CN109344399B - 一种基于堆叠双向lstm神经网络的文本相似度计算方法 - Google Patents
一种基于堆叠双向lstm神经网络的文本相似度计算方法 Download PDFInfo
- Publication number
- CN109344399B CN109344399B CN201811075571.6A CN201811075571A CN109344399B CN 109344399 B CN109344399 B CN 109344399B CN 201811075571 A CN201811075571 A CN 201811075571A CN 109344399 B CN109344399 B CN 109344399B
- Authority
- CN
- China
- Prior art keywords
- sentence
- input
- vector
- neural network
- vectors
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 32
- 230000002457 bidirectional effect Effects 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 126
- 238000000034 method Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 4
- 230000015654 memory Effects 0.000 description 4
- 238000011176 pooling Methods 0.000 description 3
- 230000008034 disappearance Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
Description
方法 | 本实施例 | Wmd | tfidf | 编辑相似度 |
相似度 | 0.77 | 0.34 | 0 | 0.22 |
方法 | 本实施例 | Wmd | tfidf | 编辑距离 |
F1值 | 0.81 | 0.68 | 0.63 | 0.47 |
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811075571.6A CN109344399B (zh) | 2018-09-14 | 2018-09-14 | 一种基于堆叠双向lstm神经网络的文本相似度计算方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811075571.6A CN109344399B (zh) | 2018-09-14 | 2018-09-14 | 一种基于堆叠双向lstm神经网络的文本相似度计算方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109344399A CN109344399A (zh) | 2019-02-15 |
CN109344399B true CN109344399B (zh) | 2023-02-03 |
Family
ID=65305318
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811075571.6A Active CN109344399B (zh) | 2018-09-14 | 2018-09-14 | 一种基于堆叠双向lstm神经网络的文本相似度计算方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109344399B (zh) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109992978B (zh) * | 2019-03-05 | 2021-03-26 | 腾讯科技(深圳)有限公司 | 信息的传输方法、装置及存储介质 |
CN109992772A (zh) * | 2019-03-13 | 2019-07-09 | 众安信息技术服务有限公司 | 一种文本相似度计算方法及装置 |
CN111861610B (zh) * | 2019-04-30 | 2024-10-25 | 北京嘀嘀无限科技发展有限公司 | 一种数据处理方法、装置、电子设备及存储介质 |
CN110941951B (zh) * | 2019-10-15 | 2022-02-15 | 平安科技(深圳)有限公司 | 文本相似度计算方法、装置、介质及电子设备 |
CN111325029B (zh) * | 2020-02-21 | 2023-08-22 | 河海大学 | 一种基于深度学习集成模型的文本相似度计算方法 |
CN111859988A (zh) * | 2020-07-28 | 2020-10-30 | 阳光保险集团股份有限公司 | 一种语义相似度评价方法、装置和计算机可读存储介质 |
CN112085091B (zh) * | 2020-09-07 | 2024-04-26 | 中国平安财产保险股份有限公司 | 基于人工智能的短文本匹配方法、装置、设备及存储介质 |
CN112328748A (zh) * | 2020-11-11 | 2021-02-05 | 上海昌投网络科技有限公司 | 一种用于保险配置意图识别的方法 |
CN112632927A (zh) * | 2020-12-30 | 2021-04-09 | 上海犀语科技有限公司 | 一种基于语义处理的表格片段链接复原方法及系统 |
CN113177406B (zh) * | 2021-04-23 | 2023-07-07 | 珠海格力电器股份有限公司 | 文本处理方法、装置、电子设备和计算机可读介质 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106295796A (zh) * | 2016-07-22 | 2017-01-04 | 浙江大学 | 基于深度学习的实体链接方法 |
EP3156949A2 (en) * | 2015-10-16 | 2017-04-19 | Baidu USA LLC | Systems and methods for human inspired simple question answering (hisqa) |
CN106997376A (zh) * | 2017-02-28 | 2017-08-01 | 浙江大学 | 一种基于多级特征的问题和答案句子相似度计算方法 |
CN107729322A (zh) * | 2017-11-06 | 2018-02-23 | 广州杰赛科技股份有限公司 | 分词方法及装置、建立句子向量生成模型方法及装置 |
CN107832400A (zh) * | 2017-11-01 | 2018-03-23 | 山东大学 | 一种基于位置的lstm和cnn联合模型进行关系分类的方法 |
CA3039517A1 (en) * | 2016-11-03 | 2018-05-11 | Salesforce.Com, Inc. | Joint many-task neural network model for multiple natural language processing (nlp) tasks |
CN108427665A (zh) * | 2018-03-15 | 2018-08-21 | 广州大学 | 一种基于lstm型rnn模型的文本自动生成方法 |
-
2018
- 2018-09-14 CN CN201811075571.6A patent/CN109344399B/zh active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3156949A2 (en) * | 2015-10-16 | 2017-04-19 | Baidu USA LLC | Systems and methods for human inspired simple question answering (hisqa) |
CN106295796A (zh) * | 2016-07-22 | 2017-01-04 | 浙江大学 | 基于深度学习的实体链接方法 |
CA3039517A1 (en) * | 2016-11-03 | 2018-05-11 | Salesforce.Com, Inc. | Joint many-task neural network model for multiple natural language processing (nlp) tasks |
CN106997376A (zh) * | 2017-02-28 | 2017-08-01 | 浙江大学 | 一种基于多级特征的问题和答案句子相似度计算方法 |
CN107832400A (zh) * | 2017-11-01 | 2018-03-23 | 山东大学 | 一种基于位置的lstm和cnn联合模型进行关系分类的方法 |
CN107729322A (zh) * | 2017-11-06 | 2018-02-23 | 广州杰赛科技股份有限公司 | 分词方法及装置、建立句子向量生成模型方法及装置 |
CN108427665A (zh) * | 2018-03-15 | 2018-08-21 | 广州大学 | 一种基于lstm型rnn模型的文本自动生成方法 |
Non-Patent Citations (3)
Title |
---|
A Deep Architecture for Semantic Matching;Shengxian Wan etc.;《Vol. 30 No. 1 (2016): Thirtieth AAAI Conference on Artificial Intelligence》;20160315;全文 * |
IDENTIFYING RAGA SIMILARITY THROUGH EMBEDDINGS LEARNED;Joe Cheri Ross etc.;《ISMIR, 2017》;20171231;全文 * |
基于CNN与双向LSTM的中文文本蕴含识别方法;谭咏梅 等;《中文信息学报》;20180715;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN109344399A (zh) | 2019-02-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109344399B (zh) | 一种基于堆叠双向lstm神经网络的文本相似度计算方法 | |
CN111104794B (zh) | 一种基于主题词的文本相似度匹配方法 | |
CN107133213B (zh) | 一种基于算法的文本摘要自动提取方法与系统 | |
CN110442760B (zh) | 一种问答检索系统的同义词挖掘方法及装置 | |
CN111221944B (zh) | 文本意图识别方法、装置、设备和存储介质 | |
CN111325029B (zh) | 一种基于深度学习集成模型的文本相似度计算方法 | |
CN110263325B (zh) | 中文分词系统 | |
CN111125349A (zh) | 基于词频和语义的图模型文本摘要生成方法 | |
CN111898374B (zh) | 文本识别方法、装置、存储介质和电子设备 | |
CN107480200B (zh) | 基于词标签的词语标注方法、装置、服务器及存储介质 | |
CN108509521B (zh) | 一种自动生成文本索引的图像检索方法 | |
CN108920599B (zh) | 一种基于知识本体库的问答系统答案精准定位和抽取方法 | |
CN113761868B (zh) | 文本处理方法、装置、电子设备及可读存储介质 | |
CN113688954A (zh) | 一种计算文本相似度的方法、系统、设备和存储介质 | |
CN111291188A (zh) | 一种智能信息抽取方法及系统 | |
CN107895000A (zh) | 一种基于卷积神经网络的跨领域语义信息检索方法 | |
CN113326702B (zh) | 语义识别方法、装置、电子设备及存储介质 | |
CN113392209A (zh) | 一种基于人工智能的文本聚类方法、相关设备及存储介质 | |
CN104008187A (zh) | 一种基于最小编辑距离的半结构化文本匹配方法 | |
CN115203421A (zh) | 一种长文本的标签生成方法、装置、设备及存储介质 | |
CN111191031A (zh) | 一种基于WordNet和IDF的非结构化文本的实体关系分类方法 | |
CN115600597A (zh) | 基于注意力机制和词内语义融合的命名实体识别方法、装置、系统及存储介质 | |
CN112699685A (zh) | 基于标签引导的字词融合的命名实体识别方法 | |
Wang et al. | Named entity recognition method of brazilian legal text based on pre-training model | |
CN112988970A (zh) | 一种服务于智能问答系统的文本匹配算法 |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Qin Hong Hui Inventor after: Du Ruo Inventor after: Xiang Hai Inventor after: Hou Cong Inventor after: Liu Ke Inventor before: Qin Hong Hui |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240926 Address after: Room 209, First Floor, No. 364 Industrial Avenue Middle Road, Haizhu District, Guangzhou City, Guangdong Province, 510220 Patentee after: Guangzhou Youyi Information Technology Co.,Ltd. Country or region after: China Address before: 401120 No. 1, Floor 3, Building 11, Internet Industrial Park, No. 106, West Section of Jinkai Avenue, Yubei District, Chongqing Patentee before: CHONGQING XIEZHI TECHNOLOGY Co.,Ltd. Country or region before: China |
|
TR01 | Transfer of patent right |