Since traditional convolutional neural network (CNN) is used to extract the spectral-spatial features of hyperspectral image (HSI) will result in lots of spatial information redundancy. Octave convolution is used to replace the traditional CNN to reduce spatial redundancy and expand the receptive field. However, the methods based on 3D octave convolution may cause many parameters and the model to be complicated. To address these issues, we propose an HSI classification approach based on a double-branch multi-scale spectral-spatial convolution network (DBMS) in this paper. Firstly, We utilize 2D octave convolution and 3D DenseNet sub-networks with different kernels sizes to extract complex spatial features and spectral features, respectively. Furthermore, a channel attention module and a spectral attention module are employed in this two sub-network respectively, to highlight the important feature areas and specific spectral bands that consist of significant information for the classification. Compared with several other state-of-the-art methods, our proposed method can achieve competitive performance on Salinas Valley (SV) HSI dataset.

In multi-turn dialog, utterances do not always take the full form of sentences (Carbonell 1983), which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog context to generate a reasonable response. Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog. Enlightened by the multi-task learning scheme, we propose a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features. To better fusing information from the question and the dialog history in the encoding part, we propose to augment the Transformer architecture with a memory updater, which is designed to selectively store and update the history dialog information so as to support downstream tasks. For the experiment, we employ human annotators to write and examine a large-scale dialog reading comprehension dataset. Extensive experiments are conducted on this dataset, and the results show that the proposed model brings substantial improvements over several strong baselines on both tasks. In this way, we demonstrate that reasoning can indeed help better response generation and vice versa. We release our large-scale dataset for further research.

A simile is a figure of speech that directly makes a comparison, showing similarities between two different things, e.g. ``Reading papers can be dull sometimes,like watching grass grow". Human writers often interpolate appropriate similes into proper locations of the plain text to vivify their writings. However, none of existing work has explored neural simile interpolation, including both locating and generation. In this paper, we propose a new task of Writing Polishment with Simile (WPS) to investigate whether machines are able to polish texts with similes as we human do. Accordingly, we design a two-staged Locate&Gen model based on transformer architecture. Our model firstly locates where the simile interpolation should happen, and then generates a location-specific simile. We also release a large-scale Chinese Simile (CS) dataset containing 5 million similes with context. The experimental results demonstrate the feasibility of WPS task and shed light on the future research directions towards better automatic text polishment.

Non-autoregressive models generate target words in a parallel way, which achieve a faster decoding speed but at the sacrifice of translation accuracy.To remedy a flawed translation by non-autoregressive models, a promising approach is to train a conditional masked translation model (CMTM), and refine the generated results within several iterations.Unfortunately, such approach hardly considers the sequential dependency among target words, which inevitably results in a translation degradation.Hence, instead of solely training a Transformer-based CMTM, we propose a Self-Review Mechanism to infuse sequential information into it.Concretely, we insert a left-to-right mask to the same decoder of CMTM, and then induce it to autoregressively review whether each generated word from CMTM is supposed to be replaced or kept.The experimental results (WMT14 En↔De and WMT16 En↔Ro) demonstrate that our model uses dramatically less training computations than the typical CMTM, as well as outperforms several state-of-the-art non-autoregressive models by over 1 BLEU.Through knowledge distillation, our model even surpasses a typical left-to-right Transformer model, while significantly speeding up decoding.