Course pages 2015–16
Machine Learning for Language Processing
Stephen Clark's lectures and notes
This year's lecture slides:
- Lecture 1: Classification [slides] [notes]
- Lecture 2: POS Tagging with HMMs [slides] [notes]
- Lecture 3: Maximum Entropy Models [slides] [notes]
- Lecture 4: The Perceptron for Structured Prediction [slides] [notes]
Ted Briscoe's reading seminars
There will be 2 presentations per 50 minute session. Your presentations should be about 15 minutes allowing for a further 5 minutes for questions, and 10 minutes at the end of each session for general discussion. You should summarise the paper briefly (remember everyone will have read it), explicate any parts you found difficult or innovative, and critically evaluate the work described. For your evaluation you should consider questions like: To what extent have the stated aims of the research been achieved? To what extent is the work replicable given the information provided? In what way does the work advance the state of the art?, etc. You may prepare slides and use the data or overhead projector and/or whiteboard. You should liaise with your co-presenter to decide the order in which to make presentations. The first presentation should briefly define the task, the other should not. You should have all slides for the session loaded onto a single laptop set up with the data projector by the beginning of each session.
All students should read all the papers and come to all sessions prepared to discuss each paper after the presentations
You may write an essay on a topic related to the paper you present, or any of the course material. Alternatively you may undertake a small project on text classification using existing datasets and machine learning software, and then submit a project report. In both cases, your essay or report should not exceed 5000 words and will be due in around the end of the first week of Lent Term.
Your essay topic should involve an in-depth critical evaluation of a specific machine learning technique and its application to language processing, or of a specific language processing task and machine learning techniques that have been applied to that task. Little credit will be given for summaries of papers. An example of a possible title/topic on named entity recognition might be `To what extent do we need sequential models to achieve accurate NER?' This essay might critically examine the claim made by Ratinov and Roth that NE recognition and classification can be done accurately by conditioning only on the class label assigned to the previous word(s) (as well as other invariant observed features of the context) without (Viterbi) decoding to find the most likely path of label assignments. In doing this, it might review the NER task definition and consider how dealing adequately with conjoined or otherwise complex NEs (see Mazur and Dale, Handling Conjunctions in Named Entities) might affect their claims. It might also propose an experiment that would resolve the issue empirically and/or identify one that has been published that sheds some light on it.
Suitable small projects will need to make use of existing labelled datasets and existing machine learning tools that are distributed and documented, so that they can be completed in reasonable time. Some examples of text classificataion tasks and datasets are: spam filtering (lingspam, genspam), sentiment of movie reviews ("sentiment polarity datasets" Pang), named entity recognition (conll shared task ner), hedge (scope) detection (conll shared task hedge scope), language identification (altw 2010 langid dataset), document topic classification (Reuters-21578), genre classification (genre collection repository), and many many more. Some examples of (good) machine learning toolkits are SVMlight, Weka, or Mallet. A project might replicate a published experiment but try different feature types or a different classifier, and describe the experiment and report results in a comparable manner to the relevant (short) paper.
Schedule and Reading List
Week 2: Document Topic Classification
Week 3: Document Topic Classification
Week 4: Spam Filtering
Week 5: Named Entity Recognition
Week 6: Relation Extraction
Week 7: Essay Scoring
Week 8 (Friday): Topic Clustering