Analysing biomedical text with the Stanford dependency grammar
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Johanna Geiss.
The Stanford parser and natural language tools come with a dependency grammar and a deterministic algorithm for mapping from standard Penn Treebank-style parse trees to dependency graphs. We have shown how this provides a lingua franca for comparing various statistical parsers on biomedical text, using benchmarking methods that highlight deficiencies in their behaviour much better than tree-based analyses. We also believe dependency graphs offer a tractable intermediate step between syntax and semantics and have developed some simple approaches to information extraction based on graph traversal.
This talk is part of the NLIP Seminar Series series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|