Info

This course introduces students to natural language processing and exposes them to the variety of methods available for reasoning about text in computational systems. NLP is deeply interdisciplinary, drawing on both linguistics and computer science, and helps drive much contemporary work in text analysis (as used in computational social science, the digital humanities, and computational journalism). We will focus on major algorithms used in NLP for various applications (part-of-speech tagging, parsing, coreference resolution, machine translation) and on the linguistic phenomena those algorithms attempt to model. Students will implement algorithms and create linguistically annotated data on which those algorithms depend.

Staff

David Bamman (dbamman@berkeley.edu), OH: Wed 10am-noon (Zoom; Queue).

TAs (info159259-instructors@lists.berkeley.edu):
  • Katie Stasaski (katie_stasaski@berkeley.edu), OH Tues 10-11:30am
  • Jon Gillick (jongillick@berkeley.edu), OH Wed 4:00-5:30pm
  • Chloe Lee (chloe.hy.lee@berkeley.edu), OH Thurs 3:30-5pm
  • Janaki Vivrekar (janaki.vivrekar@berkeley.edu), OH Fri 12-1:30pm

    • Texts

    • [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) [Online access available for free through the UC library here]

    Syllabus

    (Subject to change.)

    WeekDateTopicReadings Assignments
    11/19Introduction [slides]SLP2 ch 1 
    1/21Construction of truth; ethics [slides]PS ch. 6; Hovy and Spruit 2016HW1 out
    21/26Text classification 1 [slides]SLP3 ch 4
    1/28Text classification 2; logreg [slides]SLP3 ch 5HW2 out
    32/2Text classification 3; MLP and convolutional neural nets [slides]G 13 
    2/4Language modeling 1 [slides]SLP3 ch 3HW3 out
    42/9Language modeling 2; RNN [slides]SLP3 ch 7; G 14 
    2/11Vector semantics and static word embeddings [slides]SLP3 ch 6
    52/16Contextual word embeddings (BERT, ELMo); attention and transformers [slides]Smith 2019, Devlin et al. 2019HW4 out
    2/18Sequence labeling problems: POS tagging; HMM [slides]SLP3 ch 8Project proposal due (Info 259)
    62/23MEMM, CRF [slides]SLP3 ch 8
    2/25Neural sequence labeling [slides]SLP3 ch 9; E 7HW5 out
    73/2Context-free syntax [slides]SLP3 ch 12 
    3/4Context-free parsing algorithms [slides]SLP3 ch 13 
    83/9Review [slides]
    3/11Midterm
    93/16Dependency parsing 1 [slides]SLP3 ch 14 
    3/18Dependency parsing 2 [slides]SLP3 ch 14
    103/22Spring break
    3/25Spring break
    113/30Semantic role labeling [slides]SLP3 ch 19Project midterm report due (Info 259)
    4/1Wordnet, supersenses and WSD [slides]SLP3 ch 18HW6 out
    124/6Coreference resolution [slides]SLP3 ch 21
    4/8Information extraction [slides]SLP3 ch 17HW7 out
    134/13Question answering [slides]SLP3 ch 23 
    4/15Text generation (Katie) [slides]SLP3 ch 24HW8 out
    144/20Multimodal NLP (Jon) [slides]
    4/22Machine translation [slides]SLP3 ch 11
    154/27Social NLP [slides]Pick one: Voigt et al. 2017; Underwood et al. 2018; Antoniak et al. 2019
    4/29Final project presentations
    155/10NLP subfield survey due (Info 159); Final project report due (Info 259)

    Prerequisites

    • — Algorithms: Computer Science 61B
    • — Probability/Statistics: Computer Science 70, Math 55, Statistics 134, Statistics 140 or Data 100
    • — Strong programming skills

    Grading

    Info 159

    50%Homeworks
    10%Weekly quizzes
    20%Midterm exam
    20%NLP subfield survey

    Info 259

    40%Homeworks
    10%Weekly quizzes
    20%Midterm exam
    30%Project:
         5% Proposal/literature review
         5% Midterm report
         15% Final report
         5% Presentation

    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.

    NLP subfield survey (Info 159)

    Understanding how to read and synthesize articles in NLP is an important part of carrying out research in this space. To cultivate this skill, your final report will be a 2000-word survey for a specific NLP subfield of your choice (e.g., coreference resolution, question answering, interpretability, narrative generation, etc.), synthesizing at least 25 papers published at ACL, EMNLP, NAACL, EACL, AACL, Transactions of the ACL or Computational Linguistics. This survey should be able to provide a newcomer (such as yourself at the start of the semester) a sense of the current state of the art in that subfield in 2021, the major historical papers that have defined that area, and the different schools of thought within it. The survey should use the ACL 2021 style files for formatting, which are available as an Overleaf template and source templates for LaTeX and Microsoft Word.

    Project (Info 259)

    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 reports should use the ACL 2021 style files, which are available as an Overleaf template and source templates for LaTeX and Microsoft Word.

    Policies

    Academic Integrity

    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 and exams 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. We have zero tolerance policy for cheating and plagiarism; violations will be referred to the Center for Student Conduct and will likely result in failing the class.

    Piazza

    We'll use Piazza as a platform for asking and answering questions about the course material, including homeworks. Students are encouraged to actively participate on this forum and help others by answering questions that arise (helpful students can see a grade bump across a threshold (e.g., B+ to A-) for this participation. When helping with homework questions, keep the discussion to the high-level concepts; don't post answers to homeworks or quiz/exam questions.

    TA office hours

    TA office hours will be held over Discord, which enables students to self-organize into channels to discuss any questions they have in common among themselves, with the TA moving between channels to answer questions for everyone there. While in the channel, keep academic integrity in mind: you may discuss homework questions at a high level with others present, but don't discuss specific answers or share screens with code solutions. Neither the TA office hours or Piazza should be used for pre-grading (asking if a specific answer to a homework or quiz question is correct before the assignment is due).

    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.

    Late assignments

    Student have will have a total of three 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. If all late days have been used up, homeworks/quizzes can be turned in up to 48 hours late for 50% credit; anything submitted after 48 hours late = 0 credit. 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, you may turn it in up to 2:00am 1/23 and still be assessed 1 late day.) Late days are assessed immediately once homeworks or quizzes are submitted late and can't be retroactively changed (if you submit 2 homeworks and 2 quizzes late, for example, you can't decide after the fact which ones to apply your 3 slip days to -- they apply to whichever homeworks or quizzes use them up first).

    Curving

    Grades for this course will not be curved. Minimum thresholds for letter grades are the following: 93 A, 90 A-, 87 B+, 83 B, 80 B-, 77 C+ 73 C, 70 C-, 67 D+, 63 D, 60 D-, 0 F. Students taking the course P/NP must complete all deliverables and will receive a P if their grade is greater or equal to 70 (C-); Students taking S/U must complete all deliverables and will receive an S if their grade is greater or equal to 80 (B-).

    Exams

    This course has a midterm exam scheduled for 3/11 (in-class) and no final exam. We will not be offering alternative midterm exam dates, so if you anticipate a conflict, you should not register for this course.