CSCI 544 – Applied Natural Language Processing

D-clearance and waiting list

The course CSCI 544 — Applied Natural Language Processing has been oversubscribed in recent semesters, and therefore the department has instituted a prioritized waiting list for receiving D-clearance to enroll in the course.

Please refer all questions regarding your registration status to your academic advisor, as they have the most up-to-date information. Instructors do not have access to the waiting list, and are not able to answer questions about your status.

Master’s students

D-clearance for Master’s students is handled by the CS department office; students from outside the CS department will be able to apply through the D-clearance system starting in August. Please do not write to us asking to enroll in the course: we have no more information than the department office on which to base a decision, and therefore we will defer to the department’s priority list.

Exception: If you are a Master’s student working on a research project with a faculty advisor, and your advisor thinks that taking this class is needed for the project, please have your faculty advisor write to us to ask for D-clearance.

Other students

Undergraduate students and PhD students who wish to register for the course should write to us. We will decide whether to recommend you for D-clearance based on your academic background and interests.

Our general policy is to ask the department to give priority to Ph.D. students, and to place undergraduate students on the priority list subject to the same criteria as CS Master’s students. If you are an undergraduate student working on a research project with a faculty advisor, and your advisor thinks that taking this class is needed for the project, please have your faculty advisor write to us to ask for higher priority on the list.

Late registrations (during the add period)

As students register for the class, they are automatically added to Blackboard; this usually happens within a few hours after enrolling in the class. If you are enrolled in the class but not on Blackboard, please contact Blackboard help to resolve the issue. We do not add students manually to Blackboard.

After students are in Blackboard, we manually add them to the homework submission system (Vocareum). This can take a few days. Students who register late will be allowed to submit all the assignments they missed because of their late registration.

Completing assignments while on the waiting list

Students who are not registered for the course, including students on the waiting list, may attend the lectures if there is space in the lecture hall. However, only registered students may submit assignments.

Students who are absent from class for any reason must make up the materials themselves, and must submit their assignments on time. Students who register late will be allowed to submit all the assignments they missed because of their late registration.

Introduction to key components of human language technologies, including: information extraction, sentiment analysis, question answering, machine translation.

Students in the course will learn to perform the following:

1. Read technical literature in Natural Language Processing (including original research articles) and answer questions about such readings.

2. Implement language processing algorithms and test them on natural language data.

3. Design, implement, test, and present an original Natural Language Processing application.

The course requires programming in Python. If you are new to Python or haven’t used it in a while, it would be good to brush up on your skills before the course.

This is not a DEN course, and it does not have guaranteed provisions for students who are fully remote.

• Students who are absent from class for any reason must make up the materials themselves, and must submit their assignments on time.

• We will make the presentation slides available on Blackboard, and will endeavor to provide lectures both in-person and on Zoom.

• All the assignments will be submitted on-line.

• Students are expected to attend the article presentations and poster presentations in person. Individual arrangements for students who are unable to attend may be made on a case-by-case basis.

• The article presentations and project will be carried out in groups; it is up to the students of each group to decide how the group meets and communicates.

• The course does not have in-class exams.

• The final exam will be administered on-line according to the Final Exam Schedule. University regulations do not allow a student to omit a final examination, or take it in advance of its scheduled time.

Grade Breakdown

• 5% Written application idea (individual; peer-graded)

• 40% Coding assignments

• 10% Quizzes

• 5% Presentations of recent research papers (in groups; peer-graded)

• 35% Research project (in groups; parts of the project are self- and peer-graded)

• 5% Final exam: an on-line, take-home comprehensive exam taken during the final exam period

Grading Policies

• Grading Scale: A: 93%, A–: 90%, B+: 87%, B: 83%, B–: 80%, C+: 77%, C: 73%, C–: 70%, D+: 67%, D: 63%, D–: 60%

• Grades on an assignment or exam will only be changed if there is an error in grading. Grading errors are simple mistakes made on the part of the graders, and not differences in interpretation of a question or answer. A student who wishes to challenge a grade must identify the grading error before asking for a grade change.

• Students are welcome to discuss any aspect of the assignments and exams, but there will be no negotiation on grades, and no changes other than the correction of grading errors.

• Homework assignments must be turned in on time; late submissions will not be graded unless an approval is received prior to the deadline. Some assignments may have an option to be turned in late with a penalty; this will be announced with the assignment. In no instance will credit be given for a homework assignment submitted after the solution has been discussed in class.

• Reading quizzes are intended to make sure that students are prepared for class, so no late quizzes will be accepted.

  • There will be a small number of extra quizzes to allow students to make up for quizzes missed due to late registration, illness, or other reasons. Make-up quizzes will be given after all of the regular quizzes have been taken.

• Homework assignments will not be accepted by email. If there are technical or other issues with the submission system you should write to us and we will work to fix these issues, but do not send homework by email just because you weren’t able to submit it through the system.

• Make sure to check the exact time an assignment is due; this may be before class, at the end of the day, or some other time. We may not be available to solve issues close to the deadline, so you should plan on submitting your homework early, even if only as a draft. Multiple submissions are generally allowed, and the last submission will be graded. Quizzes may only be submitted once.

• Students are responsible for on-time submission. When submitting your assignments, please allow time to fix issues such as your computer freezing or crashing, network latencies or outages, and so on. If your assignment is submitted late because of a technical issue, it will be penalized as late.

• Students who are not able to make an assignment or exam deadline due to an emergency (for example, a medical emergency) or a conflict (for example, a job interview) must inform the instruction staff as soon as the issue arises, in order to make alternate arrangements. If you wait until after the deadline, or the grades are returned, or the end of the course, you will not be allowed to make up the work.

• Note that in general, conflicts with exams or deadlines for another class do not qualify for making alternate arrangements. Working and studying for multiple classes is an expectation from university students.

• Please use the class discussion boards on Piazza for questions and issues regarding homework assignments and the course in general. This way, the entire class can participate and see the questions and answers.

• Communications of a personal nature should also be sent on Piazza, as a private message to the entire instructional staff.

• Any special requests must be submitted in writing.

The course does not have a textbook. Required readings will be specified in the schedule as the course progresses, and will include a combination of select textbook chapters as well as original research articles. The links below give access to the full text of several textbooks; these are useful for general background on Natural Language Processing, and to supplement some of the materials taught in class. Any chapters that are required will be detailed in the schedule; otherwise, these texts are not required.

• Dan Jurafsky and James H. Martin, Speech and Language Processing (3rd edition draft, 2021)

• Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval (2008) (select chapters)

• Yoav Goldberg, Neural Network Methods for Natural Language Processing (2017) (This link provides free access to the PDF of the full book when accessed from the USC network)

• Jacob Eisenstein, Natural Language Processing (free version, 2018) or the published version (2019)

• Emily M. Bender, Linguistic Fundamentals for Natural Language Processing: 100 Essentials from Morphology and Syntax (2013) (This link provides free access to the PDF of the full book when accessed from the USC network)

When Ron Artstein taught CSCI 544 in Spring 2022, 13 students had their grades reduced for violations of academic integrity, including unauthorized collaboration on assignments and unauthorized copying from a solution posted on the web. The following policies are designed to reduce cheating.

• The penalty for copying is generally zero points on the assignment. This penalty applies regardless of the proportions of copied material and original work in the assignment.

• The penalty for copying will be doubled for students who do not reveal their source when asked. Investigating a suspicion of copying can involve substantial time and effort in tracing the source. To cut down on this time, students are required to reveal the source when asked. Copying generally results in a grade of zero on the assignment, but if a student fails to reveal the source and we later find the source on our own, the student will receive double the penalty. This applies regardless of whether the student admits to copying.

• Any attempt to fool automatic plagiarism detection will result in an automatic failing grade in the class. The modification of code to reduce its similarity to the source, in order to avoid automatic detection, is considered a worse violation of academic integrity than just copying. While copying code generally results in a grade of zero on the assignment, any deliberate attempt to avoid detection will result in a failing grade in the class.

Some tips to avoid issues with academic integrity:

• Do not look for solutions on the web. This applies not only to verbatim copying of code, but to any attempt to find or reference an external source for the solution. It is common and acceptable to consult external resources for basic language functionality (like how to read and write files, perform bitwise math operations, increment an item in a dictionary, and so on); however, consulting an external resource for a complete or partial solution to an assignment is not allowed, and is considered a violation of academic integrity.

• Never send your code to another student, even just for the purpose of comparing results. If your code performs better than that of your classmate, they may ask you to run it on their machine just to see if it achieves the same performance. But once your code is on their machine, there is a risk that parts of your code will find their way into their submission.

• Never receive code from another student, even just for the purpose of comparing results. If your classmate’s code performs better than yours, you may want to run it on your machine just to see if it achieves the same performance. But once their code is on your machine, there is a risk that parts of their code will find their way into your submission.

• Never post your code for a graded assignment to a publicly accessible repository. We encourage students to use good software practices like version and source control, and cloud services such as GitHub and BitBucket are excellent ways to do so. However, for graded assignments, you should make sure that your code is private, not public. If you make it public then someone else might find it, and you could be accused of copying or facilitating copying.

We report all academic integrity violations. Violations by graduate students are reported to the Viterbi Academic Integrity Coordinator, and violations by undergraduate students are reported to the Office of Student Judicial Affairs and Community Standards (SJACS). We follow the university procedures to the letter. There will be no negotiation, no bargaining, no makeup assignments, and no informal resolutions in cases of academic integrity violations. Also, once a violation has been reported, the instructor may not assign a grade until the individual case is resolved. Since many of the violations last semester were identified near the end of the semester, this meant that the grades of the students involved were delayed beyond the end of the semester.

Academic Conduct:

Plagiarism – presenting someone else’s ideas as your own, either verbatim or recast in your own words – is a serious academic offense with serious consequences. Please familiarize yourself with the discussion of plagiarism in SCampus in Part B, Section 11, “Behavior Violating University Standards” policy.usc.edu/scampus-part-b. Other forms of academic dishonesty are equally unacceptable. See additional information in SCampus and university policies on Research and Scholarship Misconduct.

Students and Disability Accommodations:

USC welcomes students with disabilities into all of the University’s educational programs. The Office of Student Accessibility Services (OSAS) is responsible for the determination of appropriate accommodations for students who encounter disability-related barriers. Once a student has completed the OSAS process (registration, initial appointment, and submitted documentation) and accommodations are determined to be reasonable and appropriate, a Letter of Accommodation (LOA) will be available to generate for each course. The LOA must be given to each course instructor by the student and followed up with a discussion. This should be done as early in the semester as possible as accommodations are not retroactive. More information can be found at osas.usc.edu. You may contact OSAS at (213) 740-0776 or via email at osasfrontdesk@usc.edu.

Support Systems:

Counseling and Mental Health - (213) 740-9355 – 24/7 on call

studenthealth.usc.edu/counseling

Free and confidential mental health treatment for students, including short-term psychotherapy, group counseling, stress fitness workshops, and crisis intervention.

National Suicide Prevention Lifeline - 1 (800) 273-8255 – 24/7 on call

suicidepreventionlifeline.org

Free and confidential emotional support to people in suicidal crisis or emotional distress 24 hours a day, 7 days a week.

Relationship and Sexual Violence Prevention Services (RSVP) - (213) 740-9355(WELL), press “0” after hours – 24/7 on call

studenthealth.usc.edu/sexual-assault

Free and confidential therapy services, workshops, and training for situations related to gender-based harm.

Office for Equity, Equal Opportunity, and Title IX (EEO-TIX) - (213) 740-5086

eeotix.usc.edu

Information about how to get help or help someone affected by harassment or discrimination, rights of protected classes, reporting options, and additional resources for students, faculty, staff, visitors, and applicants.

Reporting Incidents of Bias or Harassment - (213) 740-5086 or (213) 821-8298

usc-advocate.symplicity.com/care_report

Avenue to report incidents of bias, hate crimes, and microaggressions to the Office for Equity, Equal Opportunity, and Title for appropriate investigation, supportive measures, and response.

The Office of Student Accessibility Services (OSAS) - (213) 740-0776

osas.usc.edu

OSAS ensures equal access for students with disabilities through providing academic accommodations and auxiliary aids in accordance with federal laws and university policy.

USC Campus Support and Intervention - (213) 821-4710

campussupport.usc.edu

Assists students and families in resolving complex personal, financial, and academic issues adversely affecting their success as a student.

Diversity, Equity and Inclusion - (213) 740-2101

diversity.usc.edu

Information on events, programs and training, the Provost’s Diversity and Inclusion Council, Diversity Liaisons for each academic school, chronology, participation, and various resources for students.

USC Emergency - UPC: (213) 740-4321, HSC: (323) 442-1000 – 24/7 on call

dps.usc.edu, emergency.usc.edu

Emergency assistance and avenue to report a crime. Latest updates regarding safety, including ways in which instruction will be continued if an officially declared emergency makes travel to campus infeasible.

USC Department of Public Safety - UPC: (213) 740-6000, HSC: (323) 442-120 – 24/7 on call

dps.usc.edu

Non-emergency assistance or information.

Office of the Ombuds - (213) 821-9556 (UPC) / (323-442-0382 (HSC)

ombuds.usc.edu

A safe and confidential place to share your USC-related issues with a University Ombuds who will work with you to explore options or paths to manage your concern.

Occupational Therapy Faculty Practice - (323) 442-3340 or otfp@med.usc.edu

chan.usc.edu/otfp

​Confidential Lifestyle Redesign services for USC students to support health promoting habits and routines that enhance quality of life and academic performance.