Messages
Apologies: Due to illness, we are running a couple of days late publishing our grading of the final exam. We expect to have your grades published by Wednesday this week (December 19).
Tomorrow (Thursday), Andrey and Stephan will hold the final laboratory session for this semester. We have just published our own attempt at neural negation resolution (in the Microsoft GitHub repository for the course at UiO) and will use the session tomorrow to (a) admire our own code and share practical tips for hyper-parameter grid search on Abel; (b) invite everyone to critically review our code and in particular look for wasteful operations; (c) share some high-level comments on your submissions; and (d) discuss with you (which is not to say answer) any questions you might have about the exam.
We now publish the list of submitted systems which were the best in the obligatory assignment 3 (Sentiment analysis with CNNs), when evaluated on the held-out test set. Congratulations to the winners! The test set is now available in the same location as the train and dev sets (/projects/nlpl/teaching/uio/inf5820/2018/SST/ on Abel)....
We have just published the final assignment for this course, which has its submission deadline on Friday, November 16. This assignment builds on a fairly popular standard task and data set, providing more structural complexity than we have encountered so far. The first part of the assignment is intended to explore the data and enable you to navigate its structure comfortably; please start working on this part of the assignment already this week! To make available time for this preparatory work, all of us traveled today to the EMNLP 2018 conference, which means there will be no laboratory session this Thursday.
Next Tuesday, we will related the theory of gated recurrent neural networks to various practical language processing tasks, including the one of the final assignment.
We now publish the list of submitted systems which were the best in the obligatory assignment 2, when evaluated on the held-out test set. Congratulations to the winners! The test set is now available on the course Github page....
The 3rd obligatory assignment to the INF5820 course is now published, pulling you deep into convolutional neural networks for sentiment analysis.
The final results and scores for the 2nd obligatory assignment will be announced at the group session in Thursday October 11.
The second obligatory assignment to the INF5820 course is now published.
You are free to start working on it right now, or wait until the last word embedding lecture on September 25.
This is to inform the INF5820 students about 3 important updates regarding the course:
- Technical problems with Python packages and encodings, that we encountered today at the group session, are now fully resolved. All the packages can now be imported, and you don't need to tinker with encodings any more. Make sure to check the (slightly updated) Technical Setup guide. Note that we now provide the test script (you can use it to check that your Python environment on Abel is sane) and the example SLURM job file (you will need it to run jobs on the Abel c...
We have established an email address inf5820-help@ifi.uio.no that will reach all instructors for this class. Please make it a habit to send all questions or feedback to this address, so as to reach everyone (and maximize the probability of a quick response :-).
Regarding computational infrastructure, please see our instructions for gaining access to Abel. Before the first laboratory session this coming Thursday, please make sure to have your account enabled- which can take a day or two, so why not submit the on-line form linked from our instructions immediately?
Finally, the slides from the kick-off lecture are now available from the course schedule page. And in cas...
Fall 2018 is the last time this course is offered in the study programme Informatics: Language and Communication. Our primary target audience this term, thus, are students on this programme. Students on other study programmes are, of course, welcome too, but incoming MSc students on the new Informatics: Language Technologies programme are discouraged from taking INF5820. Instead, a revised variant of the class will be taught in the first half of 2019, using the new course code INF5480.
The course will be organized differently from past versions, with a heavy focus on neural (or 'deep learning') methods in Natural Language Processing (NLP) and on scientific computing tools and techniques that scales to potentially large data sets. This class will teach you the basics of what you will likely be asked about in future job interviews.
We will be leaning heavily on the recent...