Machine Learning for Coreference Resolution

Abstract   Semantic information is one of the building blocks for most NLP tasks. Adequate representation of semantic relations or the identification of the most appropriate meaning of words in discourse often requires extensive common sense and universal world knowledge. However, such information is not easy to extract and convey in useful data models. In this course we will cover the alternative to rule-based approaches. We will introduce machine learning and its use for various NLP tasks with a strong focus of the content to a specific natural language processing problem, namely Coreference Resolution. The latter is concerned with the resolution of phrases (mostly nominal phrases) and the entities that these phrases refer to.
Format of the course  
Instructors: Prof. Dr. Hinrich Schütze, Dr. Alexander M. Fraser, Thomas Müller and Desislava Zhekova  
Syllabus  
#datetopic presentingslides
116.10.2013Introduction allPDF
223.10.2013Intro ML/CR I Prof. SchützePDF
330.10.2013Intro ML/CR II Prof. SchützePDF
406.11.2013Intro ML/CR III Prof. Schütze 
513.11.2013Machine Learning Thomas MüllerPDF, PDF
620.11.2013Machine Learning Thomas MüllerPDF
727.11.2013Discussion [Domingos, 2012] Prof. Schützelink
804.12.2013Coreference Resolution for Machine TranslationDr. Fraser PDF
911.12.2013Machine Learning Thomas Müller 
1018.12.2013Coreference Resolution Desislava ZhekovaPDF
1108.01.2014Coreference Resolution Desislava ZhekovaPDF
1215.01.2014Coreference Resolution Desislava ZhekovaCancelled!
Project Abstracts due 
1322.01.2014 Dataset DiscussionDesislava Zhekova 
1429.01.2014 Project Work-  
Project Work Report due  
1505.02.2014 Project Work- 
Group Work   The approximate number of participants in a group is 2-3. Please, make sure that all participants have an equal share of the work (this you will need to indicate clearly in your project documentation). In case you wish to work alone or in a group with more than 3 participants, please, discuss this with us beforehand. The size of the group may be varied based on the complexity and extent of the project.
Project Work   The last three sessions of the class will be devoted to your projects. Within that time you will need to complete the tasks you selected. You are free to define the project titles yourself (the topic for each group needs to be approved before you submit the abstract).
Project Abstract   After you have selected a topic, you will be required to provide a written abstract (1 page, due 15.01.2014) of the problem at hand and how you plan to tackle it. The abstract should demonstrate a good understanding of the task and a proposed project work plan.
Project Work Report   To make sure that you are on the right track and that you advance with the project work you are required to submit a project work report t weeks (due on 29.01.2014). The report should consist of a half-page description of your advancement (what you have managed to implement during the week).
Project Paper   As part of your project work you will be required to write a paper (of at least 12 pages) that would both present and explain the NLP background of the topic you selected as well as provide an overview of your project work and discussion of the problems you encountered on the way. The paper should also aim to include a proper evaluation of the approach you used to tackle the task. Another possibility for the format of the paper is a scientific/conference paper (the length of this variant depends on the problem you have worked on and is within the limits of 4-8 pages). We will encourage you for the latter and will strongly promote the submission of such papers to international student workshops.
Assessment   The final assessment of the class is based on the following aspects:
References  
Domingos, P. (2012). A Few Useful Things to Know About Machine Learning. Communications of the ACM, 55(10):78–87.


File translated from TEX by TTH, version 4.03.
On 10 Oct 2013, 22:31.