This paper presents a novel encoderdecoder model for automatically generating market comments from stock prices. The model first encodes both short-and long-term series of stock prices so that it can mention short-and long-term changes in stock prices. In the decoding phase, our model can also generate a numerical value by selecting an appropriate arithmetic operation such as subtraction or rounding, and applying it to the input stock prices. Empirical experiments show that our best model generates market comments at the fluency and the informativeness approaching human-generated reference texts.

Many visually impaired people have experienced walk accident, e.g., died due to falling down from station platform, injured on stairs. They need a support to walk safely. So there have been many researches that aim to be helpful for visually impaired to walk themselves in safety. This study aims to develop a walking-support-system that can detect steps and stairs for visually impaired. Previous studies only used depth sensor, such as Kinect or Xtion. That way was not available in outdoors because of sunlight. This paper presents the method that uses RGB-D camera to detect stairs and steps by using RGB images and depth images without regarding indoors and outdoors. The effectiveness of the proposed method will be shown with some results.

This paper describes NTT's submission to the WMT19 robustness task. This task mainly focuses on translating noisy text (e.g., posts on Twitter), which presents different difficulties from typical translation tasks such as news. Our submission combined techniques including utilization of a synthetic corpus, domain adaptation, and a placeholder mechanism, which significantly improved over the previous baseline. Experimental results revealed the placeholder mechanism, which temporarily replaces the non-standard tokens including emojis and emoticons with special placeholder tokens during translation, improves translation accuracy even with noisy texts.

No abstract