Filters








15 Hits in 4.2 sec

Open IE-Triples Inference - Corpora Development and DNN Architectures

Martin Víta, Petr Škoda
2020 Proceedings of the 2020 Federated Conference on Computer Science and Information Systems  
We investigate several DNN siamese architectures for this task and this particular corresponding corpus. We set several baselines including hypothesis only baseline.  ...  We subsequently introduce a novel relation inference corpus obtained from a well known SNLI corpus and provide its brief characterization.  ...  CORE WORK: OPEN IE-TRIPLES INFERENCE TASK In this section, we state a new task of open IE-triples inference.  ... 
doi:10.15439/2020f78 dblp:conf/fedcsis/Vita020 fatcat:zz6cd3xfazdgnbbl5poaczttka

From Building Corpora for Recognizing Faceted Entailment to Recognizing Relational Entailment

Martin Víta
2018 Position Papers of the 2018 Federated Conference on Computer Science and Information Systems  
In this paper, we present a semi-automatic approach to deriving corpora for faceted entailment task from a general RTE corpus using open information extraction (open IE) tools.  ...  As a generalization of this approach and general principles of open IE, we introduce a notion of relational entailment and provide its basic properties and relations to other entailmentlike issues.  ...  ", an open IE system (open information extractor) should extract a textual triple (FedCSIS, took place in, Prague).  ... 
doi:10.15439/2018f381 dblp:conf/fedcsis/Vita18 fatcat:saqx3kivbvhqtjzcszxq5deb4a

Deep Neural Network Based Relation Extraction: An Overview [article]

Hailin Wang, Ke Qin, Rufai Yusuf Zakari, Guoming Lu, Jin Yin
2021 arXiv   pre-print
and distant supervision RE, which adopts DNNs to design sentence encoder and de-noise method.  ...  Especially, the supervised and distant supervision methods based on DNNs are the most popular and reliable solutions for RE.  ...  U19A2059), and by Ministry of Science and Technology of Sichuan Province Program (NO.2021YFG0018&No.20ZDYF0343). We sincerely thank Mr.  ... 
arXiv:2101.01907v2 fatcat:o23huhxnhjfmrk4x3gvgpnbbm4

AutoRC: Improving BERT Based Relation Classification Models via Architecture Search [article]

Wei Zhu, Xipeng Qiu, Yuan Ni, Guotong Xie
2020 arXiv   pre-print
Experiments on seven benchmark RC tasks show that our method is efficient and effective in finding better architectures than the baseline BERT based RC model.  ...  In this work, we design a comprehensive search space for BERT based RC models and employ neural architecture search (NAS) method to automatically discover the design choices mentioned above.  ...  ., 2019; Wu and He, 2019; Eberts and Ulges, 2019; Peng et al., 2019) , and shows significant improvements over the traditional DNN models.  ... 
arXiv:2009.10680v2 fatcat:dclij7hpprgvnlbeqpf7fjnnka

Seq2seq Translation Model for Sequential Recommendation [article]

Ke Sun, Tieyun Qian
2020 arXiv   pre-print
Taking the category information as an item's context, we develop a basic coupled and an extended tripled seq2seq translation models to encode the category-item and item-category-item relations between  ...  the item and context sequences.  ...  ACKNOWLEDGMENTS The work described in this paper has been supported in part by the NSFC projects (61572376, 91646206), and the 111 project(B07037).  ... 
arXiv:1912.07274v2 fatcat:k4kmbpgpfvbexo375winub5ega

Low-Resource Adaptation of Neural NLP Models [article]

Farhad Nooralahzadeh
2020 arXiv   pre-print
We develop and adapt neural NLP models to explore a number of research questions concerning NLP tasks with minimal or no training data.  ...  It is challenging to find annotated data of sufficient amount and quality.  ...  ., and Dyer, C. (2016) . "Neural Architectures for Named Entity Recognition".  ... 
arXiv:2011.04372v1 fatcat:626mbe5ba5bkdflv755o35u5pq

Energy-Efficient Speaker Identification with Low-Precision Networks

Skanda Koppula, James Glass, Anantha P. Chandrakasan
2018 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Finally, Figure 3-4 describes the micro-architecture of the individual units the comprise the inference module.  ...  of non-DNN based works have studied SID in low-resourceFPGA and embedded settings.  ... 
doi:10.1109/icassp.2018.8462498 dblp:conf/icassp/KoppulaGC18 fatcat:drfa4prtknffljedgyqtquxkdm

Deep Spoken Keyword Spotting: An Overview

Ivan Lopez-Espejo, Zheng-Hua Tan, John Hansen, Jesper Jensen
2021 IEEE Access  
GOOGLE SPEECH COMMANDS DATASET 14 Many of these corpora also include a development set.  ...  speech: Developmental changes of temporal and spectral parameters,” [203] H.-G.  ... 
doi:10.1109/access.2021.3139508 fatcat:i4pfpfxcpretlkbefp7owtxcti

The EVALITA Dependency Parsing Task: From 2007 to 2011 [chapter]

Cristina Bosco, Alessandro Mazzei
2013 Lecture Notes in Computer Science  
EVALITA's shared tasks are aimed at contributing to the development and dissemination of natural language resources and technologies by proposing a shared context for training and evaluation.  ...  the analysis of written and spoken language respectively.  ...  Acknowledgment The project has been developed by the audio team of Multimedia Assistive Technology Laboratory (MATeLab) at the Università Politecnica delle Marche, which operates in the ambient assisted  ... 
doi:10.1007/978-3-642-35828-9_1 fatcat:p6dyjaxm4zbitfajtciwclwipu

Towards Neural Information Extraction without Manual Annotated Data

Peng Xu
2018
In the first part of the thesis, we focus on one IE task -fine-grained entity type classification (FETC) and propose the NFETC model -a single, much simpler and more elegant neural network model that attempts  ...  IE tasks which are particularly suited for this setting.  ...  This observation indicates that the strategies that combine representations at inference time is not effective anymore due to the recent development in areas of both KBE and relation extraction.  ... 
doi:10.7939/r3g44j63v fatcat:olkj4cbd5vecblax2onbkewpcm

Visualising Italian Language Resources: a Snapshot [chapter]

Riccardo Del Gratta, Francesca Frontini, Monica Monachini, Gabriella Pardelli, Irene Russo, Roberto Bartolini, Sara Goggi, Fahad Khan, Valeria Quochi, Claudia Soria, Nicoletta Calzolari
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015  
and creation of a dictionary, n. 20105B3HE8), funded by the Italian Ministry of Education, University and Research (MIUR). http://combinet.humnet. unipi.it.  ...  Acknowledgments This work has been partially supported by the EC project CogNet, 671625 (H2020-ICT-2014-2, Research and Innovation action) and by an IBM Faculty Award.  ...  Our DNN model for NER In this section, we first briefly describe the architecture of the Context Window Network (CWN) from Collobert et al. (2011) , pointing out its limitation.  ... 
doi:10.4000/books.aaccademia.1442 fatcat:2gywsrwxgravrdrgprh2l25eo4

Feature Interactions: The Next Generation

Sven Apel, Joanne Atlee, Luciano Baresi, Pamela Zave, Abraham Bernstein, Jan Leimeister, Natasha Noy, Cristina Sarasua, Elena Simperl, Dirk Kutscher, Taekyoung Kwon, Ignacio Solis (+8 others)
2014 unpublished
We agreed to develop a web site with resources on this subject. Büchler has set up the basic infrastructure for this and we will begin to populate it as we experiment with teaching EBD.  ...  Berendt has shared her materials and other plan to as they experiment with teaching EBD. 4 We discussed the development of an infographic that makes the case for the importance of ethics in big data.  ...  The latter is produced by two different systems developed in this project: the first one without prior knowledge [3] , the second one with GMM and DNN with very good results.  ... 
fatcat:yocgka4htzazrj4flboybykc44

Electronic Markets and Auctions (Dagstuhl Seminar 13461) Computational Models of Language Meaning in Context (Dagstuhl Seminar 13462) Synchronous Programming (Dagstuhl Seminar 13471) Global Measurement Framework (Dagstuhl Seminar 13472) Unleashing Operational Process Mining (Dagstuhl Seminar 13481) Forensic Computing (Dagstuhl Seminar 13482)

Saul Greenberg, Kasper Hornbaek, Aaron Quigley, Harald Reiterer, Roman, Yishay Mansour, Benny Moldovanu, Noam Nisan, Berthold, Hans Kamp, Alessandro Lenci, James (+14 others)
2013 unpublished
However, it still remains an open research area and its place in HCI needs to be better understood. Acknowledgements.  ...  Two EC FP7 research projects, Leone and mPlane, kindly supported the social event of the seminar.  ...  The research activities are mainly focused on the following subjects ranging from Service-oriented Architectures to Knowledge Management over Open Source Development Paradigms and Security.  ... 
fatcat:fl5xhx4dpbeklg6o6xhmuvuety

Intelligent Prediction of Stock Market Using Text and Data Mining Techniques [article]

Mohammad Raahemi, University, My
2020
The objective of this research is to use text mining and data mining techniques to discover the relationship between news articles and stock prices fluctuations.  ...  After preprocessing the data, including labeling and balancing the data, we build five predictive models, namely Neural Networks, SVM, Decision Tree, KNN, and Random Forest to predict stock movements (  ...  direction of price movement as the future price (57.1% directional accuracy) and the highest return using a simulated trading engine (2.06% return Thus, using Open Knowledge Extraction (Open IE) to obtain  ... 
doi:10.20381/ruor-25160 fatcat:2e4wotwhnrd2lfwqwuwzvatybu

Multimodal Legal Information Retrieval

Kolawole John Adebayo
2018
One of the goals of this thesis is to develop a DNN-based classifier for the E-Discovery task as a form of technology-assisted review.  ...  Specifically, the focus has been on Information Extraction (IE) rather than IR.  ... 
doi:10.6092/unibo/amsdottorato/8634 fatcat:afij2o54njfe7cqwgpdzyvioba