Now showing items 1-5 of 5
Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing
(The University of Edinburgh, 2015-06-29)
The development of distributed training strategies for statistical prediction functions is important for applications of machine learning, generally, and the development of distributed structured prediction training ...
Automation of summarization evaluation methods and their application to the summarization process
(The University of Edinburgh, 2011-06-30)
Summarization is the process of creating a more compact textual representation of a document or a collection of documents. In view of the vast increase in electronically available information sources in the last decade, ...
Automated question answering for clinical comparison questions
(The University of Edinburgh, 2012-06-25)
This thesis describes the development and evaluation of new automated Question Answering (QA) methods tailored to clinical comparison questions that give clinicians a rank-ordered list of MEDLINE® abstracts targeted to ...
Joint models for concept-to-text generation
(The University of Edinburgh, 2014-06-27)
Much of the data found on the world wide web is in numeric, tabular, or other nontextual format (e.g., weather forecast tables, stock market charts, live sensor feeds), and thus inaccessible to non-experts or laypersons. ...
Integrated supertagging and parsing
(The University of Edinburgh, 2012-11-29)
Parsing is the task of assigning syntactic or semantic structure to a natural language sentence. This thesis focuses on syntactic parsing with Combinatory Categorial Grammar (CCG; Steedman 2000). CCG allows incremental ...