Filters








8,171 Hits in 5.7 sec

How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction [article]

Zikun Hu, Yixin Cao, Lifu Huang, Tat-Seng Chua
2021 arXiv   pre-print
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).  ...  Knowledge Graph (KG) and attention mechanism have been demonstrated effective in introducing and selecting useful information for weakly supervised methods.  ...  This work is partially supported by A*STAR through the Industry Alignment Fund -Industry Collaboration Projects Grant, by NTU (NTU-ACE2020-01) and Ministry of Education (RG96/20), and by the National Research  ... 
arXiv:2107.12064v1 fatcat:b5r7ft5ryjb2xgusih3cdvjasu

How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction

Zikun Hu, Yixin Cao, Lifu Huang, Tat-Seng Chua
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).  ...  Knowledge Graph (KG) and attention mechanism have been demonstrated effective in introducing and selecting useful information for weakly supervised methods.  ...  This work is partially supported by A*STAR through the Industry Alignment Fund -Industry Collaboration Projects Grant, by NTU (NTU-ACE2020-01) and Ministry of Education (RG96/20), and by the National Research  ... 
doi:10.18653/v1/2021.acl-long.359 fatcat:xjzspjlzfbg65e4rcj6t5ag3dq

Does deep learning help topic extraction? A kernel k-means clustering method with word embedding

Yi Zhang, Jie Lu, Feng Liu, Qian Liu, Alan Porter, Hongshu Chen, Guangquan Zhang
2018 Journal of Informetrics  
Additionally, this empirical analysis reveals insights into both overlapping and diverse research interests among the three journals that would benefit journal publishers, editorial boards, and research  ...  An empirical study on bibliometric topic extraction from articles published by three top-tier bibliometric journals between 2000 and 2017, supported by expert knowledge-based evaluations, provides supplemental  ...  Acknowledgements We acknowledge Arho Suominen and Ying Huang for their efforts in the pre-round expert knowledge-based evaluation, and our heartfelt appreciation goes to Lutz Bornmann, Kevin Boyack, Andrea  ... 
doi:10.1016/j.joi.2018.09.004 fatcat:t75tldepafcxrptzk5s2jc26ki

Predicting the Helpfulness Score of Product Reviews Using an Evidential Score Fusion Method

Fatemeh Fouladfar, Mohammad Naderi Dehkordi, Mohammad Ehsan Basiri
2020 IEEE Access  
This article presents a new model for specifying the usefulness of comments using the textual features extracted from the reviews.  ...  Various types of features including emotion-related, linguistic and text-related features, valence, arousal, and dominance (VAD) values, review-length and polarity of comments are exploited in this study  ...  of VAD and text-related features have better helpfulness recognition ability.  ... 
doi:10.1109/access.2020.2988872 fatcat:4wernhazpnbmnomiiahgzebfhu

Leveraging Domain Context for Question Answering Over Knowledge Graph

Peihao Tong, Qifan Zhang, Junjie Yao
2019 Data Science and Engineering  
., meta-paths within the targeting knowledge graph. On top of these, we design a cross-attention mechanism to improve the question and answer matching performance.  ...  With the growing availability of different knowledge graphs in a variety of domains, question answering over knowledge graph (KG-QA) becomes a prevalent information retrieval approach.  ...  reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s41019-019-00109-w fatcat:eqymus5u2jg5pkllu6kldi3gk4

A Survey on Graph-Based Deep Learning for Computational Histopathology [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
As such, graph data representations and deep learning have attracted significant attention for encoding tissue representations, and capturing intra- and inter- entity level interactions.  ...  In this review, we provide a conceptual grounding for graph analytics in digital pathology, including entity-graph construction and graph architectures, and present their current success for tumor localization  ...  extraction and selection is conducted followed by a bag-level classification.  ... 
arXiv:2107.00272v2 fatcat:3eskkeref5ccniqsjgo3hqv2sa

Improving Distant Supervised Relation Extraction by Dynamic Neural Network [article]

Yanjie Gou, Yinjie Lei, Lingqiao Liu, Pingping Zhang, Xi Peng
2019 arXiv   pre-print
Distant Supervised Relation Extraction (DSRE) is usually formulated as a problem of classifying a bag of sentences that contain two query entities, into the predefined relation classes.  ...  To unify these two arguments, we developed a novel Dynamic Neural Network for Relation Extraction (DNNRE).  ...  Acknowledgment This work was supported by the Key Research and Development Program of Sichuan Province (2019YFG0409).  ... 
arXiv:1911.06489v2 fatcat:hl4ovrxnhja55dzwk3ehjifgyi

Enriching semantic knowledge bases for opinion mining in big data applications

A. Weichselbraun, S. Gindl, A. Scharl
2014 Knowledge-Based Systems  
This paper presents a novel method for contextualizing and enriching large semantic knowledge bases for opinion mining with a focus on Web intelligence platforms and other high-throughput big data applications  ...  A quantitative evaluation shows a significant improvement when using an enriched version of SenticNet for polarity classification.  ...  ERA-NET, and the COMET Project (www.htwchur.ch/ comet), funded by the Swiss Commission for Technology and Innovation (CTI).  ... 
doi:10.1016/j.knosys.2014.04.039 pmid:25431524 pmcid:PMC4235782 fatcat:k7rcec6qeja6rkkjuou7z7g6si

Semantic Relations and Deep Learning [article]

Vivi Nastase, Stan Szpakowicz
2021 arXiv   pre-print
A new Chapter 5 of the book, by Vivi Nastase and Stan Szpakowicz, discusses relation classification/extraction in the deep-learning paradigm which arose after the first edition appeared.  ...  The second edition of "Semantic Relations Between Nominals" by Vivi Nastase, Stan Szpakowicz, Preslav Nakov and Diarmuid \'O S\'eaghdha has been published in April 2021 by Morgan & Claypool (www.morganclaypoolpublishers.com  ...  Bags which share a relation label are assembled into a bag group. An attention mechanism helps weight sentences for the construction of the bag representation.  ... 
arXiv:2009.05426v4 fatcat:rmzoalfwcza4nex7pd4u6w7kbe

Anticipating Stock Market of the Renowned Companies: A Knowledge Graph Approach

Yang Liu, Qingguo Zeng, Joaquín Ordieres Meré, Huanrui Yang
2019 Complexity  
Our work highlights the usefulness of knowledge graph in implementing business activities and helping practitioners and managers make business decisions.  ...  that uses only stock data, a bag-of-words method, and convolutional neural network.  ...  Applying our model on the basis of knowledge graph on customers helps organize all relevant knowledge fragments through deep semantic analysis and reasoning, which can be verified with a customer's bank  ... 
doi:10.1155/2019/9202457 fatcat:gissfef7ijdupd33xufrihbmby

MetaMIML: Meta Multi-Instance Multi-Label Learning [article]

Yuanlin Yang, Guoxian Yu, Jun Wang, Lei Liu, Carlotta Domeniconi, Maozu Guo
2021 arXiv   pre-print
Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances.  ...  MetaMIML introduces the context learner with network embedding to capture semantic information of objects of different types, and the task learner to extract the meta knowledge for fast adapting to new  ...  Next, the task-wise can be adapted by the global prior knowledge ω and attention based ω i , which help predicting the labels of bags.  ... 
arXiv:2111.04112v1 fatcat:rnugpdpl5vdpfn3zhnvyckhwyu

Discriminative Latent Semantic Graph for Video Captioning [article]

Yang Bai, Junyan Wang, Yang Long, Bingzhang Hu, Yang Song, Maurice Pagnucco, Yu Guan
2021 arXiv   pre-print
information into latent object proposal. 2) Visual Knowledge: Latent Proposal Aggregation is proposed to dynamically extract visual words with higher semantic levels. 3) Sentence Validation: A novel Discriminative  ...  Our main contribution is to identify three key problems in a joint framework for future video summarization tasks. 1) Enhanced Object Proposal: we propose a novel Conditional Graph that can fuse spatio-temporal  ...  Second, how to extract visual knowledge from enhanced object proposals shares the same spirit of the traditional Bag-of-Visual-Words (BoVW) paradigm.  ... 
arXiv:2108.03662v1 fatcat:6okzuqntjngcvl7cndxybjnjje

Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks [article]

Peng Cui, Le Hu, Yuanchao Liu
2020 arXiv   pre-print
To address these issues, this paper proposes a graph neural network (GNN)-based extractive summarization model, enabling to capture inter-sentence relationships efficiently via graph-structured document  ...  Extractive approaches are widely used in text summarization because of their fluency and efficiency.  ...  We thank anonymous reviewers for their helpful comments on various aspects of this work.  ... 
arXiv:2010.06253v1 fatcat:kxlj4h2cszhcvh3uis5vlfs7ni

End-to-End Video Classification with Knowledge Graphs [article]

Fang Yuan, Zhe Wang, Jie Lin, Luis Fernando D'Haro, Kim Jung Jae, Zeng Zeng, Vijay Chandrasekhar
2017 arXiv   pre-print
We first observe that there exists a significant knowledge gap between how machines and humans learn.  ...  In particular, we unify traditional "knowledgeless" machine learning models and knowledge graphs in a novel end-to-end framework.  ...  As future work, we plan to extract features from knowledge graphs and directly incorporate them into the deep neural networks.  ... 
arXiv:1711.01714v1 fatcat:kfo5ixo44ne3lezk7ztkkc34lq

Argumentative Relation Classification with Background Knowledge

Debjit Paul, Juri Opitz, Maria Becker, Jonathan Kobbe, Graeme Hirst, Anette Frank
2020 Computational Models of Argument  
This knowledge is integrated into a neural argumentative relation classifier via an attention-based gating mechanism.  ...  In this paper, we propose an unsupervised graph-based ranking method that extracts relevant multi-hop knowledge from a background knowledge resource.  ...  Our contributions are: (i) We show that our graph-based method that extracts relevant commonsense knowledge and selectively integrates it into the model improves over a strong neural and a linear argumentative  ... 
doi:10.3233/faia200515 dblp:conf/comma/PaulOBKHF20 fatcat:n2wqqkaoynalpn6dcxtlr4mw3m
« Previous Showing results 1 — 15 out of 8,171 results