Supervised machine learning methods have been widely used in relation extraction that finds the relation between two named entities in a sentence. However, their disadvantages are that constructing training data is a cost and time consuming job, and the machine learning system is dependent on the domain of the training data. To overcome these disadvantages, we construct a weakly labeled data se...

PURPOSE Our study is to confirm that hemoglobin (Hb) level is significantly reduced before operation in elderly patients with hip fracture and to specify potential amounts of bleeding and Hb decline in different types of fractures. METHODS A prospective analysis was made on the clinical data of 349 patients with both a diagnosis of hip fracture and an operative delay of greater than 72 hours ...

The direct measurement of wall shear stress in turbulent boundary layers (TBL) is challenging, therefore, requiring it to be indirectly determined from mean profile measurements. Most popular methods assume the streamwise velocity satisfy either a logarithmic law inner layer or composite with many tuned constants for entire TBL, both which require reliable data layer. presence roughness and pre...

Three new isostructural lanthanide coordination polymers {[Ln(L)2·2H2O]·Cl·4H2O}, Ln = La (LaL 1), Tb (TbL 2), Eu (EuL 3), L = 4-carboxy-1-(4-carboxybenzyl)pyridinium, have been synthesized under hydrothermal conditions and characterized by single crystal X-ray diffraction, IR, TG, PXRD, and luminescence. The solid-state luminescence properties of those Ln-CPs were investigated, realizing the z...

The paper presents a method to perform direct numerical simulations (DNS) of a jet actuator flow inside a turbulent flat plate boundary layer (TBL). A structured finite difference method is used for the simulations. The numerical scheme is adapted to account for the large scale differences both in geometric and fluid dynamic aspect. Analytical mesh transformations have been implemented to resol...

Entropy Guided Transformation Learning (ETL) is a new machine learning strategy that combines the advantages of decision trees (DT) and Transformation Based Learning (TBL). In this work, we apply the ETL framework to four phrase chunking tasks: Portuguese noun phrase chunking, English base noun phrase chunking, English text chunking and Hindi text chunking. In all four tasks, ETL shows better r...

We present a universal approach to uncover and correct systematic local errors in complex speech-to-text systems. Whereas previous work to minimize speech recognition errors mostly relies on N-best lists or word lattices, our approach is merely based on the first-best system output. The paradigm of Transformation-Based Learning (TBL) is adapted from tagging-like applications to themore complica...

For the task of recognizing dialogue acts, we are applying the Transformation-Based Learning (TBL) machine learning algorithm. To circumvent a sparse data problem, we extract values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which we find to be more effective than cue phrases and word n-grams in practice. ...