natural-language-processing-4

Keyword Extraction

3260 papers • 126 benchmarks • 313 datasets

Keyword extraction is tasked with the automatic identification of terms that best describe the subject of a document (Source: Wikipedia).

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in keyword-extraction-4

Trend

Dataset

Best Model

Actions

SemEval 2010 Task 8

SemEval-2017 Task-10

Inspec

Libraries

i

Use these libraries to find keyword-extraction-4 models and implementations

Datasets

CSL (Chinese Scientific Literature)

Subtasks

No subtasks available.

Most implemented papers

sCAKE: Semantic Connectivity Aware Keyword Extraction

Swagata Duari, Vasudha Bhatnagar•Mon Nov 26 2018

A parameterless method for constructing graph of text that captures the contextual relation between words, and a novel word scoring method based on the connection between concepts that are individually superior to those followed by the sate-of-the-art graph-based keyword extraction algorithms.

61

Content

Inspec

0

Paper Graph

A Graph Degeneracy-based Approach to Keyword Extraction

A. Tixier, M. Vazirgiannis, Fragkiskos D. Malliaros•Mon Oct 31 2016

It is hypothesized that keywords are more likely to be found among inﬂuential nodes of a graph-of-words rather than among its nodes high on eigenvector -related centrality measures.

79 0

Paper Graph

Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization

A. Tixier, M. Vazirgiannis, Polykarpos Meladianos•Thu Aug 31 2017

A fully unsupervised, extractive text summarization system that leverages a submodularity framework that allows summaries to be generated in a greedy way while preserving near-optimal performance guarantees is presented.

29 0

Paper Graph

YAKE! Keyword extraction from single documents using multiple local features

A. Jorge, A. Jatowt, Ricardo Campos, Vítor Mangaravite, Arian Pasquali, C. Nunes•Tue Dec 31 2019

YAKE!, a light-weight unsupervised automatic keyword extraction method which rests on statistical text features extracted from single documents to select the most relevant keywords of a text, is described.

671 0

Paper Graph

Efficient Generation and Processing of Word Co-occurrence Networks Using corpus2graph

Pierre Zweigenbaum, Zheng Zhang, Ruiqing Yin•Sun Dec 31 2017

Corpus2graph is an open-source NLP-application-oriented tool that generates a word co-occurrence network from a large corpus that not only contains different built-in methods to preprocess words, analyze sentences, extract word pairs and define edge weights, but also supports user-customized functions.

10 0

Paper Graph

RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation

Blaž Škrlj, Andraz Repar, Senja Pollak•Sun Jul 14 2019

This work explores how load centrality, a graph-theoretic measure applied to graphs derived from a given text can be used to efficiently identify and rank keywords.

33 0

Paper Graph

Complex Network based Supervised Keyword Extractor

Swagata Duari, Vasudha Bhatnagar•Wed Sep 25 2019

A supervised framework for automatic keyword extraction from single document is presented, and the claim that graph-theoretic properties of words are effective discriminators between keywords and non-keywords is substantiated.

45 0

Paper Graph

TNT-KID: Transformer-based neural tagger for keyword identification

S. Pollak, Blaž Škrlj, Matej Martinc•Thu Mar 19 2020

This research presents a novel algorithm for keyword identification, an extraction of one or multiword phrases representing key aspects of a given document, called Transformer-Based Neural Tagger for Keyword IDentification (TNT-KID), capable of overcoming deficiencies of both supervised and unsupervised state-of-the-art approaches to keyword extraction.

49 0

Paper Graph

Keywords lie far from the mean of all words in local vector space

Grigorios Tsoumakas, Eirini Papagiannopoulou, A. Papadopoulos•Thu Aug 20 2020

This work follows a different path to detect the keywords from a text document by modeling the main distribution of the document's words using local word vector representations, and confirms the high performance of this approach compared to strong baselines and state-of-the-art unsupervised keyword extraction methods.

3 0

Paper Graph

Semantic Sensitive TF-IDF to Determine Word Relevance in Documents

Amir Jalilifard, Vinicius F. Carid'a, Alex F. Mansano, Rogers Cristo•Sun Jan 05 2020

A set of nearly four million documents from health-care social media was collected and was trained in order to draw semantic model and to find the word embeddings, and the features of semantic space were utilized to rearrange the original TF-IDF scores through an iterative solution so as to improve the moderate performance of this algorithm on informal texts.

78 0

Paper Graph

Adding a benchmark result helps the community track progress.