scholarly journals First U-Net Layers Contain More Domain Specific Information Than the Last Ones

2020 ◽  
pp. 117-126
Author(s):  
Boris Shirokikh ◽  
Ivan Zakazov ◽  
Alexey Chernyavskiy ◽  
Irina Fedulova ◽  
Mikhail Belyaev
Keyword(s):  
Specific Information ◽  
Domain Specific

Knowledge Enhanced LSTM for Coreference Resolution on Biomedical Texts

2021 ◽  
Author(s):  
Yufei Li ◽  
Xiaoyong Ma ◽  
Xiangyu Zhou ◽  
Pengzhen Cheng ◽  
Kai He ◽  
...  
Keyword(s):  
Information Integration ◽  
Short Term Memory ◽  
Superior Performance ◽  
Supplementary Information ◽  
Specific Information ◽  
Coreference Resolution ◽  
Fine Grained ◽  
Domain Specific ◽  
Memory Network ◽  
Biomedical Texts

Abstract Motivation Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events’ attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information. Results In this paper, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences. Supplementary information Supplementary data are available at Bioinformatics online.

PROTEIN STRUCTURE ALIGNMENT AND FAST SIMILARITY SEARCH USING LOCAL SHAPE SIGNATURES

2004 ◽  
Vol 02 (01) ◽  
pp. 215-239 ◽  
Author(s):  
TOLGA CAN ◽  
YUAN-FANG WANG
Keyword(s):  
Protein Structure ◽  
Protein Structures ◽  
Structure Alignment ◽  
Protein Structure Alignment ◽  
Specific Information ◽  
Alignment Algorithm ◽  
Screening Process ◽  
Domain Specific ◽  
Local Sequence ◽  
Shape Signatures

We present a new method for conducting protein structure similarity searches, which improves on the efficiency of some existing techniques. Our method is grounded in the theory of differential geometry on 3D space curve matching. We generate shape signatures for proteins that are invariant, localized, robust, compact, and biologically meaningful. The invariancy of the shape signatures allows us to improve similarity searching efficiency by adopting a hierarchical coarse-to-fine strategy. We index the shape signatures using an efficient hashing-based technique. With the help of this technique we screen out unlikely candidates and perform detailed pairwise alignments only for a small number of candidates that survive the screening process. Contrary to other hashing based techniques, our technique employs domain specific information (not just geometric information) in constructing the hash key, and hence, is more tuned to the domain of biology. Furthermore, the invariancy, localization, and compactness of the shape signatures allow us to utilize a well-known local sequence alignment algorithm for aligning two protein structures. One measure of the efficacy of the proposed technique is that we were able to perform structure alignment queries 36 times faster (on the average) than a well-known method while keeping the quality of the query results at an approximately similar level.

scholarly journals DISSECT: DISentangle SharablE ConTent for Multimodal Integration and Crosswise-mapping

2020 ◽  
Author(s):  
Geoffrey Schau ◽  
Erik Burlingame ◽  
Young Hwan Chang
Keyword(s):  
Deep Learning ◽  
Complete Information ◽  
Specific Information ◽  
Multimodal Integration ◽  
Specific Data ◽  
Domain Specific ◽  
Cross Domain ◽  
Input Feature ◽  
Novel Approach ◽  
Latent Representations

AbstractDeep learning systems have emerged as powerful mechanisms for learning domain translation models. However, in many cases, complete information in one domain is assumed to be necessary for sufficient cross-domain prediction. In this work, we motivate a formal justification for domain-specific information separation in a simple linear case and illustrate that a self-supervised approach enables domain translation between data domains while filtering out domain-specific data features. We introduce a novel approach to identify domainspecific information from sets of unpaired measurements in complementary data domains by considering a deep learning cross-domain autoencoder architecture designed to learn shared latent representations of data while enabling domain translation. We introduce an orthogonal gate block designed to enforce orthogonality of input feature sets by explicitly removing non-sharable information specific to each domain and illustrate separability of domain-specific information on a toy dataset.

scholarly journals Measuring Models

2009 ◽  
pp. 147-169 ◽  
Author(s):  
Martin Monperrus ◽  
Jean-Marc Jézéquel ◽  
Joël Champeau ◽  
Brigitte Hoeltzener
Keyword(s):  
Quality Assurance ◽  
Software Development ◽  
Point Of View ◽  
Specific Information ◽  
Model Driven Engineering ◽  
Text Documents ◽  
Model Driven ◽  
Domain Specific ◽  
Wide Range

Model-Driven Engineering (MDE) is an approach to software development that uses models as primary artifacts, from which code, documentation and tests are derived. One way of assessing quality assurance in a given domain is to define domain metrics. We show that some of these metrics are supported by models. As text documents, models can be considered from a syntactic point of view i.e., thought of as graphs. We can readily apply graph-based metrics to them, such as the number of nodes, the number of edges or the fan-in/fan-out distributions. However, these metrics cannot leverage the semantic structuring enforced by each specific metamodel to give domain specific information. Contrary to graph-based metrics, more specific metrics do exist for given domains (such as LOC for programs), but they lack genericity. Our contribution is to propose one metric, called s, that is generic over metamodels and allows the easy specification of an open-ended wide range of model metrics.

scholarly journals The Repository Chemotion: Infrastructure for Sustainable Research in Chemistry

2020 ◽  
Author(s):  
Pierre Tremouilhac ◽  
Chia-Lin Lin ◽  
Pei-Chi Huang ◽  
Yu-Chieh Huang ◽  
An Nguyen ◽  
...  
Keyword(s):  
Analytical Data ◽  
Research Data ◽  
Digital Object Identifier ◽  
Specific Information ◽  
Data Infrastructure ◽  
Domain Specific ◽  
Chemistry Research ◽  
Peer Reviewing ◽  
Institute Of Technology ◽  
New Community

<p>We describe the development of a repository for chemistry research data (called Chemotion) that provides solutions for current challenges to store research data in a feasible manner, allowing the conservation of domain specific information in a machine readable format. A main advantage of the repository Chemotion is the comprehensive functionality, which offers options to collect, prepare and reuse data using discipline specific methods and data processing tools. For selected analytical data, automated procedures are implemented to facilitate the curation of the data. Chemotion provides functions to facilitate the publishing process of data and the citation of the deposited data. It supports automated Digital Object Identifier (DOI) generation, the comparison of the submissions with PubChem instances, and workflows for peer reviewing of the submissions including embargo settings. The described developments were used to establish a research data infrastructure that is hosted at the Karlsruhe Institute of Technology (KIT), including the necessary storage and support to build a new community-driven repository as a comprehensive alternative to commercial databases. </p>

Enabling the Matchmaking of Organizations and Public Procurement Notices by Means of Linked Open Data

2013 ◽  
pp. 105-131 ◽  
Author(s):  
Jose María Alvarez Rodríguez ◽  
José Emilio Labra Gayo ◽  
Patricia Ordoñez de Pablos
Keyword(s):  
Semantic Web ◽  
Linked Data ◽  
Public Procurement ◽  
Open Data ◽  
Specific Information ◽  
Semantic Web Technologies ◽  
Web Technologies ◽  
Domain Specific ◽  
The Status ◽  
Financial Transactions

The aim of this chapter is to present a proposal and a case study to describe the information about organizations in a standard way using the Linked Data approach. Several models and ontologies have been provided in order to formalize the data, structure and behaviour of organizations. Nevertheless, these tries have not been fully accepted due to some factors: (1) missing pieces to define the status of the organization; (2) tangled parts to specify the structure (concepts and relations) between the elements of the organization; 3) lack of text properties, and other factors. These divergences imply a set of incomplete approaches to formalize data and information about organizations. Taking into account the current trends of applying semantic web technologies and linked data to formalize, aggregate, and share domain specific information, a new model for organizations taking advantage of these initiatives is required in order to overcome existing barriers and exploit the corporate information in a standard way. This work is especially relevant in some senses to: (1) unify existing models to provide a common specification; (2) apply semantic web technologies and the Linked Data approach; (3) provide access to the information via standard protocols, and (4) offer new services that can exploit this information to trace the evolution and behaviour of the organization over time. Finally, this work is interesting to improve the clarity and transparency of some scenarios in which organizations play a key role, like e-procurement, e-health, or financial transactions.

Sign in / Sign up

Export Citation Format

Share Document