Keyphrases Extraction from Scientific Documents: Improving Machine Learning Approaches with Natural Language Processing

Krapivin, Mikalai; Autayeu, Aliaksandr; Marchese, Maurizio; Blanzieri, Enrico; Segata, Nicola

doi:10.1007/978-3-642-13654-2_12

Cited by 37 publications

(25 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Hulth2003 3 [12] dataset is a document summary dataset from the Inspec physical and engineering literature database, in which each document has two sets of keywords assigned: the manually controlled assigned keywords appear in the Inspec thesaurus instead of document, and the uncontrolled keywords, which are freely assigned by the editors; (2) Krapivin2009. Krapivin2009 4 [13] dataset has 2,304 full papers from the computer science domain, which are published by ACM in the period between 2003 and 2005, and each paper has keywords originally labeled by the authors and verified by the reviewers. In the experiments, we extract the abstracts of papers from datasets, and use user-assigned keywords as the ground truth.…”

Section: Experimental Settings a Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

An Empirical Study of TextRank for Keyword Extraction

Zhang

Yue

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As a typical keyword extraction technology, TextRank has been used in a wide variety of commercial applications, including text classification, information retrieval and clustering. In these applications, the parameters of TextRank, including the co-occurrence window size, iteration number and decay factor, are set roughly, which might affect the effectiveness of returned results. In this work, we conduct an empirical study on TextRank, towards finding optimal parameter settings for keyword extraction. The experiments are done in Hulth2003 and Krapivin2009 datasets, which are two real datasets. We first remove the stop word by an open published English stop word list XPO6. And then, we extract the word stems by Porter Stemmer. Porter Stemmer is a tool which can find the stems of words with multiple variants, discard redundant information, strengthen the filtering effect, and extract the effective features of the text fully. We carry out extensive experiments to evaluate the effects of the parameters to keywords extraction, and evaluate the effectiveness of corresponding results by Precision, Recall and Accuracy. Experimental results show that TextRank shows the best performance when setting co-occurrence window size w = 3, iteration number t = 20, decay factor c = 0.9 and rank k = 10 respectively, and the results are independent of the text length.

show abstract

Section: Experimental Settings a Datasetsmentioning

confidence: 99%

“…In this paper, we conduct an empirical study on TextRank, towards finding an optimal parameter setting for keyword extraction. The experiments are done in Hulth2003 [12] and Krapivin2009 [13] datasets. In the text preprocessing stage, we remove the stop word by an open published English stop word list XPO6.…”

Section: Introductionmentioning

confidence: 99%

An Empirical Study of TextRank for Keyword Extraction

Zhang

Yue

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…NLP techniques were used by Krapivin et al (2010) in [18] to consider machine learning approach and improve them (SVM, Local SVM, Random Forests) to solve the problem of automatic keyphrases extraction from scientific papers. Evaluation showed efficient results that can that outperform state-of-the-art Bayesian learning system KEA on the same dataset without the use of controlled vocabularies.…”

Section: Related Workmentioning

confidence: 99%

A Statistical Approach of Keyword Extraction for Efficient Retrieval

Luthra¹,

Arora²,

Mittal³

et al. 2017

IJCA

View full text Add to dashboard Cite

Large number of techniques for keyword extraction have been proposed for better matching of documents with the user's query but most of them deal with tf-idf to find the weight age of query terms in the entire document but this can result in improper result as if a term has a low term frequency in overall document but high frequency in a certain part of the document then that term can be ignored by traditional tf-idf method. Through this paper, the keyword extraction is improved using a hybrid technique in which the entire document is split into multiple domains using a master keyword and the frequency of all unique words is found in every domain . The words having high frequency are selected as candidate keywords and the final selection is made on the basis of a graph which is constructed between the keywords using Word Net. The experiments, conducted on various documents show that proposed approach outperforms other keyword extraction methodologies by enhancing document retrieval.

show abstract

“…Hulth (2003) 800 T. Nguyen (2007) 120 X. 308 A.Schutz (2013) 500 M. Krapivin (2009) 680 K. SuNam (2013) 100…”

Section: Referencesmentioning

confidence: 99%

OLAP textual aggregation approach using the Google similarity distance

Bouakkaz

Loudcher²,

Ouinten

2016

IJBIDM

View full text Add to dashboard Cite

Data warehousing and On-Line Analytical Processing (OLAP) are essential elements to decision support. In the case of textual data, decision support requires new tools, mainly textual aggregation functions, for better and faster high level analysis and decision making. Such tools will provide textual measures to users who wish to analyse documents online. In this paper, we propose a new aggregation function for textual data in an OLAP context based on the K-means method. This approach will highlight aggregates semantically richer than those provided by classical OLAP operators. The distance used in K-means is replaced by the Google similarity distance which takes into account the semantic similarity of keywords for their aggregation. The performance of our approach is analyzed and compared to other methods such as Topkeywords, TOPIC, TuBE and BienCube. The experimental study shows that our approach achieves better performances in terms of recall, precision,F-measure complexity and runtime.

show abstract

Keyphrases Extraction from Scientific Documents: Improving Machine Learning Approaches with Natural Language Processing

Cited by 37 publications

References 9 publications

An Empirical Study of TextRank for Keyword Extraction

An Empirical Study of TextRank for Keyword Extraction

A Statistical Approach of Keyword Extraction for Efficient Retrieval

OLAP textual aggregation approach using the Google similarity distance

Contact Info

Product

Resources

About