855,515 Hits in 4.9 sec

Learning to Describe E-Commerce Images from Noisy Online Data [chapter]

Takuya Yashima, Naoaki Okazaki, Kentaro Inui, Kota Yamaguchi, Takayuki Okatani
2017 Lecture Notes in Computer Science  
We learn a generation model from product images with associated title descriptions, and examine how e-commerce specific meta-data and fine-tuning improve the generated expression.  ...  The experimental results suggest that we are able to learn from the noisy online data and produce a product description that is closer to a man-made description with possibly subjective attribute expressions  ...  Naively learning a generation model results in poor product description, e.g., made to order.  ... 
doi:10.1007/978-3-319-54193-8_6 fatcat:va3v7k3n55cwrmnot4w4n6n3xm

Probing Product Description Generation via Posterior Distillation [article]

Haolan Zhan, Hainan Zhang, Hongshen Chen, Lei Shen, Zhuoye Ding, Yongjun Bao, Weipeng Yan, Yanyan Lan
2021 arXiv   pre-print
Finally, we apply a Transformer-based decoding phase with copy mechanism to automatically generate the product description.  ...  Existing works tend to generate the product description solely based on item information, i.e., product attributes or title words, which leads to tedious contents and cannot attract customers effectively  ...  Acknowledgements The authors would like to thank Hengyi Cai from Institute of Computing Technology, Chinese Academy of Sciences, and the anonymous reviewers for their constructive comments and suggestions  ... 
arXiv:2103.01594v1 fatcat:3x73nvv2fbho3pweeoru3zk54q


Ade Riska Damayanti, Masitowarni Siregar, Puan Suri Mira Annisa Sembiring
2020 REGISTER Journal of English Language Teaching of FBS-Unimed  
The study was aimed to to develop learning media in Writing Descriptive Text for Grade VII of Junior High School Students.  ...  The interview and questionnaire results proved that the students need English learning media which can motivate the students to understand about writing descriptive text.  ...  As a youth generation, how to write your short personal descriptive text about the characteristics of places? 3) Associating The next steps was accociating.  ... 
doi:10.24114/reg.v8i3.20908 fatcat:mkj6kofh25b33jaao3ascwa3zq

Learning opinions in user-generated web content

2011 Natural Language Engineering  
Web-posted reviews of consumer goods are studied to find customer opinions about the products. We hypothesize that nonemotionally charged descriptions can be applied to predict those opinions.  ...  The obtained results support the use of non-emotional descriptions in opinion learning.  ...  These user-generated texts belong to the ever growing portion of the Web data. We presented an opinion learning method inspired by general descriptive words used by product consumers.  ... 
doi:10.1017/s135132491100012x fatcat:5chyy5bqh5a45aykyzivw2kcba

On a Novel Machine Learning Based Approach to Recommender Systems

Oleg Senko
2020 Zenodo  
product to receipt relevance matrix.  ...  The corresponding product descriptions are formed by vectors of distances between the products and precalculated product clusters obtained by applying hierarchical clustering technique to large binary  ...  The derived set of clusters is further used to generate multidimentional feature description of products.  ... 
doi:10.5281/zenodo.4007460 fatcat:utucefd6vrdzlm37chaendlxeq


Frikson Siburian, Meisuri Meisuri, Sumarsih Sumarsih
2018 GENRE Journal of Applied Linguistics of FBS Unimed  
The objective of this study was to develop learning material on descriptive text based on the students' needs as a supplementary material.  ...  Each of the text consisted of two kinds of exercise and in the last page of the product were provided the answer keys. Keywords: Reading Learning Material, Supplementary Material, Descriptive text.  ...  It differs from Report which describes things, animals, persons, or others in general. The Social Function of Descriptive Text is to describe a particular person, place, or thing.  ... 
doi:10.24114/genre.v6i1.8498 fatcat:xayslr4cu5fstnqluzrwa5zzwu

Towards Knowledge-Based Personalized Product Description Generation in E-commerce [article]

Qibin Chen, Junyang Lin, Yichang Zhang, Hongxia Yang, Jingren Zhou, Jie Tang
2019 arXiv   pre-print
In this paper, we explore a new way to generate the personalized product description by combining the power of neural networks and knowledge base.  ...  Specifically, we propose a KnOwledge Based pErsonalized (or KOBE) product description generation model in the context of E-commerce.  ...  To the best of our knowledge, our research takes the first attempt to use neural methods and sequence-to-sequence learning for product description generation by considering personalization and informativeness  ... 
arXiv:1903.12457v2 fatcat:vu6hfcepfvgcfixfs4gmffwxje

Ensemble Methods for Personalized E-Commerce Search Challenge at CIKM Cup 2016 [article]

Chen Wu, Ming Yan, Luo Si
2017 arXiv   pre-print
This paper describes our solution to tackle the challenge of personalized e-commerce search at CIKM Cup 2016.  ...  The goal of this competition is to predict search relevance and re-rank the result items in SERP according to the personalized search, browsing and purchasing preferences.  ...  generate a binary cartesian product between the single words of query and product description.  ... 
arXiv:1708.04479v1 fatcat:y42a73sx2beufod4brtjwups4q

Modeling Implicit Feedback and Latent Visual Features for Machine-Learning Based Recommendation

Yue Guan, Qiang Wei, Guoqing Chen, Xunhua Guo
2019 Proceedings of the 2019 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology (EUSFLAT 2019)  
MVBPR is a machine-leaning framework integral of deep-learning (i.e., SCAE) and topic modeling (i.e., LDA) strategies to fuse image and text information.  ...  To leverage the rapid accumulation of rich media on the Internet, this paper proposes a Multi-View Bayesian Personalized Ranking (MVBPR) recommendation model, which combines visual and textual content,  ...  Thus, a pairwise learning model can be trained to automatically learn the products' ranking for each consumer to deal with the preference uncertainty.  ... 
doi:10.2991/eusflat-19.2019.44 dblp:conf/eusflat/GuanWCG19 fatcat:ut3vac6d2bclfa72t6y7ecfd5q

A Comparison of Analytic and Experimental Goal Regression for Machine Learning

Bruce W. Porter, Dennis F. Kibler
1985 International Joint Conference on Artificial Intelligence  
Recent research demonstrates the use of goal regression as an analytic technique for learning search heuristics.  ...  The conditions that operators be invertible and that the domain be closed with respect to the inverse operators severely limit the use of analytic goal regression.  ...  The technique is applied to learning generalized state descriptions for forced wins in two-person games.  ... 
dblp:conf/ijcai/PorterK85 fatcat:qirozbrzivc6rhuapche47ve4q

Learning Content Development With Social Tools: Learning Generated Content in Engineering

Ana Maria Lopez Torres, Cristobal Nico Suarez Guerrero
2013 IEEE Revista Iberoamericana de Tecnologias del Aprendizaje  
The activities associated with learner generated content are supposed to enhance the learning process, facilitating the construction of knowledge.  ...  In this paper, the description of the process of creation of learning content is addressed.  ...  However, the fact that these sources can be easily replicated may be the origin of valueless products whose generation does not imply a personalized, active approach to learning.  ... 
doi:10.1109/rita.2013.2273110 fatcat:qgctficnnrbwhnzyliiun5mqji

Conflict detection and resolution in distributed design

José A. Ceroni, Alvaro A. Velásquez
2003 Production planning & control (Print)  
The system also implements a simple learning mechanism for selecting components to include in the design.  ...  Effective support of the design process needs new approaches, from input of specifications to generation of the design documents.  ...  Contribution to generate efficient designs of products or services is the result of identifying and solving conflicts by the system during designer work, shortening the duration of the design process.  ... 
doi:10.1080/09537280310001647850 fatcat:pedcohdrnbhztlv4iilmkirz2y

Conditional Text Generation for Harmonious Human-Machine Interaction [article]

Bin Guo, Hao Wang, Yasan Ding, Wei Wu, Shaoyang Hao, Yueqi Sun, Zhiwen Yu
2020 arXiv   pre-print
text generation, personalized text generation, and so on.  ...  The automatically generated text is becoming more and more fluent so researchers begin to consider more anthropomorphic text generation technology, that is the conditional text generation, including emotional  ...  open research issues and promising research directions should be studied, such as long text generation, multimodal data translation, and lifelong learning.  ... 
arXiv:1909.03409v2 fatcat:s2zfmwxtubgwjks4luoby6vdoq

A Theoretical Model for Meaning Construction through Constructivist Concept Learning [article]

Farshad Badie
2017 The PhD Series of the Faculty of the Humanities  
Educationalists see concept formation as a process by which a person learns to sort specific experiences into general conceptions.  ...  A person who undertakes to learn something and to understand it within a constructivist interaction primarily becomes concerned with various general concepts related to that thing.  ...  The paper has focused on conceptual and logical description of how interactions lead agents to construct their own meaningful understandings based on their constructed meanings (with regard to their personal  ... 
doi:10.5278/ fatcat:sfqwkrjduncrzeuyx2shchxjaq

CaVa: An Example of the Automatic Generation of Virtual Learning Spaces [chapter]

Ricardo G. Martini, Cristiana Araújo, Pedro Rangel Henriques, Maria João Varanda Pereira
2018 Advances in Intelligent Systems and Computing  
The formal description, written in that DSL, will be processed by Cava gen engine to generate the final LS.  ...  A Domain Specific Language (CaVa DSL ) will be used to specify the learning spaces based on that ontology.  ...  To exemplify how to describe an element in CaVa DSL , Listing 3 presents a fragment of a specification to generate the main menu of the "Museum of the Person" Virtual Learning Space.  ... 
doi:10.1007/978-3-319-77703-0_63 fatcat:74rslij7pnfibd3n44xim5cwj4
« Previous Showing results 1 — 15 out of 855,515 results