Loading...
Please wait, while we are loading the content...
Similar Documents
Word embeddings and recurrent neural networks based on Long-Short Term Memory nodes in supervised biomedical word sense disambiguation
| Content Provider | Semantic Scholar |
|---|---|
| Author | Yepes, Antonio Jimeno |
| Copyright Year | 2016 |
| Abstract | Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised learning algorithm methods are used as one of the approaches to perform disambiguation. Features extracted from the context of an ambiguous word are used to identify the proper sense of such a word. The type of features have an impact on machine learning methods, thus affect disambiguation performance. In this work, we have evaluated several types of features derived from the context of the ambiguous word and we have explored as well more global features derived from MEDLINE using word embeddings. Results show that word embeddings improve the performance of more traditional features and allow as well using recurrent neural network classifiers based on Long-Short Term Memory (LSTM) nodes. The combination of unigrams and word embeddings with an SVM sets a new state of the art performance with amacro accuracy of 95.97 in the MSH WSD data set. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://arxiv.org/pdf/1604.02506v3.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Algorithm Artificial neural network Biological Neural Networks Categorization Dasypus yepesi Document classification Extraction Graphical model Graphical user interface Large Long short-term memory MEDLINE Machine learning Medical Subject Headings Monte Carlo method National Library of Medicine (U.S.) NetWare Loadable Module Neural Network Simulation PowerShell Recurrent neural network Supervised learning Test set Unified Medical Language System Usability Web Services for Devices Word embedding Word sense Word-sense disambiguation |
| Content Type | Text |
| Resource Type | Article |
