期刊文献+
共找到13,618篇文章
< 1 2 250 >
每页显示 20 50 100
基于Sentence-BERT与孤立森林算法的专利新颖性评估
1
作者 邓娜 王雨佳 +1 位作者 杨洋 陈旭 《情报杂志》 北大核心 2025年第2期174-182,共9页
[研究目的]面对专利数量的迅猛增长,采用人工方法评估专利新颖性变得愈发困难,且目前专利新颖性评估研究过度聚焦于技术层面,未能综合考虑专利的其他信息因素。因此,实现更高效、客观的专利新颖性评估具有重要的现实意义。[研究方法]提... [研究目的]面对专利数量的迅猛增长,采用人工方法评估专利新颖性变得愈发困难,且目前专利新颖性评估研究过度聚焦于技术层面,未能综合考虑专利的其他信息因素。因此,实现更高效、客观的专利新颖性评估具有重要的现实意义。[研究方法]提出一种基于Sentence-BERT与孤立森林算法的专利新颖性评估方法。首先,使用专利标题与IPC分类号分别作为专利的应用方向与功能分类特征,再通过BiLSTM-CRF模型对专利摘要进行关键技术抽取作为实施方法特征;其次,采用Sentence-BERT对上述特征进行文本向量化表示后组合输入至孤立森林算法获得离群专利集;最后,通过技术量权值过滤法提高专利新颖性评估的精度。[研究结果/结论]以金融科技领域专利进行实证研究,结果表明,该评估方法准确率相较专业专利分析平台方法提升了9%~11%。证明了该方法在专利新颖性评估中的有效性,能为后续专利审核工作和高价值专利分析提供参考。 展开更多
关键词 专利评估 专利新颖性 BiLSTM-CRF sentence-BERT 孤立森林算法 机器学习
下载PDF
Review of Research on English Translation of Chinese Running Sentences
2
作者 ZHANG Wen-hui 《Journal of Literature and Art Studies》 2024年第7期624-627,共4页
In order to convey complete meanings,there is a phenomenon in Chinese of using multiple running sentences.Xu Jingning(2023,p.66)states,“In communication,a complete expression of meaning often requires more than one c... In order to convey complete meanings,there is a phenomenon in Chinese of using multiple running sentences.Xu Jingning(2023,p.66)states,“In communication,a complete expression of meaning often requires more than one clause,which is common in human languages.”Domestic research on running sentences includes discussions on defining the concept and structural features of running sentences,sentence properties,sentence pattern classifications and their criteria,as well as issues related to translating running sentences into English.This article primarily focuses on scholarly research into the English translation of running sentences in China,highlighting recent achievements and identifying existing issues in the study of running sentence translation.However,by reviewing literature on the translation of running sentences,it is found that current research in the academic community on non-core running sentences is limited.Therefore,this paper proposes relevant strategies to address this issue. 展开更多
关键词 Chinese running sentences TOPICS English-Chinese translation
下载PDF
Sentence及其结构研究——以古典主义时期作品为例
3
作者 符方泽 杨伟杰 《北方音乐》 2024年第1期131-140,共10页
文章以sentence为研究对象,一方面对国内外曲式学教材及相关文献展开概念比较、辨析与理论梳理,阐明其基本概念与内部结构;另一方面则以古典主义时期作品为分析实例,讨论这种特定主题(句法)的“结构范型”、并进一步对其“结构变形”的... 文章以sentence为研究对象,一方面对国内外曲式学教材及相关文献展开概念比较、辨析与理论梳理,阐明其基本概念与内部结构;另一方面则以古典主义时期作品为分析实例,讨论这种特定主题(句法)的“结构范型”、并进一步对其“结构变形”的情况进行归类。 展开更多
关键词 sentence 古典风格 范型 变形 陈述短句 延续短句
下载PDF
基于Sentence-BERT的专利技术主题聚类研究——以人工智能领域为例 被引量:5
4
作者 阮光册 周萌葳 《情报杂志》 CSSCI 北大核心 2024年第2期110-117,共8页
[研究目的]将Sentence-BERT模型应用于专利技术主题聚类,解决专利文献为突出新颖性,常使用独特技术术语造成词汇向量语义特征稀疏的问题。[研究方法]以人工智能领域2015年-2019年的22370篇专利为实验数据。首先,采用Sentence-BERT算法... [研究目的]将Sentence-BERT模型应用于专利技术主题聚类,解决专利文献为突出新颖性,常使用独特技术术语造成词汇向量语义特征稀疏的问题。[研究方法]以人工智能领域2015年-2019年的22370篇专利为实验数据。首先,采用Sentence-BERT算法对专利文献摘要文本进行向量化表示;其次,对向量化矩阵进行数据降维,利用HDBSCAN方式寻找原始数据中的高密度簇;最后,识别类簇文本集合中的主题特征,并完成主题呈现。[研究结论]对比LDA主题模型、K-means、doc2vec等方法,本文的实验结果提高了主题划分的细粒度和精确度,获得了较好的主题一致性。如何采用fine-tune策略进一步提升模型的效果,是未来该方法进一步深入探索的方向。 展开更多
关键词 sentence-BERT 专利文本 主题识别 文本聚类
下载PDF
碳化钼负载Ru基催化剂的5-硝基苯并噻唑加氢性能研究
5
作者 黄佳怡 任小敏 +2 位作者 马军 储伟 刘岳峰 《低碳化学与化工》 北大核心 2025年第1期87-94,共8页
使用负载型金属催化剂催化含硫底物加氢时,由于硫在金属表面的强吸附可导致催化剂活性变差甚至完全失活。采用过体积浸渍法制备了不同晶相碳化钼负载Ru基催化剂(Ru/α-Mo C和Ru/β-Mo_(2)C),并用于催化5-硝基苯并噻唑(5-NBT)加氢。利用... 使用负载型金属催化剂催化含硫底物加氢时,由于硫在金属表面的强吸附可导致催化剂活性变差甚至完全失活。采用过体积浸渍法制备了不同晶相碳化钼负载Ru基催化剂(Ru/α-Mo C和Ru/β-Mo_(2)C),并用于催化5-硝基苯并噻唑(5-NBT)加氢。利用SEM、XRD、HR-TEM和XPS等对催化剂进行了表征。结果表明,α-Mo C上负载的Ru为原子级分散,而β-Mo_(2)C上负载的Ru以纳米颗粒形式分散。在80°C、2.0 MPa H_(2)、3 m L乙醇、10 mg底物和10 mg催化剂的条件下,当5-NBT转化率低于30%时,Ru/α-Mo C的5-NBT加氢反应速率为9113μmol/(g·h);反应40 min时,Ru/α-Mo C的5-NBT转化率为100%。氢-氘交换实验结果证实α-Mo C对5-NBT硝基的活化(吸附活化)有重要作用,而Ru对H_(2)解离有促进作用,这两方面作用的协同效应使Ru/α-Mo C在5-NBT加氢中表现出相对更高的催化性能。 展开更多
关键词 催化加氢 ru基催化剂 碳化钼 5-硝基苯并噻唑加氢
下载PDF
Information mining and similarity computation for semi-/un-structured sentences from the social data 被引量:1
6
作者 Peiying Zhang Xingzhe Huang Lei Zhang 《Digital Communications and Networks》 SCIE CSCD 2021年第4期518-525,共8页
In recent years,with the development of the social Internet of Things(IoT),all kinds of data accumulated on the network.These data,which contain a lot of social information and opinions.However,these data are rarely f... In recent years,with the development of the social Internet of Things(IoT),all kinds of data accumulated on the network.These data,which contain a lot of social information and opinions.However,these data are rarely fully analyzed,which is a major obstacle to the intelligent development of the social IoT.In this paper,we propose a sentence similarity analysis model to analyze the similarity in people’s opinions on hot topics in social media and news pages.Most of these data are unstructured or semi-structured sentences,so the accuracy of sentence similarity analysis largely determines the model’s performance.For the purpose of improving accuracy,we propose a novel method of sentence similarity computation to extract the syntactic and semantic information of the semi-structured and unstructured sentences.We mainly consider the subjects,predicates and objects of sentence pairs and use Stanford Parser to classify the dependency relation triples to calculate the syntactic and semantic similarity between two sentences.Finally,we verify the performance of the model with the Microsoft Research Paraphrase Corpus(MRPC),which consists of 4076 pairs of training sentences and 1725 pairs of test sentences,and most of the data came from the news of social data.Extensive simulations demonstrate that our method outperforms other state-of-the-art methods regarding the correlation coefficient and the mean deviation. 展开更多
关键词 sentence similarity computation Information mining and computation Social data Internet of things Type of sentence pairs
下载PDF
Evidence for the Hierarchical Structure of Sentences Revisited
7
作者 邱磊 《疯狂英语(理论版)》 2018年第4期196-198,共3页
To reveal invariant properties of human languages is one of the central goals of modern generative grammar.Hierarchical feature of sentence construction, one of the key notions in this regard, reflects one of the most... To reveal invariant properties of human languages is one of the central goals of modern generative grammar.Hierarchical feature of sentence construction, one of the key notions in this regard, reflects one of the most widely accepted invariant properties of human languages. However,researchers also challenge this point and argue that languages differ fundamentally from one another so that it is very hard to find any single structural property which they share. This paper revisits the evidence for the hierarchical structure of sentences from the principle of structure dependence in first and second language acquisition and argues that the recognition of hierarchical structure of sentences is essential to any linguistic exploration. 展开更多
关键词 hierarchical STruCTURE AMBIGUOUS sentence STruCTURE DEPENDENCE
下载PDF
Simplification of English Sentence Pattern Structure in the Teaching of Translation and Grammar
8
作者 汤伟 YANG Ya-lan 《海外英语》 2014年第20期278-279,共2页
In the teaching of translation and grammar,it is essential that the English sentence structure is analyzed and transformation of sentence structures both in English and Chinese in class and after class. However,many k... In the teaching of translation and grammar,it is essential that the English sentence structure is analyzed and transformation of sentence structures both in English and Chinese in class and after class. However,many kinds of English sentences structures prevent the students who study English from getting the basic idea and concept of a sentence in translation or grammatical analysis. In this paper,the author submitted the basic mould of simplification of English sentence structure,and the students can learn and master the translating technique through the simplified English sentence structure. Thus it helps to improve students' competence of translation. 展开更多
关键词 ENGLISH sentence STruCTURE SIMPLIFICATION SV SVO S
下载PDF
Ru团簇对Ni/Ni_(3)Al合金纳米线形变影响的原子模拟
9
作者 阳喜元 《原子与分子物理学报》 CAS 北大核心 2025年第1期81-87,共7页
镍基高温合金是制造先进航空发动机热端部件的关键材料之一,其高温力学性能直接关系到发动机运行安全和使用寿命.本文采用改进分析型嵌入原子模型(MAEAM)和分子动力学(MD)研究合金化元素钌(Ru)团簇对Ni/Ni_(3)Al纳米线形变机制的影响,... 镍基高温合金是制造先进航空发动机热端部件的关键材料之一,其高温力学性能直接关系到发动机运行安全和使用寿命.本文采用改进分析型嵌入原子模型(MAEAM)和分子动力学(MD)研究合金化元素钌(Ru)团簇对Ni/Ni_(3)Al纳米线形变机制的影响,结果表明:在单轴拉伸应变下,纳米线的弹性模量和屈服强度随温度升高而降低.温度较低时,纳米线形变由位错产生与发射而导致晶格滑移所引起.由于晶格热振动非谐效应不明显,Ru团簇阻碍效果显著,使得晶格滑移区域仅限于Ru团簇与Ni/Ni_(3)Al相界面之间且呈非对称分布.温度较高时,纳米线的形变由位错发射而引起晶格滑移所致,但因非谐效应显著,Ru团簇无法阻碍位错运动,滑移区域在Ru团簇周围对称分布于Ni_(3)Al相中.最后从Ru团簇微观结构及其稳定性的角度进一步分析其对纳米线形变影响. 展开更多
关键词 ru团簇 形变机制 Ni/Ni_(3)Al纳米线 原子模拟
下载PDF
Classification of Conversational Sentences Using an Ensemble Pre-Trained Language Model with the Fine-Tuned Parameter
10
作者 R.Sujatha K.Nimala 《Computers, Materials & Continua》 SCIE EI 2024年第2期1669-1686,共18页
Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir... Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88. 展开更多
关键词 Bidirectional encoder for representation of transformer conversation ensemble model fine-tuning generalized autoregressive pretraining for language understanding generative pre-trained transformer hyperparameter tuning natural language processing robustly optimized BERT pretraining approach sentence classification transformer models
下载PDF
Selective Sentence Production Deficit in an Agrammatic Yoruba-English Bilingual Patient with Minor Stroke: A Case Study
11
作者 Gerald C. Imaezue Ibraheem A. Salako Akinyemi T. Akinmurele 《Journal of Behavioral and Brain Science》 2017年第9期416-424,共9页
Speech helps us to communicate with our loved ones and significant others through construction of grammatically coherent sentences that are comprehensible to our communication partners. As such, impairment of this abi... Speech helps us to communicate with our loved ones and significant others through construction of grammatically coherent sentences that are comprehensible to our communication partners. As such, impairment of this ability as a result of stroke can be debilitating and disabling to the patients as well as significant others. Agrammatism is deficit in the use and processing of grammatically coherent syntactic structures following damage to the Broca’s complex or region. Most studies have traditionally emphasized monolingual patients, with bilingualism now receiving increased attention. However, few studies have specifically investigated the effect of minor stroke on agrammatic bilingual individuals. This study examined an agrammatic Yoruba- English bilingual patient with minor stroke with a view to describing their sentence production (deficit). The findings strongly support the existence of distinct language-specific lexical-subsystem centres in the Broca’s complex for native and acquired languages (Yoruba-English) whereas both languages are likely connected to a single semantic system in the anterior temporal lobe and its surrounding regions. Furthermore, acquired language is more susceptible to brain damage than native language. This might imply that severity of deficit in speech production in both native and acquired language of bilingual aphasics may be determined by the size of lesion in the Broca’s complex or region. 展开更多
关键词 Agrammatism sentence Production STROKE BILINGUAL ENGLISH Yoruba
下载PDF
MFI分子筛限域Ru催化剂的制备及其丙烷催化燃烧性能
12
作者 王晶晶 夏良辉 +6 位作者 武雅妮 刘昱洁 徐赫 刘起源 刘基丞 建艳飞 何炽 《中国环境科学》 北大核心 2025年第1期58-65,共8页
采用原位合成法、浸渍法和沉积沉淀法制备Ru与MFI分子筛结合的3种催化剂,用于丙烷(C_(3)H_(8))的催化氧化活性研究.结果显示,通过原位合成法将Ru限域在MFI分子筛孔道内时,Ru@MFI催化剂展现出最佳的低温C_(3)H_(8)氧化活性,在270℃时达到... 采用原位合成法、浸渍法和沉积沉淀法制备Ru与MFI分子筛结合的3种催化剂,用于丙烷(C_(3)H_(8))的催化氧化活性研究.结果显示,通过原位合成法将Ru限域在MFI分子筛孔道内时,Ru@MFI催化剂展现出最佳的低温C_(3)H_(8)氧化活性,在270℃时达到90%转化率,并表现出卓越的高温热稳定性和抗水性.通过XRD、N_(2)吸脱附、HAADF-STEM以及CO-TPD等表征技术发现,限域在MFI分子筛孔道内部的Ru具有最小的粒径和最高的分散度,增加了活性Ru位点的数量.拉曼和H_(2)-TPR表征结果表明,孔道内的Ru与MFI之间相互作用导致电荷重新分布,增强了还原性能.因此,Ru@MFI催化剂呈现出最优异的C_(3)H_(8)氧化活性.此外,MFI孔道的几何限制作用在高温焙烧过程中维持Ru的稳定性和分散度,有效避免了Ru的聚集,进一步确保了催化剂的高温热稳定性. 展开更多
关键词 分子筛限域贵金属 ru@MFI 丙烷催化氧化 活性位点分散度 高温热稳定性
下载PDF
Next Words Prediction and Sentence Completion in Bangla Language Using GRU-Based RNN on N-Gram Language Model
13
作者 Afranul Hoque Busrat Jahan +3 位作者 Shaikat Chandra Paul Zinat Ara Zabu Rakhi Mondal Papeya Akter 《Journal of Data Analysis and Information Processing》 2023年第4期388-399,共12页
We use a lot of devices in our daily life to communicate with others. In this modern world, people use email, Facebook, Twitter, and many other social network sites for exchanging information. People lose their valuab... We use a lot of devices in our daily life to communicate with others. In this modern world, people use email, Facebook, Twitter, and many other social network sites for exchanging information. People lose their valuable time misspelling and retyping, and some people are not happy to type large sentences because they face unnecessary words or grammatical issues. So, for this reason, word predictive systems help to exchange textual information more quickly, easier, and comfortably for all people. These systems predict the next most probable words and give users to choose of the needed word from these suggested words. Word prediction can help the writer by predicting the next word and helping complete the sentence correctly. This research aims to forecast the most suitable next word to complete a sentence for any given context. In this research, we have worked on the Bangla language. We have presented a process that can expect the next maximum probable and proper words and suggest a complete sentence using predicted words. In this research, GRU-based RNN has been used on the N-gram dataset to develop the proposed model. We collected a large dataset using multiple sources in the Bangla language and also compared it to the other approaches that have been used such as LSTM, and Naive Bayes. But this suggested approach provides excellent exactness than others. Here, the Unigram model provides 88.22%, Bi-gram model is 99.24%, Tri-gram model is 97.69%, and 4-gram and 5-gram models provide 99.43% and 99.78% on average accurateness. We think that our proposed method profound impression on Bangla search engines. 展开更多
关键词 Bangla Language Words Prediction sentence Completion Gru RNN Corpus N-Gram
下载PDF
The Influence of Translation on the Arabic Sentence Structure:Electronic Journalism as a Model
14
作者 Yahya Ababneh Rafat MAl Rousan 《Sino-US English Teaching》 2020年第1期18-27,共10页
This study investigates the influence of translation from English on the Arabic language.Specifically,it attempts to study how the translation of English auxiliary verbs influences the syntactic structure of the Arabi... This study investigates the influence of translation from English on the Arabic language.Specifically,it attempts to study how the translation of English auxiliary verbs influences the syntactic structure of the Arabic sentence and how the English predicating structure affects that of Arabic.This study is qualitative in nature.The data of this study were based on the language of electronic journalism in Jordan as a model.A sample from two popular news agencies in the Jordanian electronic media was chosen.The study reveals that the translation of English auxiliary verbs has influenced the syntactic structure of the Arabic sentence.Particularly,the study indicates that the influence of the English auxiliary verb on Arabic caused the passive form to die out from the actual use of the Arabic language.The study also reveals a change in the predicating structure of the Arabic sentence.Moreover,the study shows a change in the deictic indication of some of the demonstratives used in Arabic sentence structures. 展开更多
关键词 TRANSLATION English auxiliary VERBS ARABIC sentence ELECTRONIC media
下载PDF
The Structure and Hierarchy of Sentence-endings in Tibetan Language
15
作者 Li Huaping 《宏观语言学》 2020年第2期28-43,共16页
This paper discusses the structure and hierarchy of sentence-endings in Tibetan language. Tibetan sentence-endings are hierarchical. They can be divided into two levels from the perspectives of structure, distribution... This paper discusses the structure and hierarchy of sentence-endings in Tibetan language. Tibetan sentence-endings are hierarchical. They can be divided into two levels from the perspectives of structure, distribution and expressive function. The first level comes after the predicate or verb phrase, indicating the category of tense/aspect/mood(TAM). The second level, which follows a self-sufficient sentence, mainly expresses the meaning of the speaker’s hint, inference, evaluation and attitude to the information. Each level includes several different types of endings, which act on different syntactic categories or manifest different degrees of subjectivity. The lower the degree of correlation between the endings and the information of the self-sufficient sentence is, the higher the corresponding semantic category and the speaker’s subjective participation are. Some lower-level endings can also express the grammatical meaning of the higher level in certain context with increasing subjectivity. 展开更多
关键词 Tibetan sentence-endings syntactic hierarchy sentence-completion category pragmatic category SUBJECTIVITY syntactic sentence pragmatic sentence
下载PDF
The C-E Translation Strategies of Run-on Sentences
16
作者 LI Yuqing JIA Xiaoqing 《Psychology Research》 2022年第10期874-878,共5页
Run-on sentences are used frequently in daily life and literature;however,there is no corresponding sentence pattern in English.Therefore,it is challenging for translators to render run-on sentences into idiomatic Eng... Run-on sentences are used frequently in daily life and literature;however,there is no corresponding sentence pattern in English.Therefore,it is challenging for translators to render run-on sentences into idiomatic English.This paper introduces the definition,classification,and the translation of run-on sentences,aiming to summarize the common rules of its translation. 展开更多
关键词 Chinese run-on sentences Chinese-English translation translation strategies
下载PDF
Structure Types and Discourse Function of N+N Nominal Sentence in Mandarin Chinese
17
作者 ZHANG Li-juan 《Journal of Literature and Art Studies》 2018年第9期1392-1399,共8页
N+N nominal sentence is an important structure type of nominal sentences in Mandarin Chinese. Attributive-center, combination, apposition and subject-predicate are its main structure types. In main literary genres, ... N+N nominal sentence is an important structure type of nominal sentences in Mandarin Chinese. Attributive-center, combination, apposition and subject-predicate are its main structure types. In main literary genres, the distribution of N+N nominal sentence shows a certain trend of dominant hierarchy: poem﹥drama﹥novel﹥prose. No matter what kind of literary genres, attributive-center structure is the type with maximum quantity, while appositive structure is the type with minimum quantity. Statistical result indicates that most of N+N nominal sentence is nominal and its use is limited by genres. Function of N+N nominal sentence is textual. When it comes to discourse, it can be used as theme, rheme and dual identity of theme and rheme based on the theory of Theme-Rheme (T-R) structure pattern. It does not only construct the information structure to deliver textual information, but also its a vital means of discourse cohesion and coherence. 展开更多
关键词 N+N nominal sentence DISCOURSE information structure
下载PDF
Syntactic Structure of Interrogative Sentences and Relative Clauses in English-- An over-view of Wh-movement
18
作者 廖勇 《大观周刊》 2011年第19期216-216,共1页
下载PDF
汉语的“句子”与英语的sentence 被引量:20
19
作者 姜望琪 《解放军外国语学院学报》 北大核心 2005年第1期10-15,共6页
汉语的"句子"不等于英语的sentence,它更像utterance。在以英语研究为代表的西方语言研究中,sentence是一个抽象单位。而汉语研究一向注重实际使用的单位,忽视抽象单位,特别是对相当于sentence这一级的研究开始较晚,以至汉语... 汉语的"句子"不等于英语的sentence,它更像utterance。在以英语研究为代表的西方语言研究中,sentence是一个抽象单位。而汉语研究一向注重实际使用的单位,忽视抽象单位,特别是对相当于sentence这一级的研究开始较晚,以至汉语的"句子"至今仍是一个具体单位,或称"动态单位"。跟sentence相当的汉语单位是"词组",不是"句子"。"词组"或称"短语"是汉语最大的结构单位、语法单位或"静态单位"。 展开更多
关键词 句子 话语 动态单位 静态单位
下载PDF
融合Sentence-BERT和LDA的评论文本主题识别 被引量:13
20
作者 阮光册 黄韵莹 《现代情报》 CSSCI 2023年第5期46-53,共8页
[目的/意义]为了解决评论文本主题识别时语义描述不充分以及学习到的主题语义连贯性不强等问题。本文将Sentence-BERT句子嵌入模型和LDA模型相结合,提升评论文本主题的语义性。[方法/过程]采用Sentence-BERT模型获取评论文本句子层面的... [目的/意义]为了解决评论文本主题识别时语义描述不充分以及学习到的主题语义连贯性不强等问题。本文将Sentence-BERT句子嵌入模型和LDA模型相结合,提升评论文本主题的语义性。[方法/过程]采用Sentence-BERT模型获取评论文本句子层面的向量特征,同时,采用LDA模型获取评论文本的概率主题向量,随后使用自动编码器连接两组向量,运用K-means算法对潜在空间向量进行聚类,从类簇中获取上下文主题信息。[结果/结论]通过对评论文本数据集的实验,本文方法可以较好地获得具有语义信息的主题词。Sentence-BERT模型与LDA结合,增加了模型的复杂性。通过对比,本文方法获得的主题一致性指标(Coherence)优于目前常见的评论文本主题识别方法。 展开更多
关键词 sentence-BERT LDA模型 评论文本 主题识别
下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部