Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
We use a lot of devices in our daily life to communicate with others. In this modern world, people use email, Facebook, Twitter, and many other social network sites for exchanging information. People lose their valuab...We use a lot of devices in our daily life to communicate with others. In this modern world, people use email, Facebook, Twitter, and many other social network sites for exchanging information. People lose their valuable time misspelling and retyping, and some people are not happy to type large sentences because they face unnecessary words or grammatical issues. So, for this reason, word predictive systems help to exchange textual information more quickly, easier, and comfortably for all people. These systems predict the next most probable words and give users to choose of the needed word from these suggested words. Word prediction can help the writer by predicting the next word and helping complete the sentence correctly. This research aims to forecast the most suitable next word to complete a sentence for any given context. In this research, we have worked on the Bangla language. We have presented a process that can expect the next maximum probable and proper words and suggest a complete sentence using predicted words. In this research, GRU-based RNN has been used on the N-gram dataset to develop the proposed model. We collected a large dataset using multiple sources in the Bangla language and also compared it to the other approaches that have been used such as LSTM, and Naive Bayes. But this suggested approach provides excellent exactness than others. Here, the Unigram model provides 88.22%, Bi-gram model is 99.24%, Tri-gram model is 97.69%, and 4-gram and 5-gram models provide 99.43% and 99.78% on average accurateness. We think that our proposed method profound impression on Bangla search engines.展开更多
Purpose:Mo ve recognition in scientific abstracts is an NLP task of classifying sentences of the abstracts into different types of language units.To improve the performance of move recognition in scientific abstracts,...Purpose:Mo ve recognition in scientific abstracts is an NLP task of classifying sentences of the abstracts into different types of language units.To improve the performance of move recognition in scientific abstracts,a novel model of move recognition is proposed that outperforms the BERT-based method.Design/methodology/approach:Prevalent models based on BERT for sentence classification often classify sentences without considering the context of the sentences.In this paper,inspired by the BERT masked language model(MLM),we propose a novel model called the masked sentence model that integrates the content and contextual information of the sentences in move recognition.Experiments are conducted on the benchmark dataset PubMed 20K RCT in three steps.Then,we compare our model with HSLN-RNN,BERT-based and SciBERT using the same dataset.Findings:Compared with the BERT-based and SciBERT models,the F1 score of our model outperforms them by 4.96%and 4.34%,respectively,which shows the feasibility and effectiveness of the novel model and the result of our model comes closest to the state-of-theart results of HSLN-RNN at present.Research limitations:The sequential features of move labels are not considered,which might be one of the reasons why HSLN-RNN has better performance.Our model is restricted to dealing with biomedical English literature because we use a dataset from PubMed,which is a typical biomedical database,to fine-tune our model.Practical implications:The proposed model is better and simpler in identifying move structures in scientific abstracts and is worthy of text classification experiments for capturing contextual features of sentences.Originality/value:T he study proposes a masked sentence model based on BERT that considers the contextual features of the sentences in abstracts in a new way.The performance of this classification model is significantly improved by rebuilding the input layer without changing the structure of neural networks.展开更多
Purpose:To uncover the evaluation information on the academic contribution of research papers cited by peers based on the content cited by citing papers,and to provide an evidencebased tool for evaluating the academic...Purpose:To uncover the evaluation information on the academic contribution of research papers cited by peers based on the content cited by citing papers,and to provide an evidencebased tool for evaluating the academic value of cited papers.Design/methodology/approach:CiteOpinion uses a deep learning model to automatically extract citing sentences from representative citing papers;it starts with an analysis on the citing sentences,then it identifies major academic contribution points of the cited paper,positive/negative evaluations from citing authors and the changes in the subjects of subsequent citing authors by means of Recognizing Categories of Moves(problems,methods,conclusions,etc.),and sentiment analysis and topic clustering.Findings:Citing sentences in a citing paper contain substantial evidences useful for academic evaluation.They can also be used to objectively and authentically reveal the nature and degree of contribution of the cited paper reflected by citation,beyond simple citation statistics.Practical implications:The evidence-based evaluation tool CiteOpinion can provide an objective and in-depth academic value evaluation basis for the representative papers of scientific researchers,research teams,and institutions.Originality/value:No other similar practical tool is found in papers retrieved.Research limitations:There are difficulties in acquiring full text of citing papers.There is a need to refine the calculation based on the sentiment scores of citing sentences.Currently,the tool is only used for academic contribution evaluation,while its value in policy studies,technical application,and promotion of science is not yet tested.展开更多
In this paper we employ an improved Siamese neural network to assess the semantic similarity between sentences. Our model implements the function of inputting two sentences to obtain the similarity score. We design ou...In this paper we employ an improved Siamese neural network to assess the semantic similarity between sentences. Our model implements the function of inputting two sentences to obtain the similarity score. We design our model based on the Siamese network using deep Long Short-Term Memory (LSTM) Network. And we add the special attention mechanism to let the model give different words different attention while modeling sentences. The fully-connected layer is proposed to measure the complex sentence representations. Our results show that the accuracy is better than the baseline in 2016. Furthermore, it is showed that the model has the ability to model the sequence order, distribute reasonable attention and extract meanings of a sentence in different dimensions.展开更多
Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input source.The contents of video captioning are limited since few studies employed external corpus information to guide...Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input source.The contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning,which is not conducive to the accurate descrip-tion and understanding of video content.To address this issue,a novel video captioning method guided by a sentence retrieval generation network(ED-SRG)is proposed in this paper.First,a ResNeXt network model,an efficient convolutional network for online video understanding(ECO)model,and a long short-term memory(LSTM)network model are integrated to construct an encoder-decoder,which is utilized to extract the 2D features,3D features,and object features of video data respectively.These features are decoded to generate textual sentences that conform to video content for sentence retrieval.Then,a sentence-transformer network model is employed to retrieve different sentences in an external corpus that are semantically similar to the above textual sentences.The candidate sentences are screened out through similarity measurement.Finally,a novel GPT-2 network model is constructed based on GPT-2 network structure.The model introduces a designed random selector to randomly select predicted words with a high probability in the corpus,which is used to guide and generate textual sentences that are more in line with human natural language expressions.The proposed method in this paper is compared with several existing works by experiments.The results show that the indicators BLEU-4,CIDEr,ROUGE_L,and METEOR are improved by 3.1%,1.3%,0.3%,and 1.5%on a public dataset MSVD and 1.3%,0.5%,0.2%,1.9%on a public dataset MSR-VTT respectively.It can be seen that the proposed method in this paper can generate video captioning with richer semantics than several state-of-the-art approaches.展开更多
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
文摘We use a lot of devices in our daily life to communicate with others. In this modern world, people use email, Facebook, Twitter, and many other social network sites for exchanging information. People lose their valuable time misspelling and retyping, and some people are not happy to type large sentences because they face unnecessary words or grammatical issues. So, for this reason, word predictive systems help to exchange textual information more quickly, easier, and comfortably for all people. These systems predict the next most probable words and give users to choose of the needed word from these suggested words. Word prediction can help the writer by predicting the next word and helping complete the sentence correctly. This research aims to forecast the most suitable next word to complete a sentence for any given context. In this research, we have worked on the Bangla language. We have presented a process that can expect the next maximum probable and proper words and suggest a complete sentence using predicted words. In this research, GRU-based RNN has been used on the N-gram dataset to develop the proposed model. We collected a large dataset using multiple sources in the Bangla language and also compared it to the other approaches that have been used such as LSTM, and Naive Bayes. But this suggested approach provides excellent exactness than others. Here, the Unigram model provides 88.22%, Bi-gram model is 99.24%, Tri-gram model is 97.69%, and 4-gram and 5-gram models provide 99.43% and 99.78% on average accurateness. We think that our proposed method profound impression on Bangla search engines.
基金supported by the project “The demonstration system of rich semantic search application in scientific literature” (Grant No. 1734) from the Chinese Academy of Sciences
文摘Purpose:Mo ve recognition in scientific abstracts is an NLP task of classifying sentences of the abstracts into different types of language units.To improve the performance of move recognition in scientific abstracts,a novel model of move recognition is proposed that outperforms the BERT-based method.Design/methodology/approach:Prevalent models based on BERT for sentence classification often classify sentences without considering the context of the sentences.In this paper,inspired by the BERT masked language model(MLM),we propose a novel model called the masked sentence model that integrates the content and contextual information of the sentences in move recognition.Experiments are conducted on the benchmark dataset PubMed 20K RCT in three steps.Then,we compare our model with HSLN-RNN,BERT-based and SciBERT using the same dataset.Findings:Compared with the BERT-based and SciBERT models,the F1 score of our model outperforms them by 4.96%and 4.34%,respectively,which shows the feasibility and effectiveness of the novel model and the result of our model comes closest to the state-of-theart results of HSLN-RNN at present.Research limitations:The sequential features of move labels are not considered,which might be one of the reasons why HSLN-RNN has better performance.Our model is restricted to dealing with biomedical English literature because we use a dataset from PubMed,which is a typical biomedical database,to fine-tune our model.Practical implications:The proposed model is better and simpler in identifying move structures in scientific abstracts and is worthy of text classification experiments for capturing contextual features of sentences.Originality/value:T he study proposes a masked sentence model based on BERT that considers the contextual features of the sentences in abstracts in a new way.The performance of this classification model is significantly improved by rebuilding the input layer without changing the structure of neural networks.
文摘Purpose:To uncover the evaluation information on the academic contribution of research papers cited by peers based on the content cited by citing papers,and to provide an evidencebased tool for evaluating the academic value of cited papers.Design/methodology/approach:CiteOpinion uses a deep learning model to automatically extract citing sentences from representative citing papers;it starts with an analysis on the citing sentences,then it identifies major academic contribution points of the cited paper,positive/negative evaluations from citing authors and the changes in the subjects of subsequent citing authors by means of Recognizing Categories of Moves(problems,methods,conclusions,etc.),and sentiment analysis and topic clustering.Findings:Citing sentences in a citing paper contain substantial evidences useful for academic evaluation.They can also be used to objectively and authentically reveal the nature and degree of contribution of the cited paper reflected by citation,beyond simple citation statistics.Practical implications:The evidence-based evaluation tool CiteOpinion can provide an objective and in-depth academic value evaluation basis for the representative papers of scientific researchers,research teams,and institutions.Originality/value:No other similar practical tool is found in papers retrieved.Research limitations:There are difficulties in acquiring full text of citing papers.There is a need to refine the calculation based on the sentiment scores of citing sentences.Currently,the tool is only used for academic contribution evaluation,while its value in policy studies,technical application,and promotion of science is not yet tested.
文摘In this paper we employ an improved Siamese neural network to assess the semantic similarity between sentences. Our model implements the function of inputting two sentences to obtain the similarity score. We design our model based on the Siamese network using deep Long Short-Term Memory (LSTM) Network. And we add the special attention mechanism to let the model give different words different attention while modeling sentences. The fully-connected layer is proposed to measure the complex sentence representations. Our results show that the accuracy is better than the baseline in 2016. Furthermore, it is showed that the model has the ability to model the sequence order, distribute reasonable attention and extract meanings of a sentence in different dimensions.
基金supported in part by the National Natural Science Foundation of China under Grants 62273272 and 61873277in part by the Chinese Postdoctoral Science Foundation under Grant 2020M673446+1 种基金in part by the Key Research and Development Program of Shaanxi Province under Grant 2023-YBGY-243in part by the Youth Innovation Team of Shaanxi Universities.
文摘Currently,the video captioning models based on an encoder-decoder mainly rely on a single video input source.The contents of video captioning are limited since few studies employed external corpus information to guide the generation of video captioning,which is not conducive to the accurate descrip-tion and understanding of video content.To address this issue,a novel video captioning method guided by a sentence retrieval generation network(ED-SRG)is proposed in this paper.First,a ResNeXt network model,an efficient convolutional network for online video understanding(ECO)model,and a long short-term memory(LSTM)network model are integrated to construct an encoder-decoder,which is utilized to extract the 2D features,3D features,and object features of video data respectively.These features are decoded to generate textual sentences that conform to video content for sentence retrieval.Then,a sentence-transformer network model is employed to retrieve different sentences in an external corpus that are semantically similar to the above textual sentences.The candidate sentences are screened out through similarity measurement.Finally,a novel GPT-2 network model is constructed based on GPT-2 network structure.The model introduces a designed random selector to randomly select predicted words with a high probability in the corpus,which is used to guide and generate textual sentences that are more in line with human natural language expressions.The proposed method in this paper is compared with several existing works by experiments.The results show that the indicators BLEU-4,CIDEr,ROUGE_L,and METEOR are improved by 3.1%,1.3%,0.3%,and 1.5%on a public dataset MSVD and 1.3%,0.5%,0.2%,1.9%on a public dataset MSR-VTT respectively.It can be seen that the proposed method in this paper can generate video captioning with richer semantics than several state-of-the-art approaches.
