Investigating Keyphrase Indexing with Text Denoising
This addresses the problem of improving keyphrase extraction accuracy for researchers in domains like food and agriculture, high energy physics, and biomedical science, but it is incremental as it builds on an existing method.
The paper investigated using text denoising to improve keyphrase indexing with the Maui indexer, finding that training on denoised texts led to performance that was either better than or as good as training on full texts across three standard corpora.
In this paper, we report on indexing performance by a state-of-the-art keyphrase indexer, Maui, when paired with a text extraction procedure called text denoising. Text denoising is a method that extracts the denoised text, comprising the content-rich sentences, from full texts. The performance of the keyphrase indexer is demonstrated on three standard corpora collected from three domains, namely food and agriculture, high energy physics, and biomedical science. Maui is trained using the full texts and denoised texts. The indexer, using its trained models, then extracts keyphrases from test sets comprising full texts, and their denoised and noise parts (i.e., the part of texts that remains after denoising). Experimental findings show that against a gold standard, the denoised-text-trained indexer indexing full texts, performs either better than or as good as its benchmark performance produced by a full-text-trained indexer indexing full texts.