【摘 要】
：
The rapid development of new media results in a lot of redundant information,increasing the difficulty of quickly obtaining useful information and browsing
【机 构】
：
Beijing Institute of Technology School of Computer Science,Beijing,100081,China
【出 处】
：
第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD
论文部分内容阅读
The rapid development of new media results in a lot of redundant information,increasing the difficulty of quickly obtaining useful information and browsing simplified messages on portable devices.Thus emerges the automatic news abridgement technology.We propose a novel method of word alignment,aiming at news headlines,applying the combination method of statistics and rules to intelligent abridgement.And a new framework based on the combination of sentence abridgement and sentence selection to generate the abridgement result of news contents,abridging the original text to the word limit,in order to achieve the uttermost conservation of the original meaning.Meanwhile,for a fair and intelligent evaluation,this paper presents an evaluation method of automatic summarization specific to sentence abridgement techniques.Experimental results show that the proposed methods are feasible,and able to automatically generate coherent and representative summaries of given news with high density.
其他文献
The availability of labeled corpus is of great importance for emotion classification tasks.Because manual labeling is too time-consuming,hashtags have been
In this paper,we apply a bidirectional Long Short-Term Memory with a Conditional Random Field to the task of disfluency detection.Long-range dependencies is
The Chinese language is a character-based language,with no explicit separators between words like English.Traditionally,word segmentation is conducted to co
Large-scale annotated corpora are a prerequisite for developing high-performance age regression models.However,such annotated corpora are some-times very ex
This paper presents the state of art research progress on multilingual multi-document summarization.Our method utilizes hLDA(hierarchical Latent Dirichlet A
Previous researches on event relation classification primarily rely on lexical and syntactic features.In this paper,we use a Shallow Convolutional Neural Ne
The dialog manager is the most important component for a dialog system,in which the dialog state tracking is crucial to a real-world system.We claim that th
The algorithms for discovering global community structure require the knowledge about entire network structures,which are still difficult and unrealistic to
Finding similarity degree is one of the significant technologies used in the sample-based machine translation.It works in the following principle,first matc
Previous work has shown that joint modeling of two Natural Language Processing(NLP)tasks are effective for achieving better performances for both tasks.Lots