Generating and interpreting referring expressions have long been recognized as important problems in computational linguistics. In this seminar, we will read and discuss seminal and recent research on these topics, as well as survey related work on reference in psycholinguistics.
In the first part of the course, we will examine a range of topics related to the task of Generating Referring Expressions (GRE). Particular attention will be paid to examining the results of the recent Attribute Selection for GRE Challenge, with an eye towards assembling teams to enter the Referring Expression Generation Challenge 2008, which will be held in conjunction with the INLG-08 meeting immediately prior to ACL-08. The second part of the course will focus on recent data-driven approaches to computational anaphora resolution (CAR), and give tutorial introductions to computational tools and machine learning software that are central to modelling CAR. Bridging these two parts of the course will be a survey of work in psycholinguistics on using eye tracking to study human processing of referential domains, as well as the debate on egocentricity versus audience design in producing and interpreting referring expressions.
Students will be expected to actively participate in the discussion and research carried out in the seminar. As detailed below, students will be required to facilitate discussions and post questions on the readings in advance. For projects, students will be encouraged to either work as part of a team towards submitting an entry into the Referring Expression Generation Challenge 2008, or to carry out an independent class project on anaphora resolution. Alternatively, for students already working on a related topic, integrating their focus into the seminar will be an option.
Ling 684.02 or CSE 730 or permission of the instructors.
We'll use Carmen to schedule discussion facilitators and post advance questions on the readings. We'll also use the dropbox for project documents.
We are aiming for a dynamic discussion of papers, not death by powerpoint. Thus, we plan on taking a page from Eric Fosler-Lussier's playbook, and requiring everyone (this includes you!) to post at least one question to the discussion list on Carmen by 8 p.m. the evening before the assigned readings will be discussed. Participants should also feel free to share their (initial) thoughts and views of the papers in their posts. In particular, questions of the type "What did they mean by X" or "Why did they do X instead of Y" are encouraged. Remember that most of the papers are targeted to people who are already expert in the area, so you shouldn't expect to alway understand everything. Airing such questions can help everyone gain a better understanding of the paper — even those who thought they understood it!
Each session will have a discussion facilitator. The facilitator should read over the posted questions and choose a subset for discussion. In class, the facilitator should start the session with a fifteen minute summary of the day's readings, including the highlights and lowlights. Following the opening summary, the facilitator is responsible for managing the discussion, and ensuring that as many viewpoints are heard as possible.
Students will be required to facilitate two sessions. Auditors are expected to facilitate one session. If the discussion does not take up the entire class period, the remaining time may be used to (informally) discuss class projects.
As noted above, students (other than auditors) will be required to carry out a term project, either alone or in a team setting, on generating referring expressions, computational anaphora resolution, or a related topic of their own research. A one-page project sketch will be required by the end of the fifth week, followed by a two-page extended abstract in the eighth week, a presentation during the time the final exam would be held (if we were having one), and a final report by the Thursday of finals week.
The topics and readings we expect to cover are listed below. This list may be refined as the course progresses.
Additional/background reading:
Additional reading:
Background reading:
Background reading:
We will focus on sections 1–4.1 (11 pages) of Ng's tech report.
Background reading:
Background reading:
Additional reading:
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, the instructor is required to report the violation to the Council on Academic Misconduct.
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).
This syllabus is subject to change. All important changes will be made in writing (email), with ample time for adjustment.