Online literature contains both traditional text and hypertext. While traditional text containing ＂hypertextuality＂ provides the foundation for online literature, hypertext as the prevalent signifying medium of the ...Online literature contains both traditional text and hypertext. While traditional text containing ＂hypertextuality＂ provides the foundation for online literature, hypertext as the prevalent signifying medium of the cyberworld has awakened the latent energy and spirit of traditional text, making the latter more open, more autonomous and more interactive. The literature of ＂bits＂ points to the direction of future development. It deconstructs the traditional and overturns the nature of things through decentered ＂online reading and writing＂ that is uncertain and nonlinear. Hand in hand with post-modernism, hypertext has transformed literature＇s context and mode of existence. Above all, the shift to hypertext in online literature is transforming our mode of thinking and value criteria in relation to literature and aesthetics. We should therefore conduct in-depth and long-term explorations of how online literature may innovate while maintaining tradition.展开更多
Long-document semantic measurement has great significance in many applications such as semantic searchs, plagiarism detection, and automatic technical surveys. However, research efforts have mainly focused on the sema...Long-document semantic measurement has great significance in many applications such as semantic searchs, plagiarism detection, and automatic technical surveys. However, research efforts have mainly focused on the semantic similarity of short texts. Document-level semantic measurement remains an open issue due to problems such as the omission of background knowledge and topic transition. In this paper, we propose a novel semantic matching method for long documents in the academic domain. To accurately represent the general meaning of an academic article, we construct a semantic profile in which key semantic elements such as the research purpose, methodology, and domain are included and enriched. As such, we can obtain the overall semantic similarity of two papers by computing the distance between their profiles. The distances between the concepts of two different semantic profiles are measured by word vectors. To improve the semantic representation quality of word vectors, we propose a joint word-embedding model for incorporating a domain-specific semantic relation constraint into the traditional context constraint. Our experimental results demonstrate that, in the measurement of document semantic similarity, our approach achieves substantial improvement over state-of-the-art methods, and our joint word-embedding model produces significantly better word representations than traditional word-embedding models.展开更多
文摘Online literature contains both traditional text and hypertext. While traditional text containing ＂hypertextuality＂ provides the foundation for online literature, hypertext as the prevalent signifying medium of the cyberworld has awakened the latent energy and spirit of traditional text, making the latter more open, more autonomous and more interactive. The literature of ＂bits＂ points to the direction of future development. It deconstructs the traditional and overturns the nature of things through decentered ＂online reading and writing＂ that is uncertain and nonlinear. Hand in hand with post-modernism, hypertext has transformed literature＇s context and mode of existence. Above all, the shift to hypertext in online literature is transforming our mode of thinking and value criteria in relation to literature and aesthetics. We should therefore conduct in-depth and long-term explorations of how online literature may innovate while maintaining tradition.
基金supported by the Foundation of the State Key Laboratory of Software Development Environment(No.SKLSDE-2015ZX-04)
文摘Long-document semantic measurement has great significance in many applications such as semantic searchs, plagiarism detection, and automatic technical surveys. However, research efforts have mainly focused on the semantic similarity of short texts. Document-level semantic measurement remains an open issue due to problems such as the omission of background knowledge and topic transition. In this paper, we propose a novel semantic matching method for long documents in the academic domain. To accurately represent the general meaning of an academic article, we construct a semantic profile in which key semantic elements such as the research purpose, methodology, and domain are included and enriched. As such, we can obtain the overall semantic similarity of two papers by computing the distance between their profiles. The distances between the concepts of two different semantic profiles are measured by word vectors. To improve the semantic representation quality of word vectors, we propose a joint word-embedding model for incorporating a domain-specific semantic relation constraint into the traditional context constraint. Our experimental results demonstrate that, in the measurement of document semantic similarity, our approach achieves substantial improvement over state-of-the-art methods, and our joint word-embedding model produces significantly better word representations than traditional word-embedding models.
