Synopsis

Advanced Semantic Representation ("SemRep")
TR 3:30–4:45, Maguire 103

Natural language is an imperfect vehicle for meaning. On the one hand, some expressions can be interpreted in multiple ways; on the other hand, there are often many superficially divergent ways to express very similar meanings. Semantic representations attempt to disentangle these two effects by exposing similarities and differences in how a word or sentence is interpreted. Such representations, and algorithms for working with them, constitute a major research area in natural language processing.

This course will examine semantic representations for natural language from a computational/NLP perspective. Through readings, presentations, discussions, and hands-on exercises, we will put a semantic representation under the microscope to assess its strengths and weaknesses. For each representation we will confront questions such as: What aspects of meaning are and are not captured? How well does the representation scale to the large vocabulary of a language? What assumptions does it make about grammar? How language-specific is it? In what ways does it facilitate manual annotation and automatic analysis? What datasets and algorithms have been developed for the representation? What has it been used for? One of the representations covered in depth will be the Abstract Meaning Representation. Term projects will consist of (i) innovating on a representation's design, datasets, or analysis algorithms, or (ii) applying it to questions in linguistics or downstream NLP tasks.

Credits: 3

Prerequisites: COSC/LING-5402 (Empirical Methods in Natural Language Processing) or LING-4427 (Computational Corpus Linguistics)

(For administrative reasons, registration is divided into two sections: LING-8422 and COSC-6422. The content and requirements within the course do not differ by registration section.)

Course Staff and Office Hours

Nathan Schneider
nathan.schneider@georgetown.edu
Office Hours: Mondays 4:00–5:00 (except holidays) in STM 315H

Textbook

None. All readings will be provided electronically.

Assessments

There will be no major exams. Grades will be based on participation in class, including leading a seminar-style paper discussion, as well as homework assignments such as reading responses and mini-annotation assignments. No programming is required. About half of the grade will be based on a major research project.

Communication

This website and the Canvas platform will be used to host course content. Either the Canvas discussion forum or a Slack workspace will be set up as the virtual venue for asking and answering course-related questions. The instructor will monitor the forum and post replies from time to time, but cannot promise immediate attention to every question. Note that any content posted in Slack may become unavailable after 90 days.

The most direct way to contact the instructor is through email.

Some course meetings will take place virtually via Zoom, via the link provided in Canvas. Some of these sessions may be recorded for use within the course. These recordings should not be shared beyond the course without permission.

The most direct way to contact the instructor is through email.

Computing Resources

If you will require a course account on a university Unix server for the project, contact the instructor to request one.

Attendance and Late Policy

In general, students are expected to attend all classes and to complete all assignments on time. Absences may have an adverse effect on grades in a course, up to and including failure.

That being said, we understand that circumstances may arise preventing you from attending class. In light of COVID, we will make every effort to accommodate student needs that are communicated to the instructors, for example, providing for asynchronous participation in the course by students whose circumstances prevent synchronous attendance over Zoom. Please email the instructors ASAP to communicate any expected absences or needs. For example, inform us at the beginning of the semester about planned religious observances or athletic travel.

At the discretion of the instructors, a deadline may be adjusted for a student if there are special circumstances communicated to the instructors well in advance. 11th-hour requests for an extension to an assignment are unlikely to be granted absent truly exceptional circumstances.

Students who miss multiple classes due to prolonged illness should seek medical care and provide documentation of such to the Dean’s Office, which will communicate with the student’s professors. A prolonged absence may necessitate the student’s withdrawal from the course or from the University for the semester.

More information and resources:

Academic Integrity

In this course, you will be asked to participate at times as an individual and at times working in a group. Exams should be completed entirely on your own. Exam questions should not be posted online or disclosed to other students who have not yet taken the exam (and the same goes for solutions to homework assignments).

For homework assignments, you are expected to write code/text and perform analyses yourself unless directed otherwise. I.e., don't copy solutions from other students or share yours with them. But you are encouraged to discuss concepts and implementation stumbling blocks with fellow students, within reason. The online discussion forum and office hours are good opportunities for this.

Part of treating others with respect is giving appropriate credit for ideas and scholarly works (including code). If you consult with other students on an assignment, report this in the work that you turn in. If in your code you use a library or implementation from another source, indicate that as well (minimally by including a URL in a comment). Do not generate new content with prompt-based AI tools like ChatGPT or CodePilot without permission from instructors unless specifically allowed by the assignment. (Using, for example, Grammarly as a language aid is OK.) Instructors reserve the right to request an oral explanation of answers.

Course projects are intended to be highly collaborative, and the final project writeup should include a synopsis of who has contributed what. Version control software should be used in development for the final project. (Version control can also be used for homework assignments, provided that you ensure that other students do not have access to your solutions.)

In research writing, it is important to give credit to other research that provides specific foundations to your work, as well as to published work that is closely related. If you discuss ideas/information from a publication, be sure to cite it; if you reuse the specific phrasing of other work, use quotation marks. Knowing when and how to give credit can be tricky at times, so when in doubt, ask!

For more information:

Support Services

Many students struggle or get overwhelmed at some point in their studies. In general, if you feel like you are running into difficulties that impact your performance in the course, reaching out to the instructor or TA is a good starting point. There are also experienced academic staff members (e.g. advising dean, graduate program administrator, or director of graduate studies) who are prepared to advise students facing challenges: they can offer skills and resources to troubleshoot the situation.

In particular, Georgetown recognizes that COVID-19 has a significant impact on everyone in the Georgetown community. Georgetown offers a variety of support services for students that can be accessed online and has put together this newsletter which aims to provide you with information about well-being resources and virtual meetings that can connect you with mental health professionals on and off campus during this time. Below are some resources available to you at the university level:

  • Academic Resource Center (ARC)
    202-687-8354 | arc@georgetown.edu
  • Counseling and Psychiatric Services (CAPS)
    202-687-6985
  • Institutional Diversity, Equity & Affirmative Action (IDEAA)
    202-687-4798
  • Office of the Student Ombuds (OSO)
    • 202-784-1081 | studentombuds@georgetown.edu

Title IX/Sexual Misconduct

Georgetown University and its faculty are committed to supporting survivors and those impacted by sexual misconduct, which includes sexual assault, sexual harassment, relationship violence, and stalking. Georgetown requires faculty members, unless otherwise designated as confidential, to report all disclosures of sexual misconduct to the University Title IX Coordinator or a Deputy Title IX Coordinator. If you disclose an incident of sexual misconduct to a professor in or outside of the classroom (with the exception of disclosures in papers), that faculty member must report the incident to the Title IX Coordinator, or Deputy Title IX Coordinator. The coordinator will, in turn, reach out to the student to provide support, resources, and the option to meet. [Please note that the student is not required to meet with the Title IX coordinator.] More information about reporting options and resources can be found on the Sexual Misconduct Website: https://sexualassault.georgetown.edu/resourcecenter

If you would prefer to speak to someone confidentially, Georgetown has a number of fully confidential professional resources that can provide support and assistance. These resources include:

  • Health Education Services for Sexual Assault Response and Prevention: confidential email sarp@georgetown.edu
  • Counseling and Psychiatric Services (CAPS): 202.687.6985 or after hours, call (833) 960-3006 to reach Fonemed, a telehealth service; individuals may ask for the on-call CAPS clinician

More information about reporting options and resources can be found on the Sexual Misconduct Website.

Title IX/Pregnancy and Parenting Accommodations

Georgetown University is committed to creating an accessible and inclusive environment for pregnant and parenting students. Students may request adjustments based on general pregnancy needs or accommodations based on a pregnancy-related complication. Specific adjustments will be handled on a case by case basis and will depend on medical needs and academic requirements. Students seeking a pregnancy adjustment or accommodation should follow the process laid out on the Title IX website.

Learning Resources

The Writing Center offers peer tutoring by trained graduate and undergraduate students who can assist you at any point in the writing process. They help at any stage of your writing process, from brainstorming to revision. Tutors can offer advice on thesis development, use of evidence, organization, flow, sentence structure, grammar, and more. The Writing Center will not proofread or edit papers; rather, they will help to improve your proofreading and editing skills to become a better writer. Appointments can be booked online through their website.

Useful Software and Technical Guides

See the resources page.