Keyphrase Extraction Using Knowledge Graphs

Abstract

Extracting keyphrases from documents automatically is an important and interesting task since keyphrases provide a quick summarization for documents. Although lots of efforts have been made on keyphrase extraction, most of the existing methods (the co-occurrence-based methods and the statistic-based methods) do not take semantics into full consideration. The co-occurrence-based methods heavily depend on the co-occurrence relations between two words in the input document, which may ignore many semantic relations. The statistic-based methods exploit the external text corpus to enrich the document, which introduce more unrelated relations inevitably. In this paper, we propose a novel approach to extract keyphrases using knowledge graphs, based on which we could detect the latent relations of two keyterms (i.e., noun words and named entities) without introducing many noises. Extensive experiments over real data show that our method outperforms the state-of-the-art methods including the graph-based co-occurrence methods and statistic-based clustering methods.

A review of keyphrase extraction

“…In addition, the co‐occurrence‐based methods suffer from information loss , that is, if two words never co‐occur within a window size in a document, there will be no edges to connect them in the corresponding graph‐of‐words even though they are semantically related, whereas the statistics‐based methods suffer from information overload , that is, the real meanings of words in the document may be overwhelmed by the large amount of external texts used for the computation of statistical information. To deal with such problems and incorporate semantics for keyphrase extraction, Shi, Zheng, Yu, Cheng, and Zou () propose a keyphrase extraction system that uses knowledge graphs. First, nouns and named entities ( keyterms ) are selected and grouped based on semantic similarity by applying clustering.…”

Sentiment analysis: A survey on design framework, applications and future scopes

“…Edge-weighting is used to rate the keywords (i.e., nodes) using two words' co-occurrence frequency, followed by generation as well as the ranking of candidate keyphrases. Shi et al (2017) suggested an automated single document keyphrase extraction technique based on co-occurrence-based knowledge graphs, which learns hidden semantic associations between documents using Personalized PageRank (PPR). Thus, many experts have used co-occurrence graphs, as well as other graph properties such as centrality metrics, to demonstrate the effectiveness of these methods for keyword ranking in sentiment analysis.…”

Measuring the interdisciplinary characteristics of Chinese research in library and information science based on knowledge elements

“…In the experiment, it is found that there is a lot of noise in the extracted knowledge elements. If the tf-idf weight of each word can be calculated before classification and the threshold value can be set to filter out invalid words, the accuracy of the classification results can be effectively improved (Chen et al, 2009), or a new method of extracting key phrases using knowledge graphs that can detect potential relationships between two key terms and remove the noise of words (Shi et al, 2017). Secondly, we used the established corpus and knowledge element extraction model, combined with academic journal taxonomy, which can provide fine-grained knowledge elements to empirically verify trends, knowledge bases and developments in interdisciplinary fields such as literature research.…”