Improved Automatic Keyword Extraction Given More Linguistic Knowledge

By Anette Hulth. Conference on Empirical Methods in Natural Language Processing, 2003

1,111 citations recorded by the source corpus.

In this paper, experiments on automatic extraction of keywords from abstracts using a supervised machine learning algorithm are discussed. The main point of this paper is that by adding linguistic knowledge to the representation (such as syntactic features), rather than relying only on statistics (such as term frequency and n-grams), a better result is obtained as measured by keywords previously assigned by professional indexers. In more detail, extracting NP-chunks gives a better precision than n-grams, and by adding the PoS tag(s) assigned to the term as a feature, a dramatic improvement of the results is obtained, independent of the term selection approach applied.

Subfields: Artificial Intelligence, Information Systems, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/771ca13f78a6cfda9ed99004a386e9e7e187bd34

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Molecular Biology

Citations in the corpus

SemEval-2010 Task 5 : Automatic Keyphrase Extraction from Scientific Articles (2010, methodology): “…extraction has led to the development of several new systems and techniques for the task (Frank et al., 1999; Witten et al., 1999; Turney, 1999; Hulth, 2003; Turney, 2003; Park et al., 2004; Barker and Corrnacchia, 2000; Hulth, 2004; Matsuo and Ishizuka, 2004; Mihalcea and Tarau, 2004;…”
PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents (2017, methodology): “As already mentioned, prior works on keyphrase extraction report results also in terms of precision (P), recall (R), and F1-score (F1) (Hulth, 2003; Hasan and Ng, 2010; Liu et al., 2010; Wan and Xiao, 2008).”
Deep Keyphrase Generation (2017, methodology): “– Inspec (Hulth, 2003): This dataset provides 2,000 paper abstracts.”
Finding advertising keywords on web pages (2006, methodology): “The use of linguistic information for keyword extraction was first studied by Hulth [12].”
Clustering to Find Exemplar Terms for Keyphrase Extraction (2009, methodology): “As reported in (Hulth, 2003), most manually assigned keyphrases turn out to be noun groups.”
Automatic Keyphrase Extraction via Topic Decomposition (2010, methodology): “As reported in (Hulth, 2003), most manually assigned keyphrases turn out to be noun phrases.”
Single Document Keyphrase Extraction Using Neighborhood Knowledge (2008, methodology): “More linguistic knowledge has been explored by Hulth (2003). Statistical associations between keyphrases have been used to enhance the coherence of the extracted keyphrases (Turney, 2003). Song et al. (2003) present an information gain-based keyphrase extraction system called KPSpotter. Medelyan and”
Structure-Augmented Keyphrase Generation (2021, methodology): “We empirically tested different effects of leveraging R , by training models using KP20k training dataset and evaluating the models on KP20k test set (in-distribution) and Inspec (Hulth, 2003) test set (out-of-distribution).”
TextRank: Bringing Order into Text (2004, methodology): “This is the same test data set as used in the keyword extraction experiments reported in (Hulth, 2003).”
Main Core Retention on Graph-of-Words for Single-Document Keyword Extraction (2015, methodology): “We used two standard datasets publicly available4: (1) Hulth2003 – 500 abstracts from the Inspec database introduced by Hulth in [11] and also used by Mihalcea and Tarau in [19] with PageRank; and (2) Krapi2009 – 2,304 ACM full papers (references and captions excluded) introduced by Krapivin et al.”
Wikify!: linking documents to encyclopedic knowledge (2007, methodology): “[10] A. Hulth.”
Automatic Keyphrase Extraction: A Survey of the State of the Art (2014, methodology): “To ﬁll this gap, we ran four keyphrase extraction systems on four commonly-used datasets of varying sources, including Inspec abstracts (Hulth, 2003), DUC-2001 news articles (Over, 2001), sci-entiﬁc papers (Kim et al., 2010b), and meeting transcripts (Liu et al., 2009a).”
Discovering key concepts in verbose queries (2008, methodology): “Instead, we adopt the supervised machine learning approach [29, 12, 15] for key query concept extraction, and use a diverse mix of features as inputs for the supervised machine learning algorithm.”