Comp. Linguistics | Ch 09: Word Meaning: Lexical Resources and Distributional Semantics | Video

Video corrections and clarifications: 01:40 — Ignore the generated “Linguistics 101 – University Press © 2024” footer. The source is Foundations of Computational Linguistics, Chapter 9. 02:40 — Use these WordNet paths: key (sense 1) → device → instrumentality; key (sense 15) → lever → bar → implement → instrumentality. They meet after 2 and 4 “is a kind of” steps; the displayed replacement paths are incorrect (pp.152,162). 04:20 — The new WSD system scores 0.70 against the baseline’s 0.75. It performs worse by 5 percentage points; the equal bars and “equivalent performance” claim are incorrect (pp.156,162). 04:40 — For the textbook calculation, use all five contexts: open, lock, play, note, music. key=(2,4,2,1,0), door=(8,6,0,0,0), piano=(0,0,4,2,4); their cosines are 0.80 (key–door) and 0.33 (key–piano). The partial table has its target/context labels transposed (pp.156–157). 06:00 — Treat the post-transformation graphic as schematic: its arrows are not orthogonal to the horizontal gender axis. Debiasing can reduce measured bias, but does not eliminate it (p.159). 06:40 — Complete the textbook’s Short Quiz on p.162; answers are on p.164. The reference to an online quiz module is not supported by the source. The original video is unchanged. These notes follow sampled visual checks against the textbook. Narration was not reviewed. Chapter 9: Word Meaning: Lexical Resources and Distributional Semantics Foundations of Computational Linguistics: For EFL University Students Video lesson • Printed textbook pages 148–164 A word can have several senses, and words can be related in different ways. This chapter compares dictionary-based resources with representations learned from patterns of language use. Central question: How can computers represent what words mean and how word meanings relate to one another? Learning objectives 1. Explain how one word form can carry several senses and why idioms are stored as units. 2. Trace hypernym chains and other lexical relations in WordNet, and compare one synset across wordnets for different languages. 3. Apply the simplified Lesk algorithm and the most frequent sense baseline, and explain how word sense choices are evaluated. 4. Calculate cosine similarity for count vectors, and evaluate what word embeddings capture about similarity, analogy, and bias. Five core topics 9.1 Word Senses, Polysemy, and Multiword Expressions (p. 149) Distinguish word senses and related meanings, and explain why some multiword expressions must be interpreted as units. 9.2 Lexical Relations and WordNet (p. 151) Explore synsets and lexical relations in WordNet, keeping shared senses separate from differences in use or style. 9.3 Word Sense Disambiguation (p. 154) Compare a frequent-sense baseline with context-based methods such as simplified Lesk, and judge them against labeled examples. 9.4 The Distributional Hypothesis and Vector Representations (p. 156) Represent context counts as vectors and calculate cosine similarity, noting that one vector can mix several senses of a word. 9.5 Word Embeddings: Similarity, Analogy, and Bias (p. 157) Examine how dense word vectors capture patterns of similarity and analogy while also reflecting biases in their training data. Study with the textbook Read pages 148–164, review this chapter companion, and attempt the activities before checking the explained answers. Refer to the book for exact examples, calculations, diagrams, notation, and qualifications. Free textbook: https://zenodo.org/records/23095075 Textbook DOI: https://doi.org/10.5281/zenodo.23095075 Chapter resources: https://sites.google.com/view/els4efl... ELS4EFL series website: https://sites.google.com/view/els4efl... YouTube channel:    / @elsforefl   About the textbook Series: English Language Studies for EFL University Students (ELS4EFL) Branch: Theoretical Linguistics Project Director: Prof. Munassir Alhamami First Edition | Version 1 | 2026 Citation Alhamami, M. (2026). Foundations of computational linguistics: For EFL university students (First Edition, Version 1). Zenodo. https://doi.org/10.5281/zenodo.23095075 This is an AI-generated study companion created with Gemini Notebook (NotebookLM) from the textbook. Consult the book for complete teaching, practice activities, and explained answers. Original textbook content is licensed under CC BY 4.0 except where otherwise stated. Material credited to other sources remains subject to its stated terms. Chapter and topic headings follow the textbook; the study explanations in this description are supplementary adaptations. https://creativecommons.org/licenses/... #ComputationalLinguistics #NLP #EFL