Image inspired Chinese couplet generation

2020 ◽  
Vol 18 (3) ◽  
pp. 217-227
Author(s):  
Shengqiong Yuan ◽  
Luo Zhong ◽  
Lin Li
Keyword(s):  
Language Processing ◽  
Chinese Culture ◽  
Automatic Generation ◽  
Input Image ◽  
Cultural Value ◽  
Generation Model ◽  
Chinese History ◽  
Artistic Conception ◽  
Text Information ◽  
Antecedent Clause

Chinese couplets, as one of the traditional Chinese culture, is the treasure of Chinese civilization and the inheritance of Chinese history. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Because of the complexity of the semantic and grammatical rules of couplet, it is not easy to create a suitable couplet that meets the requirements of sentence pattern, context, and flatness. With the development of neural models and natural language processing, automatic generation of Chinese couplets has drawn significant attention due to its artistic and cultural value, most of these works mainly focus on generating couplet by given text information, while visual inspirations for couplet generation have been rarely explored. In this paper, we design a Chinese couplet generation model based on NIC (Neural Image Caption), which can compose a piece of couplet suitable to the artistic conception in an image. At first, we use the improved VGG16 model to predict the input image. The content of the image can be automatically recognized and the corresponding description are generated and translated into Chinese keywords. Then, the encoder-decoder framework is used repeatedly to process these keywords, and finally the couplet can be generated. Moreover, to satisfy special characteristics of couplets, we incorporate the attention mechanism into the encoding-decoding process, which greatly improves the accuracy of couplets generated automatically.

Teaching and Researching American Literature and American Realism in China

2019 ◽  
pp. 647-663
Author(s):  
Yuping Wang
Keyword(s):  
American Literature ◽  
Language Proficiency ◽  
Chinese Culture ◽  
Cultural Transformation ◽  
Cultural Norms ◽  
Careful Study ◽  
Chinese History ◽  
Political Incentives ◽  
History Of ◽  
English Speaking

The study and teaching of American literature and American realism in China mirrored the social development and cultural transformation in China and was often fueled by political incentives. This chapter examines the cultural and political forces affecting the reception of American literature in different stages of Chinese history and investigates the teaching of American literature and of American realism in Chinese university classrooms. Different from the teaching of American literature in English-speaking countries, the American literature course in China serves a twofold purpose: to provide cultural nutrient for the cultivation of a broader mind by highlighting the cultural norms and rubrics in literature and to promote students’ language proficiency by a careful study of the text and formal elements of literary works. The history of the Chinese reception of American literature thus reflects the resilience and openness of Chinese culture in its negotiation with foreign cultures.

scholarly journals Blending Myth and Modernity in the Global Chinese Cinema: The Hong Kong Action Hero in Zhang Yimou-Directed Hero

2018 ◽  
Vol 32 (2) ◽  
pp. 37-56
Author(s):  
Dhruba Karki
Keyword(s):  
Hong Kong ◽  
Martial Arts ◽  
Chinese Culture ◽  
Body Art ◽  
Modern China ◽  
Chinese History ◽  
Technological Advancement ◽  
Chinese Cinema ◽  
Chinese Empire ◽  
Action Hero

 Zhang Yimou’s Hero presents an action hero, yet in a slightly different cinematic mode than that of Stephen Chow-directed Shaolin Soccer to blend myth and modernity. In Yimou’s martial arts cinema, Jet Li-starred Nameless hero uses martial arts to combat the king’s adversaries, including Donnie Yen-starred Long Sky, Maggie Cheung-starred Flying Snow and Tony Leung Chiu-Wai-starred Broken Sword in the service to the Qin Dynasty (221 BC – 207 BC). The warrior hero’s indigenous body art helps the Qin Dynasty transform the smaller warring kingdoms into a powerful Chinese Empire, a strong foundation of modern China with economic and military superpower. Like their western counterparts, including T1000 and Neo, the Hong Kong action heroes, such as the warrior hero and the Qin King have been refashioned in the Hollywood controlled twentieth-century popular culture. Different from their Hollywood counterparts in actions, the Hong Kong action heroes in Hero primarily use their trained bodies and martial skills to promote the Chinese civilization, an adaptation of the Hollywood tradition of technologized machine body. Reworking of myth and archetype in Nameless’s service to the Qin Dynasty and the emperor’s mission to incept the Chinese Empire, the Hong Kong action heroes appear on screen, a blend of tradition and modernity. The film industry’s projection of the Chinese history with the legendary action heroes, including Nameless soldier and the Qin King globalizes the indigenous Chinese culture by using modern electronic digital technology, a resonance of the western technological advancement.

Improved Framework using Rider Optimization Algorithm for Precise Image Caption Generation

2021 ◽  
pp. 2250021
Author(s):  
Chaitrali Prasanna Chaudhari ◽  
Satish Devane
Keyword(s):  
Language Processing ◽  
Optimization Algorithm ◽  
Short Term Memory ◽  
Activation Function ◽  
Input Image ◽  
Image Captioning ◽  
Word Generation ◽  
Adopted Model ◽  
Conventional Models ◽  
Image Caption

“Image Captioning is the process of generating a textual description of an image”. It deploys both computer vision and natural language processing for caption generation. However, the majority of the image captioning systems offer unclear depictions regarding the objects like “man”, “woman”, “group of people”, “building”, etc. Hence, this paper intends to develop an intelligent-based image captioning model. The adopted model comprises of few steps like word generation, sentence formation, and caption generation. Initially, the input image is subjected to the Deep learning classifier called Convolutional Neural Network (CNN). Since the classifier is already trained in the relevant words that are related to all images, it can easily classify the associated words of the given image. Further, a set of sentences is formed with the generated words using Long-Short Term Memory (LSTM) model. The likelihood of the formed sentences is computed using the Maximum Likelihood (ML) function, and the sentences with higher probability are taken, which is further used for generating the visual representation of the scene in terms of image caption. As a major novelty, this paper aims to enhance the performance of CNN by optimally tuning its weight and activation function. This paper introduces a new enhanced optimization algorithm Rider with Randomized Bypass and Over-taker update (RR-BOU) for this optimal selection. In the proposed RR-BOU is the enhanced version of the Rider Optimization Algorithm (ROA). Finally, the performance of the proposed captioning model is compared over other conventional models with respect to statistical analysis.

Witch-hunting, Cultural Revolution and the bright side of kinship

2018 ◽  
Vol 17 (1) ◽  
pp. 87-101 ◽  
Author(s):  
Feng Deng
Keyword(s):  
Social Structure ◽  
Cultural Revolution ◽  
Large Scale ◽  
Chinese Culture ◽  
Social Institutions ◽  
Dark Side ◽  
Chinese History ◽  
Content Type ◽  
Bright Side ◽  
The Cultural Revolution

Purpose Many studies on witch killings in Africa suggest that “witchcraft is the dark side of kinship.” But in Chinese history, where patriarchal clan system has been emphasized as the foundation of the society, there have been few occurrences of witch-hunting except a large-scale one in the Cultural Revolution in 1966. The purpose of this paper is to explain the above two paradoxes. Design/methodology/approach Theoretical analysis based on preference falsification problem with regard to the effect of social structure on witch-hunting is carried out. Findings There is a “bright side of kinship” due to two factors: first, it would be more difficult to pick out a person as qualitatively different in Chinese culture; second, the hierarchical trust structure embedded in the Chinese culture can help mitigate the preference falsification problem, which acts as the leverage for witch-hunting. In this sense, an important factor for the Cultural Revolution is the decline of traditional social institutions and social values after 1949. Originality/value This paper is the first to advance the two paradoxes and offer an explanation from the perspective of social structure.

Notes on Professor Karlgren's System for Dating Chinese Bronzes

1936 ◽  
Vol 68 (03) ◽  
pp. 463-473
Author(s):  
Herrlee Glessner Creel
Keyword(s):  
Chinese Culture ◽  
Deep Understanding ◽  
Central Place ◽  
Chinese History ◽  
History Of ◽  
Oracle Bones

The pre-Confucian period has come, during the last decade, to occupy a central place in the attention of students of the history of Chinese culture. Research on the oracle bones, scientific excavations at Anyang and elsewhere, and other investigations and discoveries have not served merely to throw light on the civilization of late Shang and early Chou times. They have also shown us that those periods saw the laying of the foundations of the whole structure of Chinese culture, as it has persisted even to our own day, so that to understand them is no mere concern of antiquarians, but a vital necessity for any deep understanding of the currents of Chinese history.

scholarly journals Automatically Representing TExt Meaning via an Interlingua-based System (ARTEMIS). A further step towards the computational representation of RRG

2017 ◽  
Vol 1 (1) ◽  
pp. 61 ◽  
Author(s):  
Ricardo Mairal-Usón ◽  
Francisco Cortés-Rodríguez
Keyword(s):  
Language Processing ◽  
Semantic Representation ◽  
Analysis Data ◽  
Logical Structure ◽  
Automatic Generation ◽  
Role And Reference Grammar ◽  
Reference Grammar ◽  
Level 1 ◽  
Computational Resources ◽  
Computational Representation

Within the framework of FUNK Lab – a virtual laboratory for natural language processing inspired on a functionally-oriented linguistic theory like Role and Reference Grammar-, a number of computational resources have been built dealing with different aspects of language and with an application in different scientific domains, i.e. terminology, lexicography, sentiment analysis, document classification, text analysis, data mining etc. One of these resources is ARTEMIS (<span style="text-decoration: underline;">A</span>utomatically <span style="text-decoration: underline;">R</span>epresenting <span style="text-decoration: underline;">TE</span>xt <span style="text-decoration: underline;">M</span>eaning via an <span style="text-decoration: underline;">I</span>nterlingua-Based <span style="text-decoration: underline;">S</span>ystem), which departs from the pioneering work of Periñán-Pascual (2013) and Periñán-Pascual &amp; Arcas (2014).  This computational tool is a proof of concept prototype which allows the automatic generation of a conceptual logical structure (CLS) (cf. Mairal-Usón, Periñán-Pascual and Pérez 2012; Van Valin and Mairal-Usón 2014), that is, a fully specified semantic representation of an input text on the basis of a reduced sample of sentences. The primary aim of this paper is to develop the syntactic rules that form part of the computational grammar for the representation of simple clauses in English. More specifically, this work focuses on the format of those syntactic rules that account for the upper levels of the RRG Layered Structure of the Clause (LSC), that is, the <em>core</em> (and the level-1 construction associated with it), the <em>clause</em> and the <em>sentence </em>(Van Valin 2005). In essence, this analysis, together with that in Cortés-Rodríguez and Mairal-Usón (2016), offers an almost complete description of the computational grammar behind the LSC for simple clauses.

Exotica, Fashion and Immortality: The New Use of Gold in Han Dynasty China (206 bce–ce 220)

2021 ◽  
pp. 1-16
Author(s):  
Shengyu Wang
Keyword(s):  
Chinese Culture ◽  
Composite System ◽  
Well Being ◽  
Han Dynasty ◽  
Eighth Century ◽  
Third Century ◽  
Chinese History ◽  
Eurasian Steppe ◽  
History Of ◽  
History Of Use

This article explores the use of gold in the elite tombs of Han dynasty China, the popular use of which originated outside the Chinese cultural milieu, and its integration into the Han portfolio of materials representing people's expectations for the afterlife, such as immortality and well-being. In contrast to jade, which had a long history of use in China, gold was in itself a ‘new’ element of Chinese culture. This article outlines the introduction of gold objects from Europe and Central Asia via the Eurasian Steppe and borderland of China from around the eighth century bce. The unprecedented use of gold in the Han-specific jade suits, and the process by which foreign types of zoomorphic motifs were adopted and connected with local motifs, are explored. In light of the political change from multiple competing states before the first unification in Chinese history in the third century bce, and the development in ideology and concept of an ideal and eternal afterlife, this article explains the reasons and meanings of the new use of gold in Han dynasty China and the composite system of motifs, materials and objects.

scholarly journals Cognification of Program Synthesis—A Systematic Feature-Oriented Analysis and Future Direction

Computers ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 27
Author(s):  
Ahmad F. Subahi
Keyword(s):  
Code Generation ◽  
Program Synthesis ◽  
Domain Analysis ◽  
Automatic Generation ◽  
Feature Model ◽  
Automatic Process ◽  
Generation Model ◽  
Research Database ◽  
Next Generation ◽  
Research Questions

Program synthesis is defined as a software development step aims at achieving an automatic process of code generation that is satisfactory given high-level specifications. There are various program synthesis applications built on Machine Learning (ML) and Natural Language Processing (NLP) based approaches. Recently, there have been remarkable advancements in the Artificial Intelligent (AI) domain. The rise in advanced ML techniques has been remarkable. Deep Learning (DL), for instance, is considered an example of a currently attractive research field that has led to advances in the areas of ML and NLP. With this advancement, there is a need to gain greater benefits from these approaches to cognify synthesis processes for next-generation model-driven engineering (MDE) framework. In this work, a systematic domain analysis is conducted to explore the extent to the automatic generation of code can be enabled via the next generation of cognified MDE frameworks that support recent DL and NLP techniques. After identifying critical features that might be considered when distinguishing synthesis systems, it will be possible to introduce a conceptual design for the future involving program synthesis/MDE frameworks. By searching different research database sources, 182 articles related to program synthesis approaches and their applications were identified. After defining research questions, structuring the domain analysis, and applying inclusion and exclusion criteria on the classification scheme, 170 out of 182 articles were considered in a three-phase systematic analysis, guided by some research questions. The analysis is introduced as a key contribution. The results are documented using feature diagrams as a comprehensive feature model of program synthesis showing alternative techniques and architectures. The achieved outcomes serve as motivation for introducing a conceptual architectural design of the next generation of cognified MDE frameworks.

scholarly journals Middle-Level Attribute-Based Language Retouching for Image Caption Generation

2018 ◽  
Vol 8 (10) ◽  
pp. 1850 ◽  
Author(s):  
Zhibin Guan ◽  
Kang Liu ◽  
Yan Ma ◽  
Xu Qian ◽  
Tongkai Ji
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Middle Level ◽  
Generation Model ◽  
Image Description ◽  
Image Captioning ◽  
Benchmark Datasets ◽  
Intermediate Image ◽  
Image Caption Generation ◽  
Image Caption

Image caption generation is attractive research which focuses on generating natural language sentences to describe the visual content of a given image. It is an interdisciplinary subject combining computer vision (CV) and natural language processing (NLP). The existing image captioning methods are mainly focused on generating the final image caption directly, which may lose significant identification information of objects contained in the raw image. Therefore, we propose a new middle-level attribute-based language retouching (MLALR) method to solve this problem. Our proposed MLALR method uses the middle-level attributes predicted from the object regions to retouch the intermediate image description, which is generated by our language generation model. The advantage of our MLALR method is that it can correct descriptive errors in the intermediate image description and make the final image caption more accurate. Moreover, evaluation using benchmark datasets—MSCOCO, Flickr8K, and Flickr30K—validated the impressive performance of our MLALR method with evaluation metrics—BLEU, METEOR, ROUGE-L, CIDEr, and SPICE.

scholarly journals Research of Automatic Generation for Engineering Geological Survey Reports Based on a Four-Dimensional Dynamic Template

2020 ◽  
Vol 9 (9) ◽  
pp. 496
Author(s):  
Yujiao Lei ◽  
Jiqiu Deng ◽  
Jian Lin ◽  
Jeffrey M. Dick ◽  
Mohammad Naser Lessani ◽  
...  
Keyword(s):  
Automatic Generation ◽  
Geological Survey ◽  
Generation Model ◽  
Hierarchical Tree ◽  
Survey Report ◽  
Standardized Report ◽  
Report System ◽  
Professional Field ◽  
Manual Processing ◽  
Dynamic Template

Errors and inefficiency may be caused by manual processing of complex templates for the preparation and management of engineering survey reports. To address this problem, this paper analyzes the multidimensional variable features of professional field documents and proposes a generation model of standardized reports based on a four-dimensional dynamic template. This approach splits the standardized report into multiple parts to construct a hierarchical tree that represents the report structure according to the report rules, then stores the tree in a graph database, and finally generates the desired report dynamically by retrieving the relational tree for the template and obtaining the relevant data. The model has been applied to the engineering geological survey report system and is shown to improve the working efficiency and data accuracy of the report preparation. Results indicate that the model is feasible and effective.

Sign in / Sign up

Export Citation Format

Share Document