Corrections

Summary form only given, as follows. In Vol. 12, no. 3 (Summer 2007), page 9, bottom of the left column, in 'Computer Architecture and Amdahl??s Law' by Gene Amdahl, the claim about invalidating Amdahl??s Law in 1988 came from a team at Sandia National Laboratories, and not Los Alamos. The correct text should read: "Several years later I was informed of a proof that Amdahl's Law was invalidated by someone at Sandia National Laboratories, where a number of computers interconnected as an Ncube by communication lines, but with each computer also connected to I/O devices for loading the operating system, initial data, and results." On page 20 of the same issue, in the second sentence of the diagram explanation note by Justin Rattner, the percentage figures for the sequential and the system coordination parts of the workload were interchanged. The correct version of this sentence should read: "assuming a fixed sized problem, Amdahl speculated that most programs would require at least 10% of the computation to be sequential (only one instruction executing at a time), with overhead due to interprocessor coordination averaging 25%."

Are Deep Learning Approaches Suitable for Natural Language Processing?

In recent years, Deep Learning (DL) techniques have gained much at-tention from Artificial Intelligence (AI) and Natural Language Processing (NLP) research communities because these approaches can often learn features from data without the need for human design or engineering interventions. In addition, DL approaches have achieved some remarkable results. In this paper, we have surveyed major recent contributions that use DL techniques for NLP tasks. All these reviewed topics have been limited to show contributions to text understand-ing, such as sentence modelling, sentiment classification, semantic role labelling, question answering, etc. We provide an overview of deep learning architectures based on Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Recursive Neural Networks (RNNs).