The described structural model tries to answer some open questions such as: Why do quarks not exist in the open state? Where are the antiparticles from the Big Bang?
For the complex questions of Chinese question answering system, we propose an answer extraction method with discourse structure feature combination. This method uses the relevance of questions and answers to learn to ...For the complex questions of Chinese question answering system, we propose an answer extraction method with discourse structure feature combination. This method uses the relevance of questions and answers to learn to rank the answers. Firstly, the method analyses questions to generate the query string, and then submits the query string to search engines to retrieve relevant documents. Sec- ondly, the method makes retrieved documents seg- mentation and identifies the most relevant candidate answers, in addition, it uses the rhetorical relations of rhetorical structure theory to analyze the relationship to determine the inherent relationship between para- graphs or sentences and generate the answer candi- date paragraphs or sentences. Thirdly, we construct the answer ranking model,, and extract five feature groups and adopt Ranking Support Vector Machine （SVM） algorithm to train ranking model. Finally, it re-ranks the answers with the training model and fred the optimal answers. Experiments show that the proposed method combined with discourse structure features can effectively improve the answer extrac- ting accuracy and the quality of non-factoid an- swers. The Mean Reciprocal Rank （MRR） of the an- swer extraction reaches 69.53%.展开更多
With the continuous development of political, economic,social, empty nesters and more problems, it is not a simple personal issues, has become urgent to break the social proposition.This paper intr~,duces the concepts...With the continuous development of political, economic,social, empty nesters and more problems, it is not a simple personal issues, has become urgent to break the social proposition.This paper intr~,duces the concepts at the same time,Further analysis of the current situation empty-nesters of the problem and sort out the history of urban-rural dual structure,Finally, find information put forward some countermeasures and suggestions.展开更多
为了促进人们对语篇语义、信息结构前沿的了解,介绍当前待议问题(Question under discussion, QUD)的理论要点,并利用典例阐释其在理论研究和实证研究上的运用方法,最后结合QUD的优势和不足讨论其在汉语中运用的广泛空间。研究发现:首先...为了促进人们对语篇语义、信息结构前沿的了解,介绍当前待议问题(Question under discussion, QUD)的理论要点,并利用典例阐释其在理论研究和实证研究上的运用方法,最后结合QUD的优势和不足讨论其在汉语中运用的广泛空间。研究发现:首先,QUD与选项语义学、询问语义学相结合,能够消解受语境限制选项集模糊的问题,起到增强理论解释力、拓展理论解释范围的效果;其次,QUD为实验研究和自然语言处理提供了新工具,相关研究揭示了语篇信息结构对语言习得的作用,推动了语篇信息结构层面语料标注的发展;最后,QUD能够为汉语现象提供新的解决思路,促进人们挖掘语言事实背后所蕴含的深刻道理。展开更多
Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational fiel...Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational field struggles with two challenges:the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage;the other is the lack of specialized educational QG datasets.To address the challenges,a specialized QG dataset,reading comprehension dataset from examinations for QG(named RACE4QG),is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE dataset.Further,an end-to-end QG model,which can exploit the intra-and inter-sentence information to generate better questions,is proposed.In our model,the encoder utilizes a Gated Recurrent Units(GRU)network,which takes the concatenation of word embedding,answer tagging,and Graph Attention neTworks(GAT)embedding as input.The hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation,which will be fed to the decoder.Results show that our model outperforms baselines on automatic metrics and human evaluation.Consequently,the model improves the baseline by 0.44,1.32,and 1.34 on BLEU-4,ROUGE-L,and METEOR metrics,respectively,indicating the effectivity and reliability of our model.Its gap with human expectations also reflects the research potential.展开更多
Tag question is often used in English conversation,but it is also a very complicated syntactic structure in English which becomes the difficulty of English learners.Tag question involves various grammatical factors.A ...Tag question is often used in English conversation,but it is also a very complicated syntactic structure in English which becomes the difficulty of English learners.Tag question involves various grammatical factors.A full linguistic analysis of tag questions includes the classification,construction and meanings of intonations of the tag questions in English.The study of tag question aims at providing substantial contribution to the teaching and learning of English syntax.展开更多
文摘The described structural model tries to answer some open questions such as: Why do quarks not exist in the open state? Where are the antiparticles from the Big Bang?
基金supported by the National Nature Science Foundation of China under Grants No.60863011,No.61175068,No.61100205,No.60873001the Fundamental Research Funds for the Central Universities under Grant No.2009RC0212+1 种基金the National Innovation Fund for Technology based Firms under Grant No.11C26215305905the Open Fund of Software Engineering Key Laboratory of Yunnan Province under Grant No.2011SE14
文摘For the complex questions of Chinese question answering system, we propose an answer extraction method with discourse structure feature combination. This method uses the relevance of questions and answers to learn to rank the answers. Firstly, the method analyses questions to generate the query string, and then submits the query string to search engines to retrieve relevant documents. Sec- ondly, the method makes retrieved documents seg- mentation and identifies the most relevant candidate answers, in addition, it uses the rhetorical relations of rhetorical structure theory to analyze the relationship to determine the inherent relationship between para- graphs or sentences and generate the answer candi- date paragraphs or sentences. Thirdly, we construct the answer ranking model,, and extract five feature groups and adopt Ranking Support Vector Machine （SVM） algorithm to train ranking model. Finally, it re-ranks the answers with the training model and fred the optimal answers. Experiments show that the proposed method combined with discourse structure features can effectively improve the answer extrac- ting accuracy and the quality of non-factoid an- swers. The Mean Reciprocal Rank （MRR） of the an- swer extraction reaches 69.53%.
文摘With the continuous development of political, economic,social, empty nesters and more problems, it is not a simple personal issues, has become urgent to break the social proposition.This paper intr~,duces the concepts at the same time,Further analysis of the current situation empty-nesters of the problem and sort out the history of urban-rural dual structure,Finally, find information put forward some countermeasures and suggestions.
文摘为了促进人们对语篇语义、信息结构前沿的了解,介绍当前待议问题(Question under discussion, QUD)的理论要点,并利用典例阐释其在理论研究和实证研究上的运用方法,最后结合QUD的优势和不足讨论其在汉语中运用的广泛空间。研究发现:首先,QUD与选项语义学、询问语义学相结合,能够消解受语境限制选项集模糊的问题,起到增强理论解释力、拓展理论解释范围的效果;其次,QUD为实验研究和自然语言处理提供了新工具,相关研究揭示了语篇信息结构对语言习得的作用,推动了语篇信息结构层面语料标注的发展;最后,QUD能够为汉语现象提供新的解决思路,促进人们挖掘语言事实背后所蕴含的深刻道理。
基金This work was supported by the National Natural Science Foundation of China(No.62166050)Yunnan Fundamental Research Projects(No.202201AS070021)Yunnan Innovation Team of Education Informatization for Nationalities,Scientific Technology Innovation Team of Educational Big Data Application Technology in University of Yunnan Province,and Yunnan Normal University Graduate Research and innovation fund in 2020(No.ysdyjs2020006).
文摘Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational field struggles with two challenges:the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage;the other is the lack of specialized educational QG datasets.To address the challenges,a specialized QG dataset,reading comprehension dataset from examinations for QG(named RACE4QG),is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE dataset.Further,an end-to-end QG model,which can exploit the intra-and inter-sentence information to generate better questions,is proposed.In our model,the encoder utilizes a Gated Recurrent Units(GRU)network,which takes the concatenation of word embedding,answer tagging,and Graph Attention neTworks(GAT)embedding as input.The hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation,which will be fed to the decoder.Results show that our model outperforms baselines on automatic metrics and human evaluation.Consequently,the model improves the baseline by 0.44,1.32,and 1.34 on BLEU-4,ROUGE-L,and METEOR metrics,respectively,indicating the effectivity and reliability of our model.Its gap with human expectations also reflects the research potential.
文摘Tag question is often used in English conversation,but it is also a very complicated syntactic structure in English which becomes the difficulty of English learners.Tag question involves various grammatical factors.A full linguistic analysis of tag questions includes the classification,construction and meanings of intonations of the tag questions in English.The study of tag question aims at providing substantial contribution to the teaching and learning of English syntax.
