- [SLP3] Dan Jurafsky and James Martin, Speech and Language Processing (3nd ed. draft) [Available here]
- [E] Jacob Eisenstein, Natural Language Processing (2018) [Available on bCourses]
- [G] Yoav Goldberg, Neural Network Methods for Natural Language Processing (2017) [Available for free on campus/VPN here]
- [PS] James Pustejovsky and Amber Stubbs, Natural Language Annotation for Machine Learning (2012) [Available for free on campus/VPN here]
(Subject to change.)
|1||1/21||Introduction [slides]||SLP2 ch 1|
|1/23||Text classification 1 [slides]||SLP3 ch 4|
|2||1/28||Text classification 2; logreg [slides]||SLP3 ch 5||HW1 out (due 2/3)|
|1/30||Text classification 3; MLP and convolutional neural nets [slides]||G 13|
|3||2/4||Construction of truth; ethics [slides]||PS ch. 6; Hovy and Spruit 2016||HW2 out (due 2/12)|
|2/6||Language modeling 1 [slides]||SLP3 ch 3|
|4||2/11||Language modeling 2; RNN [slides]||SLP3 ch 7; G 14|
|2/13||Vector semantics and static word embeddings [slides]||SLP3 ch 6||HW3 out (due 2/24)|
|5||2/18||Contextual word embeddings (BERT, ELMo); attention and transformers [slides]||Smith 2019, Devlin et al. 2019||Project proposal due (Info 259)|
|2/20||Sequence labeling problems: POS tagging; HMM||SLP3 ch 8|
|6||2/25||MEMM, CRF||SLP3 ch 8||HW4 out (due 3/4)|
|2/27||Neural sequence labeling||SLP3 ch 9; E 7|
|7||3/3||Context-free syntax||SLP3 ch 12|
|3/5||Context-free parsing algorithms||SLP3 ch 13, 14|
|9||3/17||Dependency parsing 1||SLP3 ch 15|
|3/19||Dependency parsing 2||SLP3 ch 15||HW5 out (due 4/1)|
|11||3/31||Semantic role labeling||SLP3 ch 20||Project midterm report due (Info 259)|
|4/2||Coreference resolution||SLP3 ch 22||HW6 out (due 4/13)|
|12||4/7||Information extraction||SLP3 ch 18|
|4/9||Multimodal NLP (Jon Gillick)|
|13||4/14||Wordnet, supersenses and WSD||SLP3 ch 19||HW7 out (due 4/20)|
|4/16||Question answering||SLP3 ch 25|
|14||4/21||Text generation (Katie Stasaski)||SLP3 ch 26||HW8 out (due 4/29)|
|4/23||Machine translation||E 18, G 17|
|4/30||Future and review|
|5/5||Final project presentations (Info 259)|
|5/11||Final project reports due (Info 259)|
|5/15||Final exam (7pm-10pm)|
- — Algorithms: Computer Science 61B
- — Probability/Statistics: Computer Science 70, Math 55, Statistics 134, Statistics 140 or Data 100
- — Strong programming skills
|40%||8 homeworks||10%||Weekly quizzes|
|5% Proposal/literature review|
|5% Midterm report|
|15% Final report|
All lectures will be recorded and made available through bCourses; attendance at lectures is not required (but it is recommended). Weekly quizzes will test your knowledge of that week's lectures and readings, so be sure to watch the lecture to stay on track.
Info 259 will be capped by a semester-long project (involving one to three students), involving natural language processing -- either focusing on core NLP methods or using NLP in support of an empirical research question. For examples of the former, see papers published at ACL, NAACL and EMNLP; for examples of the latter, see workshops for NLP and Computational Social Science, Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, Natural Language Processing Techniques for Educational Applications, Noisy User-Generated Text, and many more.
The project will be comprised of four components:
- — Project proposal and literature review. Students will propose the research question to be examined, motivate its rationale as an interesting question worth asking, and assess its potential to contribute new knowledge by situating it within related literature in the scientific community. (2 pages; 5 sources)
- — Midterm report. By the middle of the course, students should present initial experimental results and establish a validation strategy to be performed at the end of experimentation. (4 pages; 10 sources)
- — Final report. The final report will include a complete description of work undertaken for the project, including data collection, development of methods, experimental details (complete enough for replication), comparison with past work, and a thorough analysis. Projects will be evaluated according to standards for conference publication—including clarity, originality, soundness, substance, evaluation, meaningful comparison, and impact (of ideas, software, and/or datasets). (6 pages, not including references)
- — Presentation. At the end of the semester, teams will present their work in a poster session.
All students will follow the UC Berkeley code of conduct. You may discuss homeworks at a high level with your classmates (if you do, include their names on the submission), but each homework deliverable must be completed independently -- all writing and code must be your own. All quizzes must be completed on your own. If you mention the work of others, you must be clear in citing the appropriate source (For additional information on plagiarism, see here.) This holds for source code as well: if you use others' code (e.g., from StackOverflow), you must cite its source. All homeworks and project deliverables are due at the time and date of the deadline.
Students with Disabilities
Our goal is to make class a learning environment accessible to all students. If you need disability-related accommodations and have a Letter of Accommodation from the DSP, have emergency medical information you wish to share with me, or need special arrangements in case the building must be evacuated, please inform me immediately. I'm happy to discuss privately after class or at my office.
Student have will have a total of two late days to use when turning in homework assignments and quizzes (not project deliverables for Info 259); each late day extends the deadline by 24 hours. Each homework and quiz will be due at 11:59pm, and will have a 2-hour grace period for any last-minute submission issues. Late days and incompletes will be assessed immediately following the grace period (at 2:00am sharp). The grace period applies to late days as well (if a homework is due at 11:59pm 1/21, and you use a late day to extend it to 11:59pm 1/22, a submission will not be accepted after 2:00am 1/23).
Grades for this course will be curved according to the EECS grading guidelines for undergraduate courses. This class is an upper-division course.
This course has a midterm exam scheduled for 3/12 (in-class) and a final exam scheduled for 5/15 (7pm-10pm). We will not be offering alternative exam dates, so if you anticipate a conflict, you should not register for this course.