Seong-Bae Park

In this research article, we study the problem of employing a neural machine translation model to translate Arabic dialects to modern standard Arabic. The proposed solution of the neural machine translation model is prompted by the recurrent neural network-based encoder-decoder neural machine translation model that has been proposed recently, which generalizes machine translation as sequence learning problems. We propose the development of a multiytask learning (MTL) model which shares one decod

This paper proposes a hybrid of hand-crafted rules and a machine learning method for chunking Korean. In the partially free word-order languages such as Korean and Japanese, a small number of rules dominate the performance due to their well-developed postpositions and endings. Thus, the proposed method is primarily based on the rules, and then the residual errors are corrected by adopting a memory-based machine learning method. Since the memory-based learning is an efficient method to handle exc

This paper proposes a novel method to compute how similar two program source codes are. Since a program source code is represented as a structural form, the proposed method adopts convolution kernel functions as a similarity measure. Actually, a program source code has two kinds of structural information. One is syntactic information and the other is the dependencies of function calls lying on the program. Since the syntactic information of a program is expressed as its parse tree, the syntactic

Aspect-based sentiment analysis (ABSA) is the task of classifying the sentiment of a specific aspect in a text. Because a single text usually has multiple aspects which are expressed independently, ABSA is a crucial task for in-depth opinion mining. A key point of solving ABSA is to align sentiment expressions with their proper target aspect in a text. Thus, many recent neural models have applied attention mechanisms to learning the alignment. However, it is problematic to depend solely on atten

The performance of Very Long Instruction Word (VLIW) microprocessors depends on the close cooperation between the compiler and the architecture. This paper evaluates a set of important compilation techniques and related architectural features for VLIW machines. The evaluation is performed on a SPARC-based VLIW testbed where gcc-generated optimized SPARC code is scheduled into high-performance VLIW code. As a base scheduling compiler, we experiment with three core scheduling techniques including

Translation-based knowledge graph embeddings learn vector representations of entities and relations by treating relations as translation operators over the entities in an embedding space. Since the translation is represented through a score function, translation-based embeddings are trained in general by minimizing a margin-based ranking loss, which assigns a low score to positive triples and a high score to negative triples. However, this type of embedding suffers from slow convergence and poor

Most corpus-based approaches to natural language processing suffer from lack of training data. This is because acquiring a large number of labeled data is expensive. This paper describes a learning method that exploits unlabeled data to tackle data sparseness problem. The method uses committee learning to predict the labels of unlabeled data that augment the existing training data. Our experiments on word sense disambiguation show that predictive accuracy is significantly improved by using addit

Knowledge bases such as Freebase, YAGO, DBPedia, and Nell contain a number of facts with various entities and relations. Since they store many facts, they are regarded as core resources for many natural language processing tasks. Nevertheless, they are not normally complete and have many missing facts. Such missing facts keep them from being used in diverse applications in spite of their usefulness. Therefore, it is significant to complete knowledge bases. Knowledge graph embedding is one of the

Most natural language processing tasks depend on the outputs of some other tasks. Thus, they involve other tasks as subtasks. The main problem of this type of pipelined model is that the optimality of the subtasks that are trained with their own data is not guaranteed in the final target task, since the subtasks are not optimized with respect to the target task. As a solution to this problem, this paper proposes a consolidation of subtasks for a target task (CST2). In CST2, all parameters of a t