Recent years, Chinese text classification has attracted more and research attention. However, most existing techniques which specifically aim at English materials may lose effectiveness on this task due to the huge difference between English. Actually, as a special kind of hieroglyphics, characters radicals are semantically useful but still unexplored in classification. To that end, paper, we first analyze motives using multiple granularity features represent by inspecting characteristics...

Visual Emotion Recognition has attracted more and research attention in recent years. Existing approaches mainly depend on facial expression or analyze the whole image between positive negative. Actually, people can recognize multiple emotions from one based global 10-cal information. In this paper, we propose a Context-Aware Generation-Based Net (CAGBN), novel architecture that makes full use of local information by considering both details target person. Inspired psychological studies when...

Cognitive psychology research shows that humans have the instinct for abstract thinking, where association plays an essential role in language comprehension. Especially Chinese, its ideographic writing system allows radicals to trigger semantic without need of phonetics. In fact, subconsciously using associative information guided by is a key readers ensure robustness understanding. Fortunately, many basic and extended concepts related are systematically included Chinese dictionaries, which...

Recent years have witnessed a booming increase of patent applications, which provides an open chance for revealing the inner law innovation, but in meantime, puts forward higher requirements on mining techniques. Considering that highly relies document analysis, this paper makes focused study constructing technology portrait each patent, i.e., to recognize technical phrases concerned it, can summarize and represent patents from angle. To end, we first give clear detailed description about...

As a vivid and linguistic symbol, Emojis have become prevailing medium interspersed in text-based communication (e.g., social media chit-chat) to express emotions, attitudes, situations. Generally speaking, social-oriented chatbot that can generate appropriate Emoji-embedded responses would be much more competitive, making communications fun, engaging, human-like. However, the current Emoji-related research is still its infancy, leading an awkward situation of data deficiency. How develop...

One of the most important subconscious reactions, micro-expression (ME), is a spontaneous, subtle, and transient facial expression that reveals human beings' genuine emotion. Therefore, automatically recognizing ME (MER) becoming increasingly crucial in field affective computing, providing essential technical support for lie detection, clinical psychological diagnosis, public safety. However, data scarcity has severely hindered development advanced data-driven MER models. Despite recent...

Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings. In this paper, we argue Chinese embeddings can be substantially enriched by the morphological information hidden characters which reflected not only strokes order sequentially, but also character glyphs spatially. Then, propose a novel Dual-channel Word Embedding (DWE) model to realize joint learning of sequential and spatial characters. Through evaluation on both similarity analogy...

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but still under exploration. Existing studies either fit fluctuations time-series or employ regularization terms to constrain learned tendencies. However, few them take into account inherent decision-making process between investors and dynamics. To address problem, paper, we propose Trajectory-based Continuous Control for Crowdfunding (TC3)...

Reading psychology believes text comprehension to involve a complex psychological construction process, with the reader mind being dynamic associative system that stores an abundance of schemata. For Chinese text, in particular, unique ideographic writing allows its lansign trigger semantic association and schema recalling without need phonetics. In contrast previous research efforts on classification problems, this paper we present interdisciplinary modeling approach draws inspirations from...

Emotion Cause Extraction (ECE) aims to reveal the cause clauses behind a given emotion expressed in text, which has become an emerging topic broad research communities, such as affective computing and natural language processing. Despite fact that current methods about ECE task have made great progress text semantic understanding from lexicon- sentence-level, they always ignore certain causal narratives of text. Significantly, these are presented form structure highly helpful for...

Text classification is a fundamental and classical problem in natural language processing. Existing methods this area attach more attention to structure modeling of texts, while largely ignoring the cognitive principles human reading. Actually, as an important aspect exploring characteristics comprehension, neuroscience research recent years has demonstrated instinct for abstract thinking, where semantic processing summarizing play essential roles. To end, we propose novel text method with...

Highlights•Propose to use resilience for performance assessment after system failure recovery.•Considering the time-varying characteristics of system, using reliability as a indicator.•Using train control on-board an example application.•The results show that system's decreases by approximately 12 % when it has recovery capability.AbstractTo address problem difficult from failures, we have proposed methodology uses indicator resilience. Since failures are time-dependent, adopted Discrete...

To address the problem of difficult performance assessment train control on-board system after recovery from failures, we have proposed a resilience methodology that uses reliability as an indicator resilience. Since failures are time-dependent, adopted DiscreteTime Bayesian Network method to obtain system's before and failure. Subsequently, used exponential model quantify curve during phase, finally utilized resilient triangle area its size. Analyzing CTCS3-300T system,we found with cold...

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but still under exploration. Existing studies either fit fluctuations time-series or employ regularization terms to constrain learned tendencies. However, few them take into account inherent decision-making process between investors and dynamics. To address problem, paper, we propose Trajectory-based Continuous Control for Crowdfunding (TC3)...