Computational Semantics for Natural Language Processing

ETH Zürich, Spring Semester 2023: Course catalog

Course Description

This course presents an introduction to Natural language processing (NLP) with an emphasis on computational semantics i.e. the process of constructing and reasoning with meaning representations of natural language text.

The objective of the course is to learn about various topics in computational semantics and its importance in natural language processing methodology and research. Exercises and the project will be key parts of the course so the students will be able to gain hands-on experience with state-of-the-art techniques in the field.


The final assessment will be a combination of a group paper presentation (10%), two graded exercises (40%) and the project (50%). There will be no written exams.

Lectures: Fri 14:00-16:00 (the class will be in person)

Discussion Sections: Fri 16:00-17:00

Office Hour (assignment, project): Please contact professor/TAs for appointment.

Textbooks: We will not follow any particular textbook. We will draw material from a number of research papers and classes taught around the world. However, the following textbooks would be useful:

  1. Introduction to Natural Language Processing by Jacob Eisenstein
  2. Speech and Language Processing by Jurafsky and Martin


09.02   Class website is online!

Course Schedule

 Lecture Date Description Course Materials Events            Exercise TA
  1  24.02     Introduction Diagnostic Quiz Answers to quiz Presentation preference indication  
  2  03.03  The Distributional Hypothesis and Word Vectors 1. Glove    
 Voluntary  03.03  Matrix Calculus and Backpropagation 1. CS231n notes on network architectures
2. CS231n notes on backprop
3. Learning Representations by Backpropagating Errors
4. Derivatives, Backpropagation, and Vectorization
5. Yes you should understand backprop
  3  13.03 (Zoom)  Word Vectors 2, Word Senses and Sentence Vectors

(Recursive and Recurrent Neural Networks)
1. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
2. Improving Vector Space Word Representations Using Multilingual Correlation
3. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
 Voluntary  13.03 (Zoom)  RNN, LSTM, GRU 1. Review of Differential Calculus
2. Natural Language Processing (Almost) from Scratch
 4  17.03  NLU beyond a sentence

Seq2Seq and Attention

Case Study: Sentence Similarity, Textual Entailment and Machine Comprehension
1. Massive Exploration of Neural Machine Translation Architectures
2. Bidirectional Attention Flow for Machine Comprehension
 Voluntary  17.03  Discussion on Final Projects (topics) 1. Practical Methodology (Deep Learning book chapter)   All TAs
 5  24.03  Syntax and Predicate Argument Structures

(Semantic Role Labelling, Frame Semantics, etc.)
1. Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task
2. Grammar as a foreign language
Assignment 1 released  
 Voluntary  24.03  TBA TBA   Tianyu
 6  31.03  Predicate Argument Structures II

(Semantic Role Labelling, Frame Semantics, etc.)
1.Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
2.Frame-Semantic Parsing
 Voluntary  31.03  Discussion on Final Projects (topics)     All TAs
 Easter  07.04      Project proposal due  
 Easter  14.04         
 7  21.04  Modelling and tracking entities: NER, coreference and information extraction (entity and relation extraction) 1. End-to-end Neural Coreference Resolution
2. Improving Coreference Resolution by Learning Entity-Level Distributed Representations
 Voluntary  21.04  Assignment 1 Review (including QA)     All TAs
 8  28.04  Formal Representations of Language Meaning 1.Compositional semantic parsing on semi-structured tables
2.Supertagging With LSTMs
Assignment 1 due  
 Voluntary  28.04  Assignment 1 Discussion (QA)     All TAs
 9  05.05  Transformers and Contextual Word Representations (BERT, etc.)

Guest lecture by Avinava Dubey (Google)
1. Big Bird: Transformers for Longer Sequences (Only cover the idea of sparse attention: don’t need to cover turing completeness and the theoretical results))
2. BERT rediscovers the classical NLP pipeline
 Voluntary  05.05  Huggingface and Transformers
1. Huggingface
 10  12.05  Question Answering
1. Reading Wikipedia to Answer Open-Domain Questions
2. Latent Retrieval for Weakly Supervised Open Domain Question Answering
 Voluntary  12.05  Discussion on Final Projects (progress)     All TAs
 11  19.05  Natural Language Generation

Case Study: Summarization and Conversation Modelling
1. Language Models are Unsupervised Multitask Learners
2. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Assignment 2 release  
 Voluntary  19.05  Transformer Illustrated 1. The Illustrated Transformer (Jay Alammar)   Jiaoda
 12  26.05  Language + {Knowledge, Vision, Action} 1. Knowledge Enhanced Contextual Word Representations
2. VisualBERT: A Simple and Performant Baseline for Vision and Language
Project mid-term report due  
 Voluntary  26.05  Project discussion Including some technical tricks on LM finetuning   Yifan
 13  02.06  Pragmatics 1. Pragmatic Language Interpretation as Probabilistic Inference
2. Rational speech act models of pragmatic reasoning in reference games
 Voluntary  02.06  Assignment 2 Review (including QA)     All TAs
   23.06      Assignment 2 due  
   14.07      Project report due  
  Schedule Poster session (gather town link)  

Assignment Submission Instructions




You can ask questions on moodle. Please post questions there, so others can see them and share in the discussion. If you have questions which are not of general interest, please don’t hesitate to contact us directly.

Lecturer Mrinmaya Sachan
Guest Lecturers Avinava DubeyEthan WilcoxAlex Warstadt
Teaching Assistants Alessandro StolfoShehzaad DhuliawalaYifan HouTianyu LiuJiaoda LiSankalan Pal Chowdhury