We consider the ROC story cloze task (Mostafazadeh et al., 2016) and present several findings. We develop a model that uses hierarchical recurrent networks with attention to encode the sentences in the story and score candidate endings. By discarding the large training set and only training on the validation set, we achieve an accuracy of 74.7%. Even when we discard the story plots (sentences before the ending) and only train to choose the better of two endings, we can still reach 72.5%. We then analyze this "ending-only" task setting.We estimate human accuracy to be 78% and find several types of clues that lead to this high accuracy, including those related to sentiment, negation, and general ending likelihood regardless of the story context.

We show that the imperceptibility of several existing linguistic steganographic systems (Fang et al., 2017;Yang et al., 2018) relies on implicit assumptions on statistical behaviors of fluent text. We formally analyze them and empirically evaluate these assumptions. Furthermore, based on these observations, we propose an encoding algorithm called patient-Huffman with improved near-imperceptible guarantees.

Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character's glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to incorporate the spatio-structural patterns of Chinese glyphs as rendered in raw pixels. In the context of two basic Chinese NLP tasks of language modeling and word segmentation, the model learns to represent each character's task-relevant semantic and syntactic information in the character-level embedding.

Feature importance is commonly used to explain machine predictions. While feature importance can be derived from a machine learning model with a variety of methods, the consistency of feature importance via different methods remains understudied. In this work, we systematically compare feature importance from built-in mechanisms in a model such as attention values and post-hoc methods that approximate model behavior such as LIME. Using text classification as a testbed, we find that 1) no matter which method we use, important features from traditional models such as SVM and XGBoost are more similar with each other, than with deep learning models; 2) posthoc methods tend to generate more similar important features for two models than built-in methods. We further demonstrate how such similarity varies across instances. Notably, important features do not always resemble each other better when two models agree on the predicted label than when they disagree.One of favorite places to eat on the King W side, simple and relatively quick. I typically always get the chicken burrito and the small is enough for me for dinner. Ingredients are always fresh and watch out for the hot sauce cause it's skull scratching hot. Seating is limited so be prepared to take your burrito outside or you can even eat at Metro Hall Park. methods models SVM ( 2) XGBoost LSTM with attention BERT built-in sauce, . 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of EMNLP.

Based on rural population return management, governance theory, and information technology theory, this paper analyzes the specific performance of rural areas in managing population return, and describes the overview, quantity, life status, and demographic characteristics of rural population return, as well as the current situation of rural population return management. A method of managing rural population return based on a rural population return management model constructed by a machine learning algorithm is designed. The empirical results show that the method designed in this paper is low-cost, fast, and highly accurate, and is well suited for improving and expanding the system for managing rural return flows. The research in this paper provides a reference for further promoting the transformation strategy of rural governance in the context of new urbanization.