Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers) 2017
DOI: 10.18653/v1/p17-1102
|View full text |Cite
|
Sign up to set email alerts
|

PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents

Abstract: The large and growing amounts of online scholarly data present both challenges and opportunities to enhance knowledge discovery. One such challenge is to automatically extract a small set of keyphrases from a document that can accurately describe the document's content and can facilitate fast information processing. In this paper, we propose PositionRank, an unsupervised model for keyphrase extraction from scholarly documents that incorporates information from all positions of a word's occurrences into a biase… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
190
0
3

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
4
1

Relationship

1
8

Authors

Journals

citations
Cited by 266 publications
(193 citation statements)
references
References 23 publications
0
190
0
3
Order By: Relevance
“…Finally, the top T ranked candidate phrases are selected as keyphrases for the document. In this vein, the more recent methods SGRank (Danesh, Sumner, & Martin, 2015) and PositionRank (PR) (Florescu & Caragea, 2017b) utilize statistical, positional, and, word co-occurrence information, thus improving the overall performance. In particular, SGRank (Danesh et al, 2015), first, extracts all possible n-grams from the input text, eliminating those that contain punctuation marks or whose words are anything different than noun, adjective or verb.…”
Section: Graph-based Ranking Methodsmentioning
confidence: 99%
“…Finally, the top T ranked candidate phrases are selected as keyphrases for the document. In this vein, the more recent methods SGRank (Danesh, Sumner, & Martin, 2015) and PositionRank (PR) (Florescu & Caragea, 2017b) utilize statistical, positional, and, word co-occurrence information, thus improving the overall performance. In particular, SGRank (Danesh et al, 2015), first, extracts all possible n-grams from the input text, eliminating those that contain punctuation marks or whose words are anything different than noun, adjective or verb.…”
Section: Graph-based Ranking Methodsmentioning
confidence: 99%
“…In supervised approaches, a model is trained to learn to classify keyphrases from training data that is annotated with keyphrases [7,13,18,28,56,57,62]. Many unsupervised keyphrase extraction techniques had also been previously proposed [10,15,24,27,33,47,49,53]. They usually extract candidate keyphrases and rank them based on term frequencies, word co-occurrences, and other similar features.…”
Section: Related Workmentioning
confidence: 99%
“…The methods that are based on statistical information and structural information, for example tf-idf (term frequency-inverse document frequency), phrase position, and topic proportion, are language independent [8,27,[35][36][37][38]. However, weighting more to single terms than multiword terms and overlooking the semantics, are their main drawbacks.…”
Section: Related Workmentioning
confidence: 99%