J
Jenny Rose Finkel
Researcher at Stanford University
Publications - 17
Citations - 12044
Jenny Rose Finkel is an academic researcher from Stanford University. The author has contributed to research in topics: Named-entity recognition & Biomedical text mining. The author has an hindex of 15, co-authored 17 publications receiving 10862 citations.
Papers
More filters
Proceedings Article
The Infinite Tree
TL;DR: The infinite tree is developed, a new infinite model capable of representing recursive branching structure over an arbitrarily large set of hidden categories, each of which enforces different independence assumptions.
Journal ArticleDOI
A System for Identifying Named Entities in Biomedical Text: how Results From two Evaluations Reflect on Both the System and the Evaluations
TL;DR: A maximum entropy-based system for identifying named entities (NEs) in biomedical abstracts and its performance in the only two biomedical named entity recognition (NER) comparative evaluations that have been held to date are presented.
Proceedings Article
Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data
TL;DR: A novel model is presented which makes use of additional single-task annotated data to improve the performance of a joint model and utilizes a hierarchical prior to link the feature weights for shared features in several single- task models and the joint model.
Robust Textual Inference using Diverse Knowledge Sources
Rajat Raina,Aria Haghighi,Christopher Cox,Jenny Rose Finkel,Jeffrey Lawrence Michels,Kristina Toutanova,Bill MacCartney,Marie-Catherine de Marneffe,Christopher D. Manning,Andrew Y. Ng +9 more
TL;DR: A machine learning approach to robust textual inference is presented, in which parses of the text and the hypothesis sentences are used to measure their asymmetric “similarity”, and thereby to decide if the hypothesis can be inferred.
Journal ArticleDOI
A system for identifying named entities in biomedical text: how results from two evaluations reflect on both the system and the evaluations: Conference Papers
TL;DR: A maximum entropy-based system for identifying named entities in biomedical abstracts and its performance in the only two biomedical named entity recognition (NER) comparative evaluations that have been held to date, namely BioCreative and Coling BioNLP is presented.