skip to primary navigationskip to content

Department of Computer Science and Technology

Masters

 

Course pages 2024–25

Introduction to Computational Semantics

Principal lecturer: Dr Weiwei Sun
Taken by: MPhil ACS, Part III
Code: L98
Term: Michaelmas
Hours: 16 (8 x 2 hour lectures)
Format: In-person lectures
Class limit: max. 16 students
Moodle, timetable

Aims

This is a lecture-style course that introduces students to various aspects of the semantics of Natural Languages (mainly English):

  • Lexical Semantics, with an emphasis on theory and phenomenology 
  • Compositional Semantics
  • Discourse and pragmatics-related aspects of semantics

Objectives

  • Give an operational definition of what is meant by “meaning” (for instance, above and beyond syntax);
  • Name the types of phenomena in language that require semantic consideration, in terms of lexical, compositional and discourse/pragmatic aspects, in other words, argue why semantics is important;
  • Demonstrate an understanding of the basics of various semantic representations, including logic-based and graph-based semantic representations, their properties, how they are used and why they are important, and how they are different from syntactic representations;
  • Know how such semantic representations are derived during or after parsing, and how they can be analysed and mapped to surface strings;
  • Understand applications of semantic representations e.g. reasoning, validation, and methods how these are approached.
  • When designing NL tasks that clearly require semantic processing (e.g. knowledge-based QA), to be aware of and reuse semantic representations and algorithms when designing the task, rather than reinventing the wheel.

Practical advantages of this course for NLP students

  • Knowledge of underlying semantic effects helps improve NLP evaluation, for instance by providing more meaningful error analysis. You will be able to link particular errors to design decisions inside your system.
  • You will learn methods for better benchmarking of your system, whatever the task may be. Supervised ML systems (in particular black-box systems such as Deep Learning) are only as clever as the datasets they are based on. In this course, you will learn to design datasets so that they are harder to trick without real understanding, or critique existing datasets.
  • You will be able to design tests for ML systems that better pinpoint which aspects of language an end-to-end system has “understood”.
  • You will learn to detect ambiguity and ill-formed semantics in human-human communication. This can serve to write more clearly and logically.
  • You will learn about decomposing complex semantics-reliant tasks sensibly so that you can reuse the techniques underlying semantic analyzers in a modular way. In this way, rather than being forced to treat complex tasks in an end-to-end manner, you will be able to profit from partial explanations and a better error analysis already built into the system.

Syllabus

  1. Overview of the course
  2. Events and semantic role labelling
  3. Referentiality and coreference resolution
  4. Truth-conditional semantics
  5. Graph-based meaning representation
  6. Compositional semantics
  7. Context-free Graph Rewriting
  8. Surface realisation
  9. Negation and psychological approach to semantics
  10. Dynamic semantics
  11. Gricean pragmatics
  12. Vector space models
  13. Cross-modality
  14. Acquisition of semantics
  15. Diachronic change of semantics
  16. Summary of the course

 

Assessment

5 take-home exercises worth 20% each:

Take-home assignment 1 is given in Lecture 4 and due is Lecture 6

Students are given 10 English sentences and asked to provide their semantic analysis according to truth-conditions. Students will be expected to return 10 logical expressions as their answers. No word limit. Assessment criteria: correctness of the 10 logical expressions; 2 points for each logical expression.

Take-home assignment 2 is given in Lecture 7 and due is Lecture 9 

Students are given 10 English sentences and asked to provide their syntactico-semantic derivations according to the compositionality principle. Students will be expected to return derivation graphs as their answers. No word limit. Assessment criteria: correctness of the 10 derivation graphs; 2 points for each derivation.

Take-home assignment 3 is given in Lecture 11 and due is Lecture 13 

All students are assigned with a paper on modelling common ground in dialogue system. Students will receive related but different papers. Each student will write a review of their assigned paper, including a comprehensive summary and their own thoughts. Word limit: 1000 words. Assessment criteria: 15 points on whether a student understands the paper correctly; 5 points on whether a student is able to think critically.

Take-home assignment 4 is given in Lecture 13 and due is Lecture 15

All students are assigned with a paper on language-vision interaction. Students will receive related but different papers. Each student will write a review of their assigned paper, including a comprehensive summary and their own thoughts. Word limit: 1000 words. Assessment criteria: 15 points on whether a student understands the paper correctly; 5 points on whether a student is able to think critically.

Take-home assignment 5 is given in Lecture 14 and due is two weeks later.

Content: All students are assigned with a paper on bootstrapping language acquisition. All students will receive the same paper. Each student will write a review of the paper, including a comprehensive summary and their own thoughts. Word limit: 1000 words. Assessment criteria: 15 points on whether a student understands the paper correctly; 5 points on whether a student is able to think critically.