Keyword extraction from Educational Video transcripts using NLP techniques

Shukla, Himani; Kakkar, Misha

doi:10.1109/confluence.2016.7508096

Cited by 17 publications

(12 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, for a phrase pattern "NN JJ" (a noun followed by an adjective), we extracted all phrases in the text having the "NN JJ" tag sequence as candidate keywords. In the previous study, Shukla and Kakkar manually defined the phrase patterns [23]. In this research, we used an automated approach by collecting the phrase patterns from all tagged keywords in the dataset, similarly resembling the knowledge domain from prior research [19].…”

Section: Phrase Pattern Developmentmentioning

confidence: 99%

“…Different from other previous studies, Shukla and Kakkar proposed an approach called Noun-Phrase Chunking [23]. This method only considers noun phrases, which are manually specified, to extract phrases from the text document.…”

mentioning

confidence: 99%

“…This method is also flexible in terms of providing control to determine which phrase patterns used to extract the keywords. The previous phrase chunking method proposed by Shukla and Kakkar [23] used several self-defined patterns. We argue that using self-defined patterns may lead to the limited coverage of phrase pattern possibilities, i.e., some keyword patterns may appropriate but not selected.…”

mentioning

confidence: 99%

“…Therefore, the contributions of this research are as follows: a. We proposed approaches for generating phrase patterns from a collection of documents, as an alternative to self-defined patterns proposed by Shukla and Kakkar [23], b. We attempted to reduce the number of keywords by conducting a candidate reduction as a part of our experiment, c. We conducted experiments using several keywords extraction scenarios, such as different sources of keywords, candidate keywords selections, and phrase patterns variations, and provide performance comparisons between those different scenarios.…”

mentioning

confidence: 99%

“…We attempted to reduce the number of keywords by conducting a candidate reduction as a part of our experiment, c. We conducted experiments using several keywords extraction scenarios, such as different sources of keywords, candidate keywords selections, and phrase patterns variations, and provide performance comparisons between those different scenarios. Our experiment include a replication of the method proposed by Shukla and Kakkar [23], but for Bahasa Indonesia, with several adjustments: 1) we generated phrase patterns from the documents instead of TELKOMNIKA Telecommun Comput El Control  Single document keywords extraction in Bahasa Indonesia… (I Nyoman Prayana Trisna) 1919 using self-defined patterns, 2) we reduced the number of yielded keywords from candidate instead of using all candidates as keywords. Compared to their method with the aforementioned adjustments, our result showed an improvement of performance based on the f-measure of the extracted keywords.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Single document keywords extraction in Bahasa Indonesia using phrase chunking

Trisna

Nurwidyantoro

2020

TELKOMNIKA

View full text Add to dashboard Cite

Keywords help readers to understand the idea of a document quickly. Unfortunately, considerable time and effort are often needed to come up with a good set of keywords manually. This research focused on generating keywords from a document automatically using phrase chunking. Firstly, we collected part of speech patterns from a collection of documents. Secondly, we used those patterns to extract candidate keywords from the abstract and the content of a document. Finally, keywords are selected from the candidates based on the number of words in the keyword phrases and some scenarios involving candidate reduction and sorting. We evaluated the result of each scenario using precision, recall, and F-measure. The experiment results show: i) shorter-phrase keywords with string reduction extracted from the abstract and sorted by frequency provides the highest score, ii) in every proposed scenario, extracting keywords using the abstract always presents a better result, iii) using shorter-phrase patterns in keywords extraction gives better score in comparison to using all phrase patterns, iv) sorting scenarios based on the multiplication of candidate frequencies and the weight of the phrase patterns offer better results.

show abstract

Section: Phrase Pattern Developmentmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations