601.467/667 Introduction to Human Language Technology

Fall 2026

Coordinator: Philipp Koehn (phi@jhu.edu)
TA: Xiluo He (xhe69@jhu.edu)
Class: Tuesday and Thursday 9:00-10:15am, Hackerman B17
Office hours: Coordinator: on request
Office hours: TA: TBD, Hodson 210
CA: Rutva Pandya (rpandya4@jh.edu)
Gradescope (entry code: N2WEZ8) ☆ Piazza (access code qlnu01yhhel) ☆ Old lecture recordings

Assignments

Note: For Fall 2026, please *do not* proceed before assignments being announced. They are subject to change.
You can confirm whether the homework is released by checking the date listed on each homework.

Late submissions: For each student, we allow a total of 10 days of late submission for all homeworks.
It is counted on a daily basis, for example, if you submit a homework even a few minutes late, you will lose 1 day of your quota.
After you use up all 10 days of late submission, each late day would cost 5% points penalty.
Late submission for teamwork would use 1-day for each teammate.
For each homework, you *are not allowed to submit* after 14 days.
  1. N-gram language modeling, CYK parsing: Due on September 23 (Wednesday)
  2. RNNLMs, word2vec: Due on September 30 (Wednesday)
  3. Seq2seq for pronunciation prediction: Due on November 4 (Wednesday)
  4. Speech recognition with CTC: Due on December 2 (Wednesday)

We also have an in-class lab/assignment on November 4. The link to the lab is here: Speech recognition lab
The lab is due on Gradescope on November 12.

Exam

There will be two mid-terms and final exam. You are allowed to bring 1 sheet of paper with notes to the exam.

The final exam time takes place December 11, 6pm, in Hackerman B17.

Lectures

Date Topic Instructor
Tu Sep 1IntroductionKoehn
Text
Th Sep 3Words and Language ModelsYarowsky
Tu Sep 8MorphologyYarowsky
Th Sep 12SemanticsLippincott
Tu Sep 15Deep learning IMurray
Th Sep 17SyntaxPost
Tu Sep 22Deep learning II (Python notebook)Murray
Th Sep 24Machine TranslationDuh
Tu Sep 29Large Language ModelsKoehn
Th Oct 1Neural and Symbolic ProcessingKoehn
Tu Oct 6Information RetrievalYang
Th Oct 8First Midterm Exam-
Speech
Tu Oct 15Auditory systemElhilali
Th Oct 17Speech basicsMoro-Velazquez
Tu Oct 22Speaker recognitionVillalba
Tu Oct 24Classic speech recognition1 (additional slides, video 0:12-1:25)Khudanpur
Th Oct 29End-to-end neural speech recognitionKhudanpur
Tu Oct 31Self-Supervised ModelsKhudanpur
Th Nov 5Enhancement and DiarizationMaciejewski
Tu Nov 10Hands on: Kaldi (K2, ESPnet, Transducer-based ASR, CTC ASR from pretrained models) Garcia and Maciejewski
Th Nov 12Second Midterm Exam
Applications
Tu Nov 17Question AnsweringDuh
Th Nov 19NLP for Digital HumanitiesLippincott
Tu Dec 1NLP for Studying Human BehaviorGligoric
Th Dec 3Ethical ProblemsMoro-Velazquez
Tu Dec 8Human-Centered Evaluation of Language TechnologiesXiao
Th Dec 10Computational Social ScienceField
1These slides present an incomplete picture of what will be discussed in class. Attentive listening is recommended for gaining maximal benefit.