601.467/667 Introduction to Human Language Technology


Fall 2025

Coordinator: Philipp Koehn (phi@jhu.edu)
TA: Neha Verma (nverma7@jhu.edu)
Class: Tuesday and Thursday 9:00-10:15am, Hackerman B17
Office hours: Coordinator: on request
Office hours: TA: Wednesday 4:00-5:00pm, Malone 216
CA: TBA
Gradescope (entry code: EEGYNW)Piazza (access code qlnu01yhhel)Old lecture recordings

Assignments

Note: For Fall 2025, 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 10 (Wednesday)
  2. RNNLMs, word2vec: Due on September 24 (Wednesday)
  3. Seq2seq for pronunciation prediction: Due on October 29 (Wednesday)
  4. Speech recognition with CTC: Due on November 26 (Wednesday)

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 Aug 26IntroductionKoehn
Text
Th Aug 28Words and Language ModelsYarowsky
Tu Sep 2MorphologyYarowsky
Th Sep 4SyntaxPost
Tu Sep 9Deep learning IMurray
Th Sep 11SemanticsLippincott
Tu Sep 16Deep learning II (Python notebook)Murray
Th Sep 18Machine TranslationDuh
Tu Sep 23Distributional Semantics and Large Language ModelsKoehn
Th Sep 25Information ExtractionKoehn
Tu Sep 30Information RetrievalYang
Th Oct 2First Midterm Exam-
Speech
Tu Oct 7Speech basicsMoro-Velazquez
Th Oct 9Classic speech recognition1 (additional slides, video 0:12-1:25)Khudanpur
Tu Oct 14Speaker recognitionVillalba
Tu Oct 21End-to-end neural speech recognitionWiesner
Th Oct 23Auditory systemElhilali
Tu Oct 28Enhancement and DiarizationMaciejewski
Th Oct 30Hands on: Kaldi (K2, ESPnet)Wiesner and Maciejewski
Tu Nov 4Hands on: Kaldi (Transducer-based ASR, CTC ASR from pretrained models)
Th Nov 6Second Midterm Exam
Applications
Tu Nov 11Question AnsweringDuh
Th Nov 13NLP for Digital HumanitiesLippincott
Tu Nov 18(no class) 
Th Nov 20Ethical ProblemsMoro-Velazquez
Tu Dec 2Human-Centered Evaluation of Language TechnologiesZiang Xiao
Th Dec 4Computational Social ScienceField
1These slides present an incomplete picture of what will be discussed in class. Attentive listening is recommended for gaining maximal benefit.