A New, Fully Automatic Version of Mitkov’s Knowledge-Poor Pronoun Resolution Method

Computational Linguistics and Intelligent Text Processing - Lecture Notes in Computer Science ◽

10.1007/3-540-45715-1_15 ◽

2002 ◽

pp. 168-186 ◽

Cited By ~ 24

Author(s):

Ruslan Mitkov ◽

Richard Evans ◽

Constantin Orasan

Keyword(s):

Resolution Method ◽

Pronoun Resolution ◽

Fully Automatic

Download Full-text

DeepRes: a new deep-learning- and aspect-based local resolution method for electron-microscopy maps

IUCrJ ◽

10.1107/s2052252519011692 ◽

2019 ◽

Vol 6 (6) ◽

pp. 1054-1063 ◽

Cited By ~ 7

Author(s):

Erney Ramírez-Aportela ◽

Javier Mota ◽

Pablo Conesa ◽

Jose Maria Carazo ◽

Carlos Oscar S. Sorzano

Keyword(s):

Electron Microscopy ◽

Deep Learning ◽

Feature Detection ◽

Quality Measure ◽

Human Observer ◽

Resolution Method ◽

Model Based ◽

Local Quality ◽

Fully Automatic

In this article, a method is presented to estimate a new local quality measure for 3D cryoEM maps that adopts the form of a `local resolution' type of information. The algorithm (DeepRes) is based on deep-learning 3D feature detection. DeepRes is fully automatic and parameter-free, and avoids the issues of most current methods, such as their insensitivity to enhancements owing to B-factor sharpening (unless the 3D mask is changed), among others, which is an issue that has been virtually neglected in the cryoEM field until now. In this way, DeepRes can be applied to any map, detecting subtle changes in local quality after applying enhancement processes such as isotropic filters or substantially more complex procedures, such as model-based local sharpening, non-model-based methods or denoising, that may be very difficult to follow using current methods. It performs as a human observer expects. The comparison with traditional local resolution indicators is also addressed.

Download Full-text

A new method of complex structure analysis by electron microscopy

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100110283 ◽

1978 ◽

Vol 36 (1) ◽

pp. 628-629

Author(s):

V.V. Rybin ◽

E.V. Voronina

Keyword(s):

Complex Structure ◽

Reciprocal Lattice ◽

Stacking Faults ◽

Plastic Strains ◽

Base Position ◽

Structural Regularity ◽

Orientation Matrix ◽

Computerized Processing ◽

Fully Automatic ◽

Diffraction Patterns

Recently, it has become essential to develop a helpful method of the complete crystallographic identification of fine fragmented crystals. This was maainly due to the investigation into structural regularity of large plastic strains. The method should be practicable for determining crystallographic orientation (CO) of elastically stressed micro areas of the order of several micron fractions in size and filled with λ>1010 cm-2 density dislocations or stacking faults. The method must provide the misorientation vectors of the adjacent fragments when the angle ω changes from 0 to 180° with the accuracy of 0,3°. The problem is that the actual electron diffraction patterns obtained from fine fragmented crystals are the superpositions of reflections from various fragments, though more than one or two reflections from a fragment are hardly possible. Finally, the method should afford fully automatic computerized processing of the experimental results.The proposed method meets all the above requirements. It implies the construction for a certain base position of the crystal the orientation matrix (0M) A, which gives a single intercorrelation between the coordinates of the unity vector in the reference coordinate system (RCS) and those of the same vector in the crystal reciprocal lattice base : .

Download Full-text