• Improving Distributional Similarity with Lessons Learned from Wrod Embeddings

    WHY? Word embedding using neural network(Skipgram) seems to outperform traditional count-based distributional model. However, this paper points out that current superiority of word2vec is not because of the algorithm itself, but because of system design choices and hyperparameter optimizations. Note Traditional method of word representation is count-based representation (bag-of-contexts). This...


  • Hadamard Product for Low-rank Bilinear Pooling

    WHY? Bilinear model can caputure rich relation of two vectors. However, the computational complexity of bilinear model is huge due to its high dimensionality. To make bilinear model more applicable, this paper suggests low-rank bilinear pooling using Hadamard product. WHAT? Bilinear model have huge matrix W of N x M....


  • Stacked Attention Networks for Image Question Answering

    WHY? Visual question answering task is answering natural language questions based on images. To solve questions that require multi-step reasoning, stacked attention networks(SANs) stacks several layers of attention on parts of images based on query. WHAT? Image model extracts feature map from image with VGGNet structure. Question model uses the...


  • Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing

    Summary Resilient Distributed Datasets(RDD) is a distributed memory abstraction to perform in-memory computations of large clusters. While many data-processing algorithms are applied to data iteratively, the reuse of intermediate results are rarely exploited. To enable in-memory processing with fault-tolerence, RDD provide an interface based on coarse-grained transformation while logging the...


  • The Hadoop Distributed File System

    Summary Hadoop Distributed File System(HDFS) construct file system in cluster level. Huge amount of data are stored in distributed servers and enable users to access with high bandwith. Just like UNIX file system, HDFS keep metadata for data it stores. A dedicated server that stores metadata is called NameNode, and...