Keyword extraction using backpropagation neural networks and rule extraction

Azcarraga, Arnulfo P.; Liu, Michael David; Setiono, Rudy

doi:10.1109/ijcnn.2012.6252618

Cited by 18 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to explain how the back propagation network works, a rule extraction method will be used to extract symbolic data from the resulting backpropagation network. The rules fetched can then be transformed into decision trees performing almost as accurate as the network plus the advantage of being in an easily comprehensible format [1].…”

Section: Literature Surveymentioning

confidence: 99%

Adaptive Keywords Extraction using Back Propagation Neural Networks- A Review

Sharma¹,

Mann²

2014

IJCA

View full text Add to dashboard Cite

Section: Literature Surveymentioning

confidence: 99%

Adaptive Keywords Extraction using Back Propagation Neural Networks- A Review

Sharma¹,

Mann²

2014

IJCA

View full text Add to dashboard Cite

“…The same IEEE documents previously used in [25] are used for all the experiments reported here. The dataset is composed of IEEE journal articles on different scientific topics.…”

Section: Datasetmentioning

confidence: 99%

“…It was argued in the earlier study [25] that in the absence of a more authoritative dataset that has manually selected keywords (by experts), it is justifiable to use title words and words in a keyword list as basis for proxy labels. This is preferred over allowing researchers themselves to assign the desired labels per document.…”

Section: Experimental Set-upmentioning

confidence: 99%

“…Note that in the 2012 study [25], format features (italicized, bold-faced, and large font size) were not included. Experiment II used all 14 features, including the format features.…”

Section: Experimental Set-upmentioning

confidence: 99%

“…Indeed, ANNs have been used for keyword extraction [25] [26][27] [28] and the work reported in this paper builds on past work reported in [25].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tagging documents using neural networks based on local word features

Azcarraga

Tensuan

Setiono

2014

2014 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Keywords and key-phrases that concisely represent text documents are integral to many knowledge management and text information retrieval systems, as well as digital libraries in general. Not all text documents, however, are annotated with good keywords; and the quality of these keywords is often dependent on a tedious, sometimes manual, extraction and tagging process. To automatically extract high quality keywords without the need for a semantic analysis of the document, it is shown that artificial neural networks (ANN) can be trained to only consider in-document word features such as word frequency, word distribution in document, use of word in special parts of the document, and use of word formatting features (i.e. bold-faced, italicized, large-font size). Results show that purely local features are adequate in determining whether a word in a document is a keyword or not. Classification performance yields a G mean of a least 0.83, and weighted f-measure of 0.96 for both keywords and nonkeywords. Precision for keywords alone, however, is not as high. To understand the basis for classifying keywords, C4.5 is used to extract rules from the ANN. The extracted rules from C4.5, in the form of a decision tree, show the relative importance of the different document features that were extracted.

show abstract

GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors

Sabbatini

Ciatto

Omicini

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Knowledge extraction methods are applied to ML-based predictors to attain explainable representations of their operation when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the extraction of either lists or trees of rules. Yet, most of them only support supervised learning -and, in particular, classification -tasks. Iter is among the few rule-extraction methods capable of extracting symbolic rules out of sub-symbolic regressors. However, its performance -here intended as the interpretability of the rules it extracts -easily degrades as the complexity of the regression task at hand increases.In this paper we propose GridEx, an extension of the Iter algorithm, aimed at extracting symbolic knowledge -in the form of lists of if-thenelse rules -from any sort of sub-symbolic regressor-there including neural networks of arbitrary depth. With respect to Iter, GridEx produces shorter rule lists retaining higher fidelity w.r.t. the original regressor. We report several experiments assessing GridEx performance against Iter and Cart (i.e., decision-tree regressors) used as benchmarks.

show abstract

Keyword extraction using backpropagation neural networks and rule extraction

Cited by 18 publications

References 13 publications

Adaptive Keywords Extraction using Back Propagation Neural Networks- A Review

Adaptive Keywords Extraction using Back Propagation Neural Networks- A Review

Tagging documents using neural networks based on local word features

GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors

Contact Info

Product

Resources

About