We deal with embedding a large scale knowledge graph composed of entities and relations into a continuous vector space. TransE is a promising method proposed recently, which is very efficient while achieving state-of-the-art predictive performance. We discuss some mapping properties of relations which should be considered in embedding, such as reflexive, one-to-many, many-to-one, and many-to-ma...

This work presents a grapheme-based approach of English-to-Chinese (E2C) transliteration, which consists of many-to-many (M2M) alignment and conditional random fields (CRF) using accessor variety (AV) as an additional feature to approximate local context of source graphemes. Experiment results show that the AV of a given English named entity generally improves effectiveness of E2C transliteration.

Learning Decompositional Shape Models from Examples Alex Levinshtein Master of Science Graduate Department of Computer Science University of Toronto 2005 We present an algorithm for automatically constructing a decompositional shape model from examples. Unlike current approaches to structural model acquisition, in which one-to-one correspondences among appearance-based features are used to cons...

this study compared the use of five different models to describe the growth from birth to 20 weeks of age of kids from both genders of nondescript goats. fifty nine (59) nondescript kids were weighed weekly at the university of maiduguri livestock teaching and research farm, nigeria and the live weights were modeled. biologically relevant variables were estimated for each kid from the logistic,...

Even though tree-based reliable multicast protocols are known to be most scalable for one-to-many sessions, there is still an open question whether these protocols are also scalable for many-to-many sessions. We analyze and compare two promising multicast protocols-the receiver-initiated protocol with NACK suppression and the tree-based protocol-using a new spatial loss model. The proposed mode...

Multiplayer perceptrons or feed-forward networks are generally trained to represent functions or many-to-one (m-o) mappings. This creates a problem if the training data exhibits the property of many-to-many or almost many-many valued-ness because the model, which generated the data, was many-to-many. Therefore in this paper a modified feed-forward network and training algorithm is considered to...