Purpose:Automatic keyphrase extraction(AKE)is an important task for grasping the main points of the text.In this paper,we aim to combine the benefits of sequence labeling formulation and pretrained language model to p...Purpose:Automatic keyphrase extraction(AKE)is an important task for grasping the main points of the text.In this paper,we aim to combine the benefits of sequence labeling formulation and pretrained language model to propose an automatic keyphrase extraction model for Chinese scientific research.Design/methodology/approach:We regard AKE from Chinese text as a character-level sequence labeling task to avoid segmentation errors of Chinese tokenizer and initialize our model with pretrained language model BERT,which was released by Google in 2018.We collect data from Chinese Science Citation Database and construct a large-scale dataset from medical domain,which contains 100,000 abstracts as training set,6,000 abstracts as development set and 3,094 abstracts as test set.We use unsupervised keyphrase extraction methods including term frequency(TF),TF-IDF,TextRank and supervised machine learning methods including Conditional Random Field(CRF),Bidirectional Long Short Term Memory Network(BiLSTM),and BiLSTM-CRF as baselines.Experiments are designed to compare word-level and character-level sequence labeling approaches on supervised machine learning models and BERT-based models.Findings:Compared with character-level BiLSTM-CRF,the best baseline model with F1 score of 50.16%,our character-level sequence labeling model based on BERT obtains F1 score of 59.80%,getting 9.64%absolute improvement.Research limitations:We just consider automatic keyphrase extraction task rather than keyphrase generation task,so only keyphrases that are occurred in the given text can be extracted.In addition,our proposed dataset is not suitable for dealing with nested keyphrases.Practical implications:We make our character-level IOB format dataset of Chinese Automatic Keyphrase Extraction from scientific Chinese medical abstracts(CAKE)publicly available for the benefits of research community,which is available at:https://github.com/possible1402/Dataset-For-Chinese-Medical-Keyphrase-Extraction.Originality/value:By designing comparative experiments,our study demonstrates that character-level formulation is more suitable for Chinese automatic keyphrase extraction task under the general trend of pretrained language models.And our proposed dataset provides a unified method for model evaluation and can promote the development of Chinese automatic keyphrase extraction to some extent.展开更多
Purpose: The thrust of this paper is to present a method for improving the accuracy of automatic indexing of Chinese-English mixed documents.Design/methodology/approach: Based on the inherent characteristics of Chines...Purpose: The thrust of this paper is to present a method for improving the accuracy of automatic indexing of Chinese-English mixed documents.Design/methodology/approach: Based on the inherent characteristics of Chinese-English mixed texts and the cybernetics theory,we proposed an integrated control method for indexing documents. It consists of 'feed-forward control','in-progress control' and 'feed-back control',aiming at improving the accuracy of automatic indexing of Chinese-English mixed documents. An experiment was conducted to investigate the effect of our proposed method.Findings: This method distinguishes Chinese and English documents in grammatical structures and word formation rules. Through the implementation of this method in the three phases of automatic indexing for the Chinese-English mixed documents,the results were encouraging. The precision increased from 88.54% to 97.10% and recall improved from97.37% to 99.47%.Research limitations: The indexing method is relatively complicated and the whole indexing process requires substantial human intervention. Due to pattern matching based on a bruteforce(BF) approach,the indexing efficiency has been reduced to some extent.Practical implications: The research is of both theoretical significance and practical value in improving the accuracy of automatic indexing of multilingual documents(not confined to Chinese-English mixed documents). The proposed method will benefit not only the indexing of life science documents but also the indexing of documents in other subject areas.Originality/value: So far,few studies have been published about the method for increasing the accuracy of multilingual automatic indexing. This study will provide insights into the automatic indexing of multilingual documents,especially Chinese-English mixed documents.展开更多
Automatic word-segmentation is widely used in the ambiguity cancellation when processing large-scale real text,but during the process of unknown word detection in Chinese word segmentation,many detected word candidate...Automatic word-segmentation is widely used in the ambiguity cancellation when processing large-scale real text,but during the process of unknown word detection in Chinese word segmentation,many detected word candidates are invalid.These false unknown word candidates deteriorate the overall segmentation accuracy,as it will affect the segmentation accuracy of known words.In this paper,we propose several methods for reducing the difficulties and improving the accuracy of the word-segmentation of written Chinese,such as full segmentation of a sentence,processing the duplicative word,idioms and statistical identification for unknown words.A simulation shows the feasibility of our proposed methods in improving the accuracy of word-segmentation of Chinese.展开更多
基金This work is supported by the project“Research on Methods and Technologies of Scientific Researcher Entity Linking and Subject Indexing”(Grant No.G190091)from the National Science Library,Chinese Academy of Sciencesthe project“Design and Research on a Next Generation of Open Knowledge Services System and Key Technologies”(2019XM55).
文摘Purpose:Automatic keyphrase extraction(AKE)is an important task for grasping the main points of the text.In this paper,we aim to combine the benefits of sequence labeling formulation and pretrained language model to propose an automatic keyphrase extraction model for Chinese scientific research.Design/methodology/approach:We regard AKE from Chinese text as a character-level sequence labeling task to avoid segmentation errors of Chinese tokenizer and initialize our model with pretrained language model BERT,which was released by Google in 2018.We collect data from Chinese Science Citation Database and construct a large-scale dataset from medical domain,which contains 100,000 abstracts as training set,6,000 abstracts as development set and 3,094 abstracts as test set.We use unsupervised keyphrase extraction methods including term frequency(TF),TF-IDF,TextRank and supervised machine learning methods including Conditional Random Field(CRF),Bidirectional Long Short Term Memory Network(BiLSTM),and BiLSTM-CRF as baselines.Experiments are designed to compare word-level and character-level sequence labeling approaches on supervised machine learning models and BERT-based models.Findings:Compared with character-level BiLSTM-CRF,the best baseline model with F1 score of 50.16%,our character-level sequence labeling model based on BERT obtains F1 score of 59.80%,getting 9.64%absolute improvement.Research limitations:We just consider automatic keyphrase extraction task rather than keyphrase generation task,so only keyphrases that are occurred in the given text can be extracted.In addition,our proposed dataset is not suitable for dealing with nested keyphrases.Practical implications:We make our character-level IOB format dataset of Chinese Automatic Keyphrase Extraction from scientific Chinese medical abstracts(CAKE)publicly available for the benefits of research community,which is available at:https://github.com/possible1402/Dataset-For-Chinese-Medical-Keyphrase-Extraction.Originality/value:By designing comparative experiments,our study demonstrates that character-level formulation is more suitable for Chinese automatic keyphrase extraction task under the general trend of pretrained language models.And our proposed dataset provides a unified method for model evaluation and can promote the development of Chinese automatic keyphrase extraction to some extent.
基金supported by the Shanghai International Studies University(Grant No.:2011114061)
文摘Purpose: The thrust of this paper is to present a method for improving the accuracy of automatic indexing of Chinese-English mixed documents.Design/methodology/approach: Based on the inherent characteristics of Chinese-English mixed texts and the cybernetics theory,we proposed an integrated control method for indexing documents. It consists of 'feed-forward control','in-progress control' and 'feed-back control',aiming at improving the accuracy of automatic indexing of Chinese-English mixed documents. An experiment was conducted to investigate the effect of our proposed method.Findings: This method distinguishes Chinese and English documents in grammatical structures and word formation rules. Through the implementation of this method in the three phases of automatic indexing for the Chinese-English mixed documents,the results were encouraging. The precision increased from 88.54% to 97.10% and recall improved from97.37% to 99.47%.Research limitations: The indexing method is relatively complicated and the whole indexing process requires substantial human intervention. Due to pattern matching based on a bruteforce(BF) approach,the indexing efficiency has been reduced to some extent.Practical implications: The research is of both theoretical significance and practical value in improving the accuracy of automatic indexing of multilingual documents(not confined to Chinese-English mixed documents). The proposed method will benefit not only the indexing of life science documents but also the indexing of documents in other subject areas.Originality/value: So far,few studies have been published about the method for increasing the accuracy of multilingual automatic indexing. This study will provide insights into the automatic indexing of multilingual documents,especially Chinese-English mixed documents.
文摘Automatic word-segmentation is widely used in the ambiguity cancellation when processing large-scale real text,but during the process of unknown word detection in Chinese word segmentation,many detected word candidates are invalid.These false unknown word candidates deteriorate the overall segmentation accuracy,as it will affect the segmentation accuracy of known words.In this paper,we propose several methods for reducing the difficulties and improving the accuracy of the word-segmentation of written Chinese,such as full segmentation of a sentence,processing the duplicative word,idioms and statistical identification for unknown words.A simulation shows the feasibility of our proposed methods in improving the accuracy of word-segmentation of Chinese.
