501 Hits in 9.2 sec

TRM – Learning Dependencies between Text and Structure with Topical Relational Models [chapter]

Veli Bicer, Thanh Tran, Yongtao Ma, Rudi Studer
2013 Lecture Notes in Computer Science  
We propose an approach, called Topical Relational Model, as a principled approach for automatically learning topics from both textual and structure information.  ...  Text-rich structured data become more and more ubiquitous on the Web and on the enterprise databases by encoding heterogeneous structural relationships between entities such as people, locations, or organizations  ...  In this paper, we propose Topical Relational Model (TRM) that uses relational information in structured data for topic modeling (text analysis tasks), and also allows the learned topics to be employed  ... 
doi:10.1007/978-3-642-41335-3_1 fatcat:jkqusnnyjzhspbfazew7jijvki

Semi-automatic Technology Roadmapping Composing Method for Multiple Science, Technology, and Innovation Data Incorporation [chapter]

Yi Zhang, Hongshu Chen, Donghua Zhu
2016 Innovation, Technology, and Knowledge Management  
TRM composing model with expert aid.  ...  Addressing these concerns, this paper proposes a TRM composing method with a clustering-based topic identification model, a multiple science data sources integration model, and a semi-automated fuzzy set-based  ...  , we re-arrange the hieratical structure of TRM composing model in [19] and enrich the relations between components on the multi-layer landscape to display detailed topic changing routes for assessment  ... 
doi:10.1007/978-3-319-39056-7_12 fatcat:2zfhh4ju4fb65hchzgb6etuehu

BERTERS: Multimodal Representation Learning for Expert Recommendation System with Transformer [article]

N. Nikzad-Khasmakhi, M. A. Balafar, M.Reza Feizi-Derakhshi, Cina Motamed
2020 arXiv   pre-print
In our proposed system, the modalities are derived from text (articles published by candidates) and graph (their co-author connections) information.  ...  BERTERS converts text into a vector using the Bidirectional Encoder Representations from Transformer (BERT).  ...  Moreover, authors introduced a topic-sensitive method to reflect both the link structure and the topic relevance between questioners and answerers.  ... 
arXiv:2007.07229v1 fatcat:pknabu6xqrfqndyp6dsmkd2gye

Topic analysis and forecasting for science, technology and innovation: Methodology with a case study focusing on big data research

Yi Zhang, Guangquan Zhang, Hongshu Chen, Alan L. Porter, Donghua Zhu, Jie Lu
2016 Technological forecasting & social change  
By addressing and predicting these changes, this paper proposes an analytic method to (1) cluster associated terms and phrases to constitute meaningful technological topics and their interactions, and  ...  (2) identify changing topical emphases.  ...  "Related Works" reviews previous studies including text clustering, topic analysis, TRM, and a comparison between our research and related works.  ... 
doi:10.1016/j.techfore.2016.01.015 fatcat:zjqqq2pwondftgvl6zjbpq6c2y

Hierarchical Network Emotional Assistance Mechanism for Emotion Cause Extraction

Yu Wang, Bingjie Wei, Shuhua Ruan, Xingshu Chen, Haizhou Wang, Aleksandar Jevremovic
2022 Security and Communication Networks  
, and structural information between clause neighborhoods.  ...  Most of the existing work regards the task as an independent text clause classification problem, ignoring the relationship between the clauses and failing to use the indicative relationship between emotional  ...  It proves that the HNEAM model reduces the information loss caused by the long-distance dependence of clauses due to the learning of the semantic and structural information of the text and can effectively  ... 
doi:10.1155/2022/3597771 fatcat:rq4emposbve2lfpro325yva2za

Holistic and Compact Selectivity Estimation for Hybrid Queries over RDF Graphs [chapter]

Andreas Wagner, Veli Bicer, Thanh Tran, Rudi Studer
2014 Lecture Notes in Computer Science  
This way, we capture correlations between structured and unstructured data in a holistic and compact manner.  ...  We propose a novel estimation approach, TopGuess, which exploits topic models as data synopsis.  ...  These topic models summarize the data by means of one uniform synopsis -considering structured and text data.  ... 
doi:10.1007/978-3-319-11915-1_7 fatcat:ufz44u3z4zdedooeusolv2qthi

Developing a risk-adaptive technology roadmap using a Bayesian network and topic modeling under deep uncertainty

Yujin Jeong, Hyejin Jang, Byungun Yoon
2021 Scientometrics  
First we identify risk by topic modeling based on futuristic data and then by sentiment analysis.  ...  Third, we convert an existing TRM to network topology with adaptive plans and construct a conditional probability table for the network.  ...  We used a Bayesian network and text mining including topic modeling to develop the risk-adaptive roadmap because Bayesian networks allow for considering relationships between nodes and make it possible  ... 
doi:10.1007/s11192-021-03945-8 pmid:33776164 pmcid:PMC7980740 fatcat:tcymybya5nd2dgl6uhyj3u3i6e

Development of Morphology Analysis-Based Technology Roadmap Considering Layer Expansion Paths: Application of TRIZ and Text Mining

Lijie Feng, Yuxiang Niu, Jinfeng Wang
2020 Applied Sciences  
solving (TRIZ) inventive principles to establish innovation paths for new opportunities with the aid of text mining tools.  ...  Thus, the aim of this research is to develop MA-based TRMs by utilizing MA to describe the characteristics of the technology and product layers in the TRMs and apply the improved theory of inventive problem  ...  The models pulled by market and pushed by technology have interconnections with the market and technology layers in TRMs, which could be used to explain the integration between MA and TRMs. Yoon et al  ... 
doi:10.3390/app10238498 fatcat:gbpho32oyrfdbfrlis55rcuefy


Huyen Trang Phan, Ngoc Thanh Nguyen, Dosam Hwang
2021 Journal of Computer Science and Cybernetics  
In addition, discussions and comparisons related to these methods are provided. Additionally, we discuss the challenges and possible research directions for future research in this field.  ...  With the rapid development of the Internet industry, an increasing number of social media platforms have been developed.  ...  Therefore, before using machine-learning and deep-learning algorithms, it is essential to convert text data into numerical vectors by building text representation models (TRMs).  ... 
doi:10.15625/1813-9663/37/4/15892 fatcat:2dgv3sygovgelk3mffmvnmokay

Technology Roadmapping of Emerging Technologies: Scientometrics and Time Series Approach [chapter]

Iñaki Bildosola, Rosamaría Río-Bélver, Gaizka Garechana, Enara Zarrabeitia
2018 Scientometrics  
These methods are scientometrics, with which a customized and clean database is generated; hierarchical clustering to generate the ontology of the technology; principal component analysis, which is used  ...  The present work is framed within tech mining and technology forecasting fields.  ...  fuzzy set-based TRM composing model with expert aid.  ... 
doi:10.5772/intechopen.76675 fatcat:6cycw6vqj5banblmud2bgmuwwi

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Yufeng Sun, Fengbao Yang, Xiaoxia Wang, Hongsong Dong, Ali Ahmadian
2021 Mathematical Problems in Engineering  
kernels with different sizes are designed to extract the relationships between adjacent sentences.  ...  of the text and in turn leads to an adverse summarization performance.  ...  Our model can better extract long dependency and relations between sentences. Training Loss Convergence.  ... 
doi:10.1155/2021/3591894 fatcat:vhj5yxhv6jeapbadyaxg3mdnt4

Sentiment Analysis of online reviews based on LDA and AP-Bert model

Menglin Yang, Yiqing Lu
2022 Highlights in Science, Engineering and Technology  
Firstly, LDA topic extraction model is used to extract the topic of online review text, and the concerned attributes are extracted.  ...  According to the characteristics of online comments, a BERT emotion analysis model with enhanced pooling was proposed.  ...  However, the deep learning model is not suitable for review texts with such features as multi-dependent word vector encoding or one-HOT encoding in the text embedding layer.  ... 
doi:10.54097/hset.v1i.472 fatcat:dts27tiz7fbbjjte2ptds2vdw4

A Novel Framework for Mining Social Media Data Based on Text Mining, Topic Modeling, Random Forest, and DANP Methods

Chi-Yo Huang, Chia-Lee Yang, Yi-Hao Hsiao
2021 Mathematics  
Latent Dirichlet allocation (LDA) will be adopted to derive topic models based on the data retrieved from social media.  ...  ., the mutual influences between altruistic concerns and egoistic concerns, as well as those between altruistic concerns and biosphere concerns, are worth further investigation in future.  ...  A corpus D is defined as a collection Text Mining, Topic Model and LDA Text mining was first proposed by Fledman et al. [28] .  ... 
doi:10.3390/math9172041 fatcat:zewlvwxazzhwtgymch3z4qpy4i

A literature review on the state-of-the-art in patent analysis

Assad Abbas, Limin Zhang, Samee U. Khan
2014 World Patent Information  
patents quality and the most promising patents, and identifying technological hotspots and patent vacuums.  ...  Moreover, the key features and weaknesses of the discussed tools and techniques are presented and several directions for future research are highlighted.  ...  Khan's research interests include optimization, robustness, and security of: cloud, grid, cluster and big data computing, social networks, wired and wireless networks, power systems, smart grids, and optical  ... 
doi:10.1016/j.wpi.2013.12.006 fatcat:prs6spbuhfd6lheiocbw5jz3di

DialogueTRM: Exploring the Intra- and Inter-Modal Emotional Behaviors in the Conversation [article]

Yuzhao Mao, Qi Sun, Guang Liu, Xiaojie Wang, Weiguo Gao, Xuan Li, Jianping Shen
2020 arXiv   pre-print
For intra-modal, we construct a novel Hierarchical Transformer that can easily switch between sequential and feed-forward structures according to the differentiated context preference within each modality  ...  For inter-modal, we constitute a novel Multi-Grained Interactive Fusion that applies both neuron- and vector-grained feature interactions to learn the differentiated contributions across all modalities  ...  The "67.67" result in the text-only column is based on our intra-modal module fed with text-only features. Comparison with SOTA. DialogueRNN is the SOTA model for ERC in multi-modal settings.  ... 
arXiv:2010.07637v1 fatcat:dgihpizrdfenrgayok7mketuj4
« Previous Showing results 1 — 15 out of 501 results