Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art (SOTA) methods select candidate keyphrases based on the similarity between learned representations of the candidates and the document. They suffer performance degradation on long documents due to discrepancy between sequence lengths which causes mismatch between representations of keyphrase candidates and the document. In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document. We further develop a KPE-oriented BERT (KPEBERT) model by proposing a novel self-supervised contrastive learning method, which is more compatible to MDERank than vanilla BERT. Comprehensive evaluations on six KPE benchmarks demonstrate that the proposed MDERank outperforms state-of-the-art unsupervised KPE approach by average 1.80 F 1@15 improvement. MDERank further benefits from KPEBERT and overall achieves average 3.53 F 1@15 improvement over the SOTA SIFRank. Our code is available at https: //github.com/LinhanZ/mderank.
Skin color detection is a hot research of computer vision, pattern identification and human-computer interaction. Skin region is one of the most important features to detect the face and hand pictures. For detecting the skin images effectively, a skin color classification technique that employs Bayesian decision with color statistics data has been presented. In this paper, we have provided the description, comparison and evaluation results of popular methods for skin modeling and detection. A Bayesian approach to skin color classification was presented. The statistics of skin color distribution were obtained in YCbCr color space. Using the Bayes decision rule for minimum cot, the amount of false detection and false dismissal could be controlled by adjusting the threshold value. The results showed that this approach could effectively identify skin color pixels and provide good coverage of all human races, and this technique is capable of segmenting the hands and face quite effectively. The algorithm allows the flexibility of incorporating additional techniques to enhance the results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.