Filters








5 Hits in 5.1 sec

A Joint Neural Model for Patent Classification and Rationale Identification

Yuta Koreeda, Hisao Mase, Kohsuke Yanai
2019 Transactions of the Japanese society for artificial intelligence  
The proposed method outperformed baseline methods in terms of the rationale identification, implying that incorporating rationales in training is particularly useful in identifying rationales.  ...  It was first trained for F-term annotation, and then fine-tuned using the ground-truth rationales to discriminate rationales from non-rationales.  ...  Using the k nearest neighbor method and BM25 in the patent document categorization subtask at NTCIR-5, in Proceedings of NTCIR-5 Workshop Meeting (2005) ( 3) Recurrent Neural Network (RNN) 1 1 F F  ... 
doi:10.1527/tjsai.f-ic1 fatcat:xq4od66nmjgalorultr4zltio4

Automated Patent Categorization and Guided Patent Search using IPC as Inspired by MeSH and PubMed

Daniel Eisinger, George Tsatsaronis, Markus Bundschus, Ulrich Wieneke, Michael Schroeder
2013 Journal of Biomedical Semantics  
Acknowledgments 3 Acknowledgments The work presented in this thesis was carried out in equal parts at Roche Diagnostics GmbH in Penzberg and at the Biotechnology Center (BIOTEC) in Dresden.  ...  Our methods use both keywords and class codes that the user enters to retrieve additional relevant keywords and classes that are then suggested to the user.  ...  such as Naive Bayes and k-nearest neighbor.  ... 
doi:10.1186/2041-1480-4-s1-s3 pmid:23734562 pmcid:PMC3632996 fatcat:mqdxpiitgzbx3akonwwzfq2edq

Content Facets For Individual Information Needs In Media

Elisabeth Lex, Stefanie Lindstaedt, Michael Granitzer, Harald Kosch
2018 Zenodo  
Third, the best features have successfully been used to classify traditional and social media content in both types of content facets.  ...  The amount of content published in traditional media is huge and steadily growing. Additionally, social media gained momentum since people use blogs to share comments and opinions to current events.  ...  k Nearest neighbor Algorithm The k Nearest neighbor (k-NN) algorithm [Aha et al., 1991] is a text classification algorithm that takes into consideration the k nearest neighbors of an item in the vector  ... 
doi:10.5281/zenodo.1196397 fatcat:udr3736ejbek5lzl34tu4g4ppq

Content Facets For Individual Information Needs In Media

Elisabeth Lex, Stefanie Lindstaedt, Michael Granitzer, Harald Kosch
2018 Zenodo  
Third, the best features have successfully been used to classify traditional and social media content in both types of content facets.  ...  The amount of content published in traditional media is huge and steadily growing. Additionally, social media gained momentum since people use blogs to share comments and opinions to current events.  ...  k Nearest neighbor Algorithm The k Nearest neighbor (k-NN) algorithm [Aha et al., 1991] is a text classification algorithm that takes into consideration the k nearest neighbors of an item in the vector  ... 
doi:10.5281/zenodo.1195993 fatcat:ce3ljnthjfhkpir3y4atnnlicy

Multimodal Legal Information Retrieval

Kolawole John Adebayo
2018
GoNTogle (Bikakis et al., 2010) uses weighted k Nearest Neighbor (kNN) classifier for document annotation and retrieval.  ...  TABLE 5 . 5 1: Evaluation on Choi's Dataset using P k error metric.  ... 
doi:10.6092/unibo/amsdottorato/8634 fatcat:afij2o54njfe7cqwgpdzyvioba