In this course, you will learn how to build Natural Language Generation (NLG) systems, i.e. systems which use AI and comp. ling. techniques to automatically produce texts in English or other natural languages, starting from some non-linguistic representation of input data. Topics to be covered include content determination and structuring; sentence planning or microplanning (lexicalization, aggregation and referring expression generation); surface realization; and prosody prediction. During the course, we will examine the task of generating route directions as an ongoing case study. Homework assignments will provide you with practical experience using XML Schema, XSLT, the OpenCCG surface realizer, and the Festival speech synthesis system.
Ling 684.01 or permission of the instructor. The course is open to advanced undergraduate and graduate students.
You will be expected to keep up with the readings and actively participate in class discussions and activities.
There will be approximately six homework assignments. Homework assignments are due by the beginning of class, on paper. No late homeworks will be accepted without prior notice of a justifiable delay.
I encourage group work on the homework assignments, but each of you should write out your own answers. Note that group work means that everyone in the group contributes and fully understands what you turn in.
We'll be using the Carmen system for the schedule and for homework and reading assignments. There will also be discussion forums for posting questions and providing feedback (comments, complaints or ideas) during the course, anonymously if desired.
Readings will draw from Reiter and Dale's book, Building Natural Language Generation Systems, which has recently become available in paperback (e.g. at amazon.com).
There will also be further readings of primary sources assigned periodically, and listed below.
Students who need an accommodation based on the impact of a disability should contact me to arrange an appointment as soon as possible to discuss the course format, to anticipate needs, and to explore potential accommodations. I rely on the Office of Disability Services for assistance in verifying the need for accommodations and developing accommodation strategies. Students who have not previously contacted the Office for Disability Services are encouraged to do so (292-3307; http://www.ods.ohio-state.edu).
As with any class at this university, students are required to follow the Ohio State Code of Student Conduct. In particular, note that students are not allowed to, among other things, submit plagiarized (copied but unacknowledged) work for credit. If any violation occurs, I am required to report the violation to the Council on Academic Misconduct.
This syllabus is subject to change. All important changes will be made in writing (email), with ample time for adjustment.