TeKET: a tree-based unsupervised keyphrase extraction technique
Automatic keyphrase extraction techniques aim to extract quality keyphrases for higher level summarization of a document. Majority of the existing techniques are mainly domain-specific, which require application domain knowledge and employ higher order statistical methods, and computationally expe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2020
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/29348/ |
| _version_ | 1848827277164412928 |
|---|---|
| author | Rabby, Gollam Md Saiful, Azad Mufti, Mahmud Kamal Z., Zamli Mohammed Mostafizur, Rahman |
| author_facet | Rabby, Gollam Md Saiful, Azad Mufti, Mahmud Kamal Z., Zamli Mohammed Mostafizur, Rahman |
| author_sort | Rabby, Gollam |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Automatic keyphrase extraction techniques aim to extract quality keyphrases for higher level summarization of a document.
Majority of the existing techniques are mainly domain-specific, which require application domain knowledge and employ
higher order statistical methods, and computationally expensive and require large train data, which is rare for many
applications. Overcoming these issues, this paper proposes a new unsupervised keyphrase extraction technique. The
proposed unsupervised keyphrase extraction technique, named TeKET or Tree-based Keyphrase Extraction Technique, is
a domain-independent technique that employs limited statistical knowledge and requires no train data. This technique
also introduces a new variant of a binary tree, called KeyPhrase Extraction (KePhEx) tree, to extract final keyphrases
from candidate keyphrases. In addition, a measure, called Cohesiveness Index or CI, is derived which denotes a given
node’s degree of cohesiveness with respect to the root. The CI is used in flexibly extracting final keyphrases from the
KePhEx tree and is co-utilized in the ranking process. The effectiveness of the proposed technique and its domain and
language independence are experimentally evaluated using available benchmark corpora, namely SemEval-2010 (a scientific
articles dataset), Theses100 (a thesis dataset), and a German Research Article dataset, respectively. The acquired results
are compared with other relevant unsupervised techniques belonging to both statistical and graph-based techniques. The
obtained results demonstrate the improved performance of the proposed technique over other compared techniques in terms
of precision, recall, and F1 scores. |
| first_indexed | 2025-11-15T03:58:09Z |
| format | Article |
| id | ump-29348 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:58:09Z |
| publishDate | 2020 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-293482025-09-26T08:37:11Z https://umpir.ump.edu.my/id/eprint/29348/ TeKET: a tree-based unsupervised keyphrase extraction technique Rabby, Gollam Md Saiful, Azad Mufti, Mahmud Kamal Z., Zamli Mohammed Mostafizur, Rahman QA75 Electronic computers. Computer science Automatic keyphrase extraction techniques aim to extract quality keyphrases for higher level summarization of a document. Majority of the existing techniques are mainly domain-specific, which require application domain knowledge and employ higher order statistical methods, and computationally expensive and require large train data, which is rare for many applications. Overcoming these issues, this paper proposes a new unsupervised keyphrase extraction technique. The proposed unsupervised keyphrase extraction technique, named TeKET or Tree-based Keyphrase Extraction Technique, is a domain-independent technique that employs limited statistical knowledge and requires no train data. This technique also introduces a new variant of a binary tree, called KeyPhrase Extraction (KePhEx) tree, to extract final keyphrases from candidate keyphrases. In addition, a measure, called Cohesiveness Index or CI, is derived which denotes a given node’s degree of cohesiveness with respect to the root. The CI is used in flexibly extracting final keyphrases from the KePhEx tree and is co-utilized in the ranking process. The effectiveness of the proposed technique and its domain and language independence are experimentally evaluated using available benchmark corpora, namely SemEval-2010 (a scientific articles dataset), Theses100 (a thesis dataset), and a German Research Article dataset, respectively. The acquired results are compared with other relevant unsupervised techniques belonging to both statistical and graph-based techniques. The obtained results demonstrate the improved performance of the proposed technique over other compared techniques in terms of precision, recall, and F1 scores. Springer 2020 Article PeerReviewed pdf en cc_by_4 https://umpir.ump.edu.my/id/eprint/29348/1/20.%20TeKET%20-%20a%20tree%20based%20unsupervised%20keyphrase%20extraction%20technique.pdf Rabby, Gollam and Md Saiful, Azad and Mufti, Mahmud and Kamal Z., Zamli and Mohammed Mostafizur, Rahman (2020) TeKET: a tree-based unsupervised keyphrase extraction technique. Cognitive Computation, 12 (4). pp. 811-833. ISSN 1866 - 9956. (Published) https://doi.org/10.1007/s12559-019-09706-3 https://doi.org/10.1007/s12559-019-09706-3 https://doi.org/10.1007/s12559-019-09706-3 |
| spellingShingle | QA75 Electronic computers. Computer science Rabby, Gollam Md Saiful, Azad Mufti, Mahmud Kamal Z., Zamli Mohammed Mostafizur, Rahman TeKET: a tree-based unsupervised keyphrase extraction technique |
| title | TeKET: a tree-based unsupervised keyphrase extraction technique |
| title_full | TeKET: a tree-based unsupervised keyphrase extraction technique |
| title_fullStr | TeKET: a tree-based unsupervised keyphrase extraction technique |
| title_full_unstemmed | TeKET: a tree-based unsupervised keyphrase extraction technique |
| title_short | TeKET: a tree-based unsupervised keyphrase extraction technique |
| title_sort | teket: a tree-based unsupervised keyphrase extraction technique |
| topic | QA75 Electronic computers. Computer science |
| url | https://umpir.ump.edu.my/id/eprint/29348/ https://umpir.ump.edu.my/id/eprint/29348/ https://umpir.ump.edu.my/id/eprint/29348/ |