Sequential Labeling With Structural SVM Under Nondecomposable Losses

2018 ◽  
Vol 29 (9) ◽  
pp. 4177-4188 ◽  
Author(s):  
Guopeng Zhang ◽  
Massimo Piccardi ◽  
Ehsan Zare Borzeshi
Keyword(s):  
Structural Svm ◽  
Sequential Labeling

scholarly journals Partial characterization of the shift from IgG to IgA synthesis in the clonal differentiation of human leukemic bone marrow-derived lymphocytes.

1975 ◽  
Vol 142 (3) ◽  
pp. 549-559 ◽  
Author(s):  
R A Rudders ◽  
R Ross
Keyword(s):  
B Cell ◽  
B Lymphocyte ◽  
Plasma Cells ◽  
Lymphocytic Leukemia ◽  
B Cell Differentiation ◽  
Cell Staining ◽  
Clonal Origin ◽  
Switch Mechanism ◽  
Sequential Labeling ◽  
Chain Synthesis

An unusual B-cell proliferation was noted in an individual (Tun) which was characterized by the presence of two separate populations of chronic lymphocytic leukemia (CLL) cell staining on the surface and in the cytoplasm for either IgG(k) or IgA(k). Utilizing an idiotypic antiserum prepared from the associated serum monoclonal IgG(k) protein the idiotype was detected on the surface and in the cytoplasm of both the IgG- and IgA-bearing cell populations. These observations are consistent with a common clonal origin and a switch mechanism involving IgG and IgA synthesis. Sequential-labeling of Surface Ig and intracellular Ig with antisera conjugated to opposite fluorochromes documented the progressive maturation of the terminal differentiation of the IgA-bearing cell population at a level before morphologically distinct plasma cells. The distribution and pattern of surface and cytoplasmic IgG and IgA staining in individual cells suggest that the direction of switching is from IgG to IgA synthesis. The demonstration of shared idiotypic specificity between the IgG- and IgA-bearing populations is consistent with a transition in Ig heavy chain synthesis resulting from an alternation in the CH gene. It is concluded that certain CLL clones may manifest a switch from IgG to IgA synthesis at a level of B-cell differentiation which encompasses both the B lymphocyte and the Ig-synthesizing plasma cell.

Volume-Referent Bone Turnover Estimated From the Interlabel Area Fraction After Sequential Labeling

Bone ◽  
1998 ◽  
Vol 22 (6) ◽  
pp. 677-682 ◽  
Author(s):  
T Frisch ◽  
M.S Sørensen ◽  
S Overgaard ◽  
M Lind ◽  
P Bretlau
Keyword(s):  
Bone Turnover ◽  
Area Fraction ◽  
Sequential Labeling

scholarly journals A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

2020 ◽  
Vol 34 (05) ◽  
pp. 9098-9105
Author(s):  
Amir Veyseh ◽  
Franck Dernoncourt ◽  
Dejing Dou ◽  
Thien Nguyen
Keyword(s):  
Prior Work ◽  
Semantic Consistency ◽  
Learning Framework ◽  
Local Structures ◽  
Joint Inference ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Sequential Labeling ◽  
Sentence Classification ◽  
Model Features

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.1

Sign in / Sign up

Export Citation Format

Share Document