The rise of social media platforms has revolutionized communication, enabling the exchange of vast amounts of data through text, audio, images, and videos. These platforms have become critical for sharing opinions and...The rise of social media platforms has revolutionized communication, enabling the exchange of vast amounts of data through text, audio, images, and videos. These platforms have become critical for sharing opinions and insights, influencing daily habits, and driving business, political, and economic decisions. Text posts are particularly significant, and natural language processing (NLP) has emerged as a powerful tool for analyzing such data. While traditional NLP methods have been effective for structured media, social media content poses unique challenges due to its informal and diverse nature. This has spurred the development of new techniques tailored for processing and extracting insights from unstructured user-generated text. One key application of NLP is the summarization of user comments to manage overwhelming content volumes. Abstractive summarization has proven highly effective in generating concise, human-like summaries, offering clear overviews of key themes and sentiments. This enhances understanding and engagement while reducing cognitive effort for users. For businesses, summarization provides actionable insights into customer preferences and feedback, enabling faster trend analysis, improved responsiveness, and strategic adaptability. By distilling complex data into manageable insights, summarization plays a vital role in improving user experiences and empowering informed decision-making in a data-driven landscape. This paper proposes a new implementation framework by fine-tuning and parameterizing Transformer Large Language Models to manage and maintain linguistic and semantic components in abstractive summary generation. The system excels in transforming large volumes of data into meaningful summaries, as evidenced by its strong performance across metrics like fluency, consistency, readability, and semantic coherence.展开更多
The existing abstractive text summarisation models only consider the word sequence correlations between the source document and the reference summary,and the summary generated by models lacks the cover of the subject ...The existing abstractive text summarisation models only consider the word sequence correlations between the source document and the reference summary,and the summary generated by models lacks the cover of the subject of source document due to models'small perspective.In order to make up these disadvantages,a multi‐domain attention pointer(MDA‐Pointer)abstractive summarisation model is proposed in this work.First,the model uses bidirectional long short‐term memory to encode,respectively,the word and sentence sequence of source document for obtaining the semantic representations at word and sentence level.Furthermore,the multi‐domain attention mechanism between the semantic representations and the summary word is established,and the proposed model can generate summary words under the proposed attention mechanism based on the words and sen-tences.Then,the words are extracted from the vocabulary or the original word sequences through the pointer network to form the summary,and the coverage mechanism is introduced,respectively,into word and sentence level to reduce the redundancy of sum-mary content.Finally,experiment validation is conducted on CNN/Daily Mail dataset.ROUGE evaluation indexes of the model without and with the coverage mechanism are improved respectively,and the results verify the validation of model proposed by this paper.展开更多
A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary.Therefore...A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary.Therefore,in this paper,a simple and weakly supervised framework considering factual consistency is proposed to generate a summary of city-based complaint reports without pre-labeled sentences/words.Furthermore,it considers the importance of entity in complaint reports to ensure factual consistency of summary.Experimental results on the customer review datasets(Yelp and Amazon)and complaint report dataset(complaint reports of Shenyang in China)show that the proposed framework outperforms state-of-the-art approaches in ROUGE scores and human evaluation.It unveils the effectiveness of our approach to helping in dealing with complaint reports.展开更多
Text summarization aims to generate a concise version of the original text.The longer the summary text is,themore detailed it will be fromthe original text,and this depends on the intended use.Therefore,the problem of...Text summarization aims to generate a concise version of the original text.The longer the summary text is,themore detailed it will be fromthe original text,and this depends on the intended use.Therefore,the problem of generating summary texts with desired lengths is a vital task to put the research into practice.To solve this problem,in this paper,we propose a new method to integrate the desired length of the summarized text into the encoder-decoder model for the abstractive text summarization problem.This length parameter is integrated into the encoding phase at each self-attention step and the decoding process by preserving the remaining length for calculating headattention in the generation process and using it as length embeddings added to theword embeddings.We conducted experiments for the proposed model on the two data sets,Cable News Network(CNN)Daily and NEWSROOM,with different desired output lengths.The obtained results show the proposed model’s effectiveness compared with related studies.展开更多
TENORM Regulation in the United States of America post-West Virginia vs.EPA Spenser Lynn,Charles Wilson,Emily Caffrey1(1.University of Alabama at Birmingham,School of Health Professions,Clinical and Diagnostic Science...TENORM Regulation in the United States of America post-West Virginia vs.EPA Spenser Lynn,Charles Wilson,Emily Caffrey1(1.University of Alabama at Birmingham,School of Health Professions,Clinical and Diagnostic Sciences,Health Physics Program,1720 University Blvd,Birmingham,AL 35294)Abstract:The regulation of technologically enhanced naturally occurring radioactive materials(TENORM)in the United States of America consists of fragmentary rules split between the federal and state governments.展开更多
Effects of High Temperature and High Humidity on the Degree of Ocular Damage Caused by 60 GHz Millimeter Wave Exposure Masami Kojima1,2,Takafumi Tasaki3,4,Toshio Kamijo5,Aki Hada5,Yukihisa Suzuki5,Masateru Ikehata6,Hi...Effects of High Temperature and High Humidity on the Degree of Ocular Damage Caused by 60 GHz Millimeter Wave Exposure Masami Kojima1,2,Takafumi Tasaki3,4,Toshio Kamijo5,Aki Hada5,Yukihisa Suzuki5,Masateru Ikehata6,Hiroshi Sasaki1,2(1.Division of Vision Research for Environmental Health,Medical Research Institute,Kanazawa Medical University,Kahoku,Japan;2.Department of Ophthalmology,Kanazawa Medical University,Kahoku,Japan;3.Division of Protein Regulation Research,Medical Research Institute;4.Department of Medical Zoology,Kanazawa Medical University,Kahoku,Japan;5.Department of Electrical Engineering and Computer Science,Graduate School of Systems Design,Tokyo Metropolitan University,Tokyo,Japan;6.Comfort Science and Engineering Laboratory,Human Science Division,Railway Technical Research Institute,Tokyo,Japan)Abstract:Millimeter waves(MMW)are pervasive in society;however,studies on the biological effects of MMWexposure are usually performed in laboratory settings not reflecting global environmental diversity.We investigated the effects of a 6 min exposure to 60 GHz MMW(wavelength,5.0 mm)at incident power densities of 200 and 300 mW cm-2 in eyes(exposed right eyes vs.unexposed left eyes)under various ambient temperature/relative humidity environments(24℃/50%,45℃/20%,and 45℃/80%)using an in vivo rabbit model.Correlations were examined with adverse ocular events,including corneal epithelial damage(assessed using fluorescein staining),corneal opacity(evaluated by slit-lamp microscopy)。展开更多
Graphical abstracts(GAs)are emerging as a pivotal tool in medical literature,enhancing the dissemination and comprehension of complex clinical data through visual summaries.This editorial highlights the significant ad...Graphical abstracts(GAs)are emerging as a pivotal tool in medical literature,enhancing the dissemination and comprehension of complex clinical data through visual summaries.This editorial highlights the significant advantages of GAs,including improved clarity,increased reader engagement,and enhanced visibility of research findings.By transforming intricate scientific data into accessible visual formats,these abstracts facilitate quick and effective knowledge transfer,crucial in clinical decision-making and patient care.However,challenges such as potential data misrepresentation due to oversimplification,the skill gap in graphic design among researchers,and the lack of standardized creation guidelines pose barriers to their widespread adoption.Additionally,while software such as Adobe Illustrator,BioRender,and Canva are commonly employed to create these visuals,not all researchers may be proficient in their use.To address these issues,we recommend that academic journals establish clear guidelines and provide necessary design training to researchers.This proactive approach will ensure the creation of high-quality GAs,promote their standardization,and expand their use in clinical reporting,ultimately benefiting the medical community and improving healthcare outcomes.展开更多
Automatically generating a brief summary for legal-related public opinion news(LPO-news,which contains legal words or phrases)plays an important role in rapid and effective public opinion disposal.For LPO-news,the cri...Automatically generating a brief summary for legal-related public opinion news(LPO-news,which contains legal words or phrases)plays an important role in rapid and effective public opinion disposal.For LPO-news,the critical case elements which are significant parts of the summary may be mentioned several times in the reader comments.Consequently,we investigate the task of comment-aware abstractive text summarization for LPO-news,which can generate salient summary by learning pivotal case elements from the reader comments.In this paper,we present a hierarchical comment-aware encoder(HCAE),which contains four components:1)a traditional sequenceto-sequence framework as our baseline;2)a selective denoising module to filter the noisy of comments and distinguish the case elements;3)a merge module by coupling the source article and comments to yield comment-aware context representation;4)a recoding module to capture the interaction among the source article words conditioned on the comments.Extensive experiments are conducted on a large dataset of legal public opinion news collected from micro-blog,and results show that the proposed model outperforms several existing state-of-the-art baseline models under the ROUGE metrics.展开更多
Text summarization is an important task in natural language processing and it has been applied in many applications.Recently,abstractive summarization has attracted many attentions.However,the traditional evaluation m...Text summarization is an important task in natural language processing and it has been applied in many applications.Recently,abstractive summarization has attracted many attentions.However,the traditional evaluation metrics that consider little semantic information,are unsuitable for evaluating the quality of deep learning based abstractive summarization models,since these models may generate new words that do not exist in the original text.Moreover,the out-of-vocabulary(OOV)problem that affects the evaluation results,has not been well solved yet.To address these issues,we propose a novel model called ENMS,to enhance existing N-gram based evaluation metrics with semantics.To be specific,we present two types of methods:N-gram based Semantic Matching(NSM for short),and N-gram based Semantic Similarity(NSS for short),to improve several widely-used evaluation metrics including ROUGE(Recall-Oriented Understudy for Gisting Evaluation),BLEU(Bilingual Evaluation Understudy),etc.NSM and NSS work in different ways.The former calculates the matching degree directly,while the latter mainly improves the similarity measurement.Moreover we propose an N-gram representation mechanism to explore the vector representation of N-grams(including skip-grams).It serves as the basis of our ENMS model,in which we exploit some simple but effective integration methods to solve the OOV problem efficiently.Experimental results over the TAC AESOP dataset show that the metrics improved by our methods are well correlated with human judgements and can be used to better evaluate abstractive summarization methods.展开更多
From a distance,they look like vivid pieces of abstract art-but move a little closer and dozens of small and characterful portraits shine out of the work.The ambitious idea of the City of Portraits project,a decade in...From a distance,they look like vivid pieces of abstract art-but move a little closer and dozens of small and characterful portraits shine out of the work.The ambitious idea of the City of Portraits project,a decade in the making and nowhere near complete,is to record the faces of all 1,800 people who live in Britain's smallest city,St Davids in south-west Wales.展开更多
The authors regret that in the original article,the structure of(–)-swainsonine(1)in Graphical abstract,Fig.1,Schemes 1 and 3 was incorrect.The correct structure is shown here.
This study systematically analyzes the genre structure and linguistic features of 42 English abstracts from six internationally renowned medical journals,based on the revised CARS model proposed by Swales.The research...This study systematically analyzes the genre structure and linguistic features of 42 English abstracts from six internationally renowned medical journals,based on the revised CARS model proposed by Swales.The research findings indicate that medical abstracts typically follow a three-step structure:“Establishing a Research Territory-Establishing a Research Niche-Occupying the Niche”,where the steps“Research Purpose”and“Research Results”are the most frequently utilized,forming the core content of the abstracts.Within the sequence of moves,81%conform to conventional patterns,while a minority of samples exhibit unconventional structures such as inversion,cycling,and repetition.In terms of linguistic features,the present simple tense and active voice are predominantly used,reflecting the universality of the research and the author’s agency;conversely,the simple past tense and passive voice are primarily employed to describe research methods and processes.This study reveals the writing conventions of medical abstracts,providing empirical evidence and genre reference for non-native scholars in the preparation and publication of their work in international journals.展开更多
Knowledge graphs convey precise semantic information that can be effectively interpreted by neural networks,and generating descriptive text based on these graphs places significant emphasis on content consistency.Howe...Knowledge graphs convey precise semantic information that can be effectively interpreted by neural networks,and generating descriptive text based on these graphs places significant emphasis on content consistency.However,knowledge graphs are inadequate for providing additional linguistic features such as paragraph structure and expressive modes,making it challenging to ensure content coherence in generating text that spans multiple sentences.This lack of coherence can further compromise the overall consistency of the content within a paragraph.In this work,we present the generation of scientific abstracts by leveraging knowledge graphs,with a focus on enhancing both content consistency and coherence.In particular,we construct the ACL Abstract Graph Dataset(ACL-AGD)which pairs knowledge graphs with text,incorporating sentence labels to guide text structure and diverse expressions.We then implement a Siamese network to complement and concretize the entities and relations based on paragraph structure by accomplishing two tasks:graph-to-text generation and entity alignment.Extensive experiments demonstrate that the logical paragraphs generated by our method exhibit entities with a uniform position distribution and appropriate frequency.In terms of content,our method accurately represents the information encoded in the knowledge graph,prevents the generation of irrelevant content,and achieves coherent and non-redundant adjacent sentences,even with a shared knowledge graph.展开更多
General Information Journal of Chinese Pharmaceutical Sciences(JCPS)is a peer-reviewed bimonthly journal founded in 1992.JCPS has been indexed in the Core Journals of China's science and technology field.At presen...General Information Journal of Chinese Pharmaceutical Sciences(JCPS)is a peer-reviewed bimonthly journal founded in 1992.JCPS has been indexed in the Core Journals of China's science and technology field.At present it has been included by Chemical Abstracts(CA),UIPD,Index of Copurmicus(IC),CABI,SCOPUS,JSTChina,DOAJ,EBSCO,CSTPCD,Chinese Science Citation Database(CSCD),the Chinese National Knowledge Infrastructure(CNKI)and World Journal Clout Index(WJCI)Report。展开更多
文摘The rise of social media platforms has revolutionized communication, enabling the exchange of vast amounts of data through text, audio, images, and videos. These platforms have become critical for sharing opinions and insights, influencing daily habits, and driving business, political, and economic decisions. Text posts are particularly significant, and natural language processing (NLP) has emerged as a powerful tool for analyzing such data. While traditional NLP methods have been effective for structured media, social media content poses unique challenges due to its informal and diverse nature. This has spurred the development of new techniques tailored for processing and extracting insights from unstructured user-generated text. One key application of NLP is the summarization of user comments to manage overwhelming content volumes. Abstractive summarization has proven highly effective in generating concise, human-like summaries, offering clear overviews of key themes and sentiments. This enhances understanding and engagement while reducing cognitive effort for users. For businesses, summarization provides actionable insights into customer preferences and feedback, enabling faster trend analysis, improved responsiveness, and strategic adaptability. By distilling complex data into manageable insights, summarization plays a vital role in improving user experiences and empowering informed decision-making in a data-driven landscape. This paper proposes a new implementation framework by fine-tuning and parameterizing Transformer Large Language Models to manage and maintain linguistic and semantic components in abstractive summary generation. The system excels in transforming large volumes of data into meaningful summaries, as evidenced by its strong performance across metrics like fluency, consistency, readability, and semantic coherence.
基金supported by the National Social Science Foundation of China(2017CG29)the Science and Technology Research Project of Chongqing Municipal Education Commission(2019CJ50)the Natural Science Foundation of Chongqing(2017CC29).
文摘The existing abstractive text summarisation models only consider the word sequence correlations between the source document and the reference summary,and the summary generated by models lacks the cover of the subject of source document due to models'small perspective.In order to make up these disadvantages,a multi‐domain attention pointer(MDA‐Pointer)abstractive summarisation model is proposed in this work.First,the model uses bidirectional long short‐term memory to encode,respectively,the word and sentence sequence of source document for obtaining the semantic representations at word and sentence level.Furthermore,the multi‐domain attention mechanism between the semantic representations and the summary word is established,and the proposed model can generate summary words under the proposed attention mechanism based on the words and sen-tences.Then,the words are extracted from the vocabulary or the original word sequences through the pointer network to form the summary,and the coverage mechanism is introduced,respectively,into word and sentence level to reduce the redundancy of sum-mary content.Finally,experiment validation is conducted on CNN/Daily Mail dataset.ROUGE evaluation indexes of the model without and with the coverage mechanism are improved respectively,and the results verify the validation of model proposed by this paper.
基金supported by National Natural Science Foundation of China(62276058,61902057,41774063)Fundamental Research Funds for the Central Universities(N2217003)Joint Fund of Science&Technology Department of Liaoning Province and State Key Laboratory of Robotics,China(2020-KF-12-11).
文摘A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary.Therefore,in this paper,a simple and weakly supervised framework considering factual consistency is proposed to generate a summary of city-based complaint reports without pre-labeled sentences/words.Furthermore,it considers the importance of entity in complaint reports to ensure factual consistency of summary.Experimental results on the customer review datasets(Yelp and Amazon)and complaint report dataset(complaint reports of Shenyang in China)show that the proposed framework outperforms state-of-the-art approaches in ROUGE scores and human evaluation.It unveils the effectiveness of our approach to helping in dealing with complaint reports.
基金funded by Vietnam National Foundation for Science and Technology Development(NAFOSTED)under Grant Number 102.05-2020.26。
文摘Text summarization aims to generate a concise version of the original text.The longer the summary text is,themore detailed it will be fromthe original text,and this depends on the intended use.Therefore,the problem of generating summary texts with desired lengths is a vital task to put the research into practice.To solve this problem,in this paper,we propose a new method to integrate the desired length of the summarized text into the encoder-decoder model for the abstractive text summarization problem.This length parameter is integrated into the encoding phase at each self-attention step and the decoding process by preserving the remaining length for calculating headattention in the generation process and using it as length embeddings added to theword embeddings.We conducted experiments for the proposed model on the two data sets,Cable News Network(CNN)Daily and NEWSROOM,with different desired output lengths.The obtained results show the proposed model’s effectiveness compared with related studies.
文摘TENORM Regulation in the United States of America post-West Virginia vs.EPA Spenser Lynn,Charles Wilson,Emily Caffrey1(1.University of Alabama at Birmingham,School of Health Professions,Clinical and Diagnostic Sciences,Health Physics Program,1720 University Blvd,Birmingham,AL 35294)Abstract:The regulation of technologically enhanced naturally occurring radioactive materials(TENORM)in the United States of America consists of fragmentary rules split between the federal and state governments.
文摘Effects of High Temperature and High Humidity on the Degree of Ocular Damage Caused by 60 GHz Millimeter Wave Exposure Masami Kojima1,2,Takafumi Tasaki3,4,Toshio Kamijo5,Aki Hada5,Yukihisa Suzuki5,Masateru Ikehata6,Hiroshi Sasaki1,2(1.Division of Vision Research for Environmental Health,Medical Research Institute,Kanazawa Medical University,Kahoku,Japan;2.Department of Ophthalmology,Kanazawa Medical University,Kahoku,Japan;3.Division of Protein Regulation Research,Medical Research Institute;4.Department of Medical Zoology,Kanazawa Medical University,Kahoku,Japan;5.Department of Electrical Engineering and Computer Science,Graduate School of Systems Design,Tokyo Metropolitan University,Tokyo,Japan;6.Comfort Science and Engineering Laboratory,Human Science Division,Railway Technical Research Institute,Tokyo,Japan)Abstract:Millimeter waves(MMW)are pervasive in society;however,studies on the biological effects of MMWexposure are usually performed in laboratory settings not reflecting global environmental diversity.We investigated the effects of a 6 min exposure to 60 GHz MMW(wavelength,5.0 mm)at incident power densities of 200 and 300 mW cm-2 in eyes(exposed right eyes vs.unexposed left eyes)under various ambient temperature/relative humidity environments(24℃/50%,45℃/20%,and 45℃/80%)using an in vivo rabbit model.Correlations were examined with adverse ocular events,including corneal epithelial damage(assessed using fluorescein staining),corneal opacity(evaluated by slit-lamp microscopy)。
文摘Graphical abstracts(GAs)are emerging as a pivotal tool in medical literature,enhancing the dissemination and comprehension of complex clinical data through visual summaries.This editorial highlights the significant advantages of GAs,including improved clarity,increased reader engagement,and enhanced visibility of research findings.By transforming intricate scientific data into accessible visual formats,these abstracts facilitate quick and effective knowledge transfer,crucial in clinical decision-making and patient care.However,challenges such as potential data misrepresentation due to oversimplification,the skill gap in graphic design among researchers,and the lack of standardized creation guidelines pose barriers to their widespread adoption.Additionally,while software such as Adobe Illustrator,BioRender,and Canva are commonly employed to create these visuals,not all researchers may be proficient in their use.To address these issues,we recommend that academic journals establish clear guidelines and provide necessary design training to researchers.This proactive approach will ensure the creation of high-quality GAs,promote their standardization,and expand their use in clinical reporting,ultimately benefiting the medical community and improving healthcare outcomes.
基金supported by the National Key Research and Development Program of China (2018YFC0830105,2018YFC 0830101,2018YFC0830100)the National Natural Science Foundation of China (Grant Nos.61972186,61762056,61472168)+1 种基金the Yunnan Provincial Major Science and Technology Special Plan Projects (202002AD080001)the General Projects of Basic Research in Yunnan Province (202001AT070046,202001AT070047).
文摘Automatically generating a brief summary for legal-related public opinion news(LPO-news,which contains legal words or phrases)plays an important role in rapid and effective public opinion disposal.For LPO-news,the critical case elements which are significant parts of the summary may be mentioned several times in the reader comments.Consequently,we investigate the task of comment-aware abstractive text summarization for LPO-news,which can generate salient summary by learning pivotal case elements from the reader comments.In this paper,we present a hierarchical comment-aware encoder(HCAE),which contains four components:1)a traditional sequenceto-sequence framework as our baseline;2)a selective denoising module to filter the noisy of comments and distinguish the case elements;3)a merge module by coupling the source article and comments to yield comment-aware context representation;4)a recoding module to capture the interaction among the source article words conditioned on the comments.Extensive experiments are conducted on a large dataset of legal public opinion news collected from micro-blog,and results show that the proposed model outperforms several existing state-of-the-art baseline models under the ROUGE metrics.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos.62172149,61632009,62172159,and 62172372the Natural Science Foundation of Hunan Province of China under Grant No.2021JJ30137the Open Project of ZHEJIANG LAB under Grant No.2019KE0AB02.
文摘Text summarization is an important task in natural language processing and it has been applied in many applications.Recently,abstractive summarization has attracted many attentions.However,the traditional evaluation metrics that consider little semantic information,are unsuitable for evaluating the quality of deep learning based abstractive summarization models,since these models may generate new words that do not exist in the original text.Moreover,the out-of-vocabulary(OOV)problem that affects the evaluation results,has not been well solved yet.To address these issues,we propose a novel model called ENMS,to enhance existing N-gram based evaluation metrics with semantics.To be specific,we present two types of methods:N-gram based Semantic Matching(NSM for short),and N-gram based Semantic Similarity(NSS for short),to improve several widely-used evaluation metrics including ROUGE(Recall-Oriented Understudy for Gisting Evaluation),BLEU(Bilingual Evaluation Understudy),etc.NSM and NSS work in different ways.The former calculates the matching degree directly,while the latter mainly improves the similarity measurement.Moreover we propose an N-gram representation mechanism to explore the vector representation of N-grams(including skip-grams).It serves as the basis of our ENMS model,in which we exploit some simple but effective integration methods to solve the OOV problem efficiently.Experimental results over the TAC AESOP dataset show that the metrics improved by our methods are well correlated with human judgements and can be used to better evaluate abstractive summarization methods.
文摘From a distance,they look like vivid pieces of abstract art-but move a little closer and dozens of small and characterful portraits shine out of the work.The ambitious idea of the City of Portraits project,a decade in the making and nowhere near complete,is to record the faces of all 1,800 people who live in Britain's smallest city,St Davids in south-west Wales.
文摘The authors regret that in the original article,the structure of(–)-swainsonine(1)in Graphical abstract,Fig.1,Schemes 1 and 3 was incorrect.The correct structure is shown here.
文摘This study systematically analyzes the genre structure and linguistic features of 42 English abstracts from six internationally renowned medical journals,based on the revised CARS model proposed by Swales.The research findings indicate that medical abstracts typically follow a three-step structure:“Establishing a Research Territory-Establishing a Research Niche-Occupying the Niche”,where the steps“Research Purpose”and“Research Results”are the most frequently utilized,forming the core content of the abstracts.Within the sequence of moves,81%conform to conventional patterns,while a minority of samples exhibit unconventional structures such as inversion,cycling,and repetition.In terms of linguistic features,the present simple tense and active voice are predominantly used,reflecting the universality of the research and the author’s agency;conversely,the simple past tense and passive voice are primarily employed to describe research methods and processes.This study reveals the writing conventions of medical abstracts,providing empirical evidence and genre reference for non-native scholars in the preparation and publication of their work in international journals.
文摘Knowledge graphs convey precise semantic information that can be effectively interpreted by neural networks,and generating descriptive text based on these graphs places significant emphasis on content consistency.However,knowledge graphs are inadequate for providing additional linguistic features such as paragraph structure and expressive modes,making it challenging to ensure content coherence in generating text that spans multiple sentences.This lack of coherence can further compromise the overall consistency of the content within a paragraph.In this work,we present the generation of scientific abstracts by leveraging knowledge graphs,with a focus on enhancing both content consistency and coherence.In particular,we construct the ACL Abstract Graph Dataset(ACL-AGD)which pairs knowledge graphs with text,incorporating sentence labels to guide text structure and diverse expressions.We then implement a Siamese network to complement and concretize the entities and relations based on paragraph structure by accomplishing two tasks:graph-to-text generation and entity alignment.Extensive experiments demonstrate that the logical paragraphs generated by our method exhibit entities with a uniform position distribution and appropriate frequency.In terms of content,our method accurately represents the information encoded in the knowledge graph,prevents the generation of irrelevant content,and achieves coherent and non-redundant adjacent sentences,even with a shared knowledge graph.
文摘General Information Journal of Chinese Pharmaceutical Sciences(JCPS)is a peer-reviewed bimonthly journal founded in 1992.JCPS has been indexed in the Core Journals of China's science and technology field.At present it has been included by Chemical Abstracts(CA),UIPD,Index of Copurmicus(IC),CABI,SCOPUS,JSTChina,DOAJ,EBSCO,CSTPCD,Chinese Science Citation Database(CSCD),the Chinese National Knowledge Infrastructure(CNKI)and World Journal Clout Index(WJCI)Report。
