297
Is of dimension of
Figure SMS_299
Wherein each dimension represents a stride element +.>
Figure SMS_293
The represented character sequence belongs to the probability value of a certain class of entity.
The embodiment takes
Figure SMS_301
Entity class corresponding to the dimension with the largest probability value in the text is used as the input textDMid span unit->
Figure SMS_305
Entity recognition results of the represented character sequence. For example, there are 4 entities in total in the corpus, if
Figure SMS_307
Span unit->
Figure SMS_302
Represented character sequence->
Figure SMS_304
Belonging to a second class of entities; if it is
Figure SMS_306
Span unit->
Figure SMS_308
Represented character sequence->
Figure SMS_303
Belongs to non-entity.
The entity recognition method of the embodiment performs character embedding on an input text, and generates unique vector representation for each character; determining potential entity areas and corresponding context areas in the text by enumerating span units in the input sequence; jointly modeling potential entity regions and context regions using a graph convolution network and a multi-headed attention layer; the result of the joint modeling determines the entity class of the potential entity region via a classifier. The entity identification method can efficiently and accurately identify the contained entity information from the unstructured sequence text. When the character sequence in the text is identified as the entity, the embodiment considers the semantic information of the sequence, fully models the context information formed by the residual characters, and effectively improves the accuracy of entity identification. In this embodiment, by means of enumeration, all character sub-sequences in the text are considered to be potential entities, so that overlapping entity information in the text can be well identified. For example, "Wuhan Yangtze bridge" is an entity, and "Wuhan" included therein is also an entity.
Example III
Referring to fig. 8, fig. 8 is a schematic diagram of the structure of an entity recognition apparatus of the present embodiment. The entity identification device 20 of this embodiment comprises a processor 21, a memory 22 and a computer program stored in said memory 22 and executable on said processor 21. The steps of the above-described method embodiments are implemented by the processor 21 when executing the computer program. Alternatively, the processor 21 may implement the functions of the modules/units in the above-described device embodiments when executing the computer program.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used to describe the execution of the computer program in the entity identification device 20. For example, the computer program may be divided into modules in the second embodiment, and specific functions of each module refer to the working process of the apparatus described in the foregoing embodiment, which is not described herein.
The entity identification device 20 may include, but is not limited to, a processor 21, a memory 22. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the entity identification device 20 and does not constitute a limitation of the entity identification device 20, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the entity identification device 20 may also include input-output devices, network access devices, buses, etc.
The processor 21 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 21 is a control center of the entity identification device 20, and connects the various parts of the entire entity identification device 20 using various interfaces and lines.
The memory 22 may be used to store the computer program and/or module, and the processor 21 may implement the various functions of the entity identification device 20 by running or executing the computer program and/or module stored in the memory 22 and invoking data stored in the memory 22. The memory 22 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 (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Wherein the integrated modules/units of the entity identification device 20 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of each of the method embodiments described above when executed by the processor 21. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (10)

1. An entity identification method is characterized in that: the method comprises the following steps:
s1, performing character embedding on an input text to obtainGenerating a unique vector representation for each character to obtain a vector sequence of input text
Figure QLYQS_1
；
S2, inputting a text vector sequence by enumeration
Figure QLYQS_2
The span unit in (1) obtaining the span set of the input text +.>
Figure QLYQS_3
；
S3, collecting the spans
Figure QLYQS_4
Input semantic feature vector of bidirectional convolution generation span region +.>
Figure QLYQS_5
；
S4, the semantic feature vector is processed
Figure QLYQS_6
Inputting the two-way long-short-period memory network to obtain the context information +.>
Figure QLYQS_7
；
S5, the context information is processed
Figure QLYQS_8
Obtaining the joint modeling result of the semantic features and the contextual features of the span units by nonlinear transformation>
Figure QLYQS_9
；
S6, modeling the indicated combination results
Figure QLYQS_10
The input classifier obtains the entity class.
2. The method according to claim 1, characterized in that: the step S1 includes: s11, randomly initializing a feature matrix
Figure QLYQS_11
An embedding matrix as a character, wherein->
Figure QLYQS_12
Is the length of the character table, < >>
Figure QLYQS_13
Representing the embedding dimension of each character;
s12, for each character in the input text, the character is extracted from the feature matrix according to the id of the character in the character table
Figure QLYQS_14
The middle cables lead to respective vector representations.
3. The method according to claim 1, characterized in that: the step S3 includes:
s31, reconstructing a span sequence of the chain structure into a graph structure;
s32, constructing each node characteristic in the two-way graph convolution layer aggregation graph;
s33, accumulating and averaging all nodes in the feature map, and calculating semantic feature representation of the span unit
Figure QLYQS_15
。
4. A method according to claim 3, characterized in that: the step S4 includes:
s41, using feature vectors
Figure QLYQS_16
Replacement of vector sequences of span units in the original input vector sequence, i.e. +.>
Figure QLYQS_17
Become->
Figure QLYQS_18
;
S42, constructing two-way long-short-term memory network modeling
Figure QLYQS_19
Is a sequence feature of (2);
s43, aggregating sequences based on self-attention mechanisms
Figure QLYQS_20
Midspan characteristics->
Figure QLYQS_21
And contextual characteristics->
Figure QLYQS_22
The dependency relationship exists, and the calculation formula is as follows:
Figure QLYQS_23
，
wherein ,
Figure QLYQS_25
is of dimension +.>
Figure QLYQS_27
Is a normalized exponential function; />
Figure QLYQS_29
Is a feature vector of a span unit with dimension +.>
Figure QLYQS_26
；/>
Figure QLYQS_28
Is of a two-way long-short-term memory networkFeature matrix formed by state feature vectors, the dimension is +.>
Figure QLYQS_30
；/>
Figure QLYQS_31
As a joint modeling output of span semantic features and context features, the vector dimension is +.>
Figure QLYQS_24
。/>
5. The method according to claim 4, wherein: the step S5 includes:
s51, repeatlSub-step S4, depth modeling semantic and contextual features, the output feature vectors of which are expressed as
Figure QLYQS_32
；
S52, feature vectors
Figure QLYQS_33
The most input is output via the following way>
Figure QLYQS_34
Combined modeling result of semantic features and contextual features +.>
Figure QLYQS_35
。
6. An entity recognition device, characterized in that: comprising the following units:
an input text vector generation unit for character embedding the input text, generating a unique vector representation for each character to obtain a vector sequence of the input text
Figure QLYQS_36
；
A span set generating unit for inputting text for enumerating the input text vector sequence
Figure QLYQS_37
The span unit in (1) obtaining the span set of the input text +.>
Figure QLYQS_38
；
A semantic feature vector generation unit for aggregating the spans
Figure QLYQS_39
Input semantic feature vector of bidirectional convolution generation span region +.>
Figure QLYQS_40
；
A context information generating unit for generating the semantic feature vector
Figure QLYQS_41
Inputting the two-way long-short-period memory network to obtain the context information +.>
Figure QLYQS_42
；
A joint modeling result generation unit of semantic features and context features for generating the context information
Figure QLYQS_43
Obtaining the joint modeling result of the semantic features and the contextual features of the span units by nonlinear transformation>
Figure QLYQS_44
；
An entity acquisition unit for modeling the results of the joint modeling
Figure QLYQS_45
The input classifier obtains the entity class.
7. The apparatus according to claim 6, wherein: the input text vector generation unit includes: an embedded matrix initializing unit for randomly initializing a feature matrix
Figure QLYQS_46
An embedding matrix as a character, wherein->
Figure QLYQS_47
Is the length of the character table, < >>
Figure QLYQS_48
Representing the embedding dimension of each character;
a vector generation unit for generating a character matrix for each character in the input text based on its id in the character table
Figure QLYQS_49
The middle cables lead to respective vector representations.
8. The apparatus according to claim 6, wherein: the semantic feature vector generating unit includes:
a graph structure reconstructing unit for reconstructing the span sequence of the chain structure into a graph structure;
the bidirectional graph convolution construction unit is used for constructing each node characteristic in the bidirectional graph convolution layer aggregation graph;
a semantic feature representation calculation unit for calculating semantic feature representation of the span unit by cumulatively averaging each node in the feature map
Figure QLYQS_50
。
9. The apparatus according to claim 8, wherein: the context information generation unit includes:
a first vector replacement unit for using feature vectors
Figure QLYQS_51
Replacement of vector sequences of span units in the original input vector sequence, i.e. +.>
Figure QLYQS_52
Become->
Figure QLYQS_53
;
Two-way long-short-term memory network construction unit for constructing two-way long-short-term memory network modeling
Figure QLYQS_54
Is a sequence feature of (2); />
A first joint modeling unit for aggregating sequences based on a self-attention mechanism
Figure QLYQS_55
Midspan characteristics->
Figure QLYQS_56
With contextual characteristics
Figure QLYQS_57
The dependency relationship exists, and the calculation formula is as follows:
Figure QLYQS_58
，
wherein ,
Figure QLYQS_60
is of dimension +.>
Figure QLYQS_63
Is a normalized exponential function; />
Figure QLYQS_65
Is a feature vector of a span unit with dimension +.>
Figure QLYQS_61
；/>
Figure QLYQS_62
Is a feature matrix formed by state feature vectors of a two-way long-short-term memory network, and the dimension is +.>
Figure QLYQS_64
；/>
Figure QLYQS_66
As a joint modeling output of span semantic features and context features, the vector dimension is +.>
Figure QLYQS_59
。
10. The apparatus according to claim 9, wherein: the joint modeling result generating unit of the semantic features and the context features comprises:
a first execution unit for repeatedly executinglA secondary context information generating unit for modeling semantic features and context feature depth, the output feature vector of which is expressed as
Figure QLYQS_67
；
A second modeling unit for modeling the feature vector
Figure QLYQS_68
The most input is output via the following way>
Figure QLYQS_69
Combined modeling result of semantic features and contextual features +.>
Figure QLYQS_70
。/>
CN202310417766.9A 2023-04-19 2023-04-19 Entity identification method and device Active CN116151241B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310417766.9A CN116151241B (en) 2023-04-19 2023-04-19 Entity identification method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310417766.9A CN116151241B (en) 2023-04-19 2023-04-19 Entity identification method and device

Publications (2)

Publication Number Publication Date
CN116151241A true CN116151241A (en) 2023-05-23
CN116151241B CN116151241B (en) 2023-07-07

Family

ID=86373973

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310417766.9A Active CN116151241B (en) 2023-04-19 2023-04-19 Entity identification method and device

Country Status (1)

Country Link
CN (1) CN116151241B (en)

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180082197A1 (en) * 2016-09-22 2018-03-22 nference, inc. Systems, methods, and computer readable media for visualization of semantic information and inference of temporal signals indicating salient associations between life science entities
EP3385862A1 (en) * 2017-04-03 2018-10-10 Siemens Aktiengesellschaft A method and apparatus for performing hierarchical entity classification
CN109165384A (en) * 2018-08-23 2019-01-08 成都四方伟业软件股份有限公司 A kind of name entity recognition method and device
CN111178074A (en) * 2019-12-12 2020-05-19 天津大学 Deep learning-based Chinese named entity recognition method
CN111651993A (en) * 2020-05-11 2020-09-11 北京理工大学 Chinese named entity recognition method fusing local-global character level association features
CN112711948A (en) * 2020-12-22 2021-04-27 北京邮电大学 Named entity recognition method and device for Chinese sentences
CN112765994A (en) * 2021-01-26 2021-05-07 武汉大学 Deep learning-based information element joint extraction method and system
CN113408273A (en) * 2021-06-30 2021-09-17 北京百度网讯科技有限公司 Entity recognition model training and entity recognition method and device
CN113535928A (en) * 2021-08-05 2021-10-22 陕西师范大学 Service discovery method and system of long-term and short-term memory network based on attention mechanism
CN113591483A (en) * 2021-04-27 2021-11-02 重庆邮电大学 Document-level event argument extraction method based on sequence labeling
CN113836910A (en) * 2021-09-17 2021-12-24 山东师范大学 Text recognition method and system based on multilevel semantics
CN114239585A (en) * 2021-12-17 2022-03-25 安徽理工大学 Biomedical nested named entity recognition method
CN114330338A (en) * 2022-01-13 2022-04-12 东北电力大学 Program language identification system and method fusing associated information
CN115600605A (en) * 2022-10-31 2023-01-13 陕西师范大学（Cn） Method, system, equipment and storage medium for jointly extracting Chinese entity relationship
CN115688752A (en) * 2022-09-16 2023-02-03 杭州电子科技大学 Knowledge extraction method based on multi-semantic features
US20230059494A1 (en) * 2021-08-19 2023-02-23 Digital Asset Capital, Inc. Semantic map generation from natural-language text documents

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180082197A1 (en) * 2016-09-22 2018-03-22 nference, inc. Systems, methods, and computer readable media for visualization of semantic information and inference of temporal signals indicating salient associations between life science entities
EP3385862A1 (en) * 2017-04-03 2018-10-10 Siemens Aktiengesellschaft A method and apparatus for performing hierarchical entity classification
CN109165384A (en) * 2018-08-23 2019-01-08 成都四方伟业软件股份有限公司 A kind of name entity recognition method and device
CN111178074A (en) * 2019-12-12 2020-05-19 天津大学 Deep learning-based Chinese named entity recognition method
CN111651993A (en) * 2020-05-11 2020-09-11 北京理工大学 Chinese named entity recognition method fusing local-global character level association features
CN112711948A (en) * 2020-12-22 2021-04-27 北京邮电大学 Named entity recognition method and device for Chinese sentences
CN112765994A (en) * 2021-01-26 2021-05-07 武汉大学 Deep learning-based information element joint extraction method and system
CN113591483A (en) * 2021-04-27 2021-11-02 重庆邮电大学 Document-level event argument extraction method based on sequence labeling
CN113408273A (en) * 2021-06-30 2021-09-17 北京百度网讯科技有限公司 Entity recognition model training and entity recognition method and device
CN113535928A (en) * 2021-08-05 2021-10-22 陕西师范大学 Service discovery method and system of long-term and short-term memory network based on attention mechanism
US20230059494A1 (en) * 2021-08-19 2023-02-23 Digital Asset Capital, Inc. Semantic map generation from natural-language text documents
CN113836910A (en) * 2021-09-17 2021-12-24 山东师范大学 Text recognition method and system based on multilevel semantics
CN114239585A (en) * 2021-12-17 2022-03-25 安徽理工大学 Biomedical nested named entity recognition method
CN114330338A (en) * 2022-01-13 2022-04-12 东北电力大学 Program language identification system and method fusing associated information
CN115688752A (en) * 2022-09-16 2023-02-03 杭州电子科技大学 Knowledge extraction method based on multi-semantic features
CN115600605A (en) * 2022-10-31 2023-01-13 陕西师范大学（Cn） Method, system, equipment and storage medium for jointly extracting Chinese entity relationship

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CHIU J P C,NICHOLS E: "Named entity recognition with bidirectional LSTM-CNNs", TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS *
魏笑;秦永彬;陈艳平;: "一种基于部件CNN的网络安全命名实体识别方法", 计算机与数字工程, no. 01 *

Also Published As

Publication number Publication date
CN116151241B (en) 2023-07-07

Similar Documents

Publication Publication Date Title
TWI788529B (en) Credit risk prediction method and device based on LSTM model
CN112016312B (en) Data relation extraction method and device, electronic equipment and storage medium
CN111461168A (en) Training sample expansion method and device, electronic equipment and storage medium
CN108921566A (en) A kind of wash sale recognition methods and device based on graph structure model
US11861308B2 (en) Mapping natural language utterances to operations over a knowledge graph
CN112836502B (en) Financial field event implicit causal relation extraction method
CN112507095A (en) Information identification method based on weak supervised learning and related equipment
CN112966517A (en) Training method, device, equipment and medium for named entity recognition model
CN114780701A (en) Automatic question-answer matching method, device, computer equipment and storage medium
CN113486166B (en) Construction method, device and equipment of intelligent customer service robot and storage medium
CN113110843A (en) Contract generation model training method, contract generation method and electronic equipment
CN113626576A (en) Method and device for extracting relational characteristics in remote supervision, terminal and storage medium
CN116151241B (en) Entity identification method and device
CN117520503A (en) Financial customer service dialogue generation method, device, equipment and medium based on LLM model
CN112507323A (en) Model training method and device based on unidirectional network and computing equipment
CN112765936B (en) Training method and device for operation based on language model
CN114692022A (en) Position prediction method and system based on space-time behavior mode
CN112651753A (en) Intelligent contract generation method and system based on block chain and electronic equipment
CN113282837A (en) Event analysis method and device, computer equipment and storage medium
CN112836045A (en) Data processing method and device based on text data set and terminal equipment
CN115544214B (en) Event processing method, device and computer readable storage medium
CN111738358A (en) Data identification method, device, equipment and readable medium
CN111882429B (en) Bank system field length segmentation method and device
CN111046153B (en) Voice assistant customization method, voice assistant customization device and intelligent equipment
CN111311076B (en) Account risk management method, device, equipment and medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant