5

Metaphor and metonymy are both ways of connecting two concepts (or making one concept stand for another). The fundamental distinction between metaphor and metonymy is that metaphor connects two concepts based on similarity and metonymy based on part/whole relationship (meronymy). Typical examples of metaphor are 'Our relationship is on rocky ground' or 'We ...


4

The difference between polysemy and homonymy is often one of degree or the direction you approach them. They are difficult semantic relationships to fix with certainty even when it comes to lexical items let alone constructions with more abstract meanings (like tense or affixes). But the examples you give are examples of polysemy NOT homonymy. You have one ...


3

These are more or less like the word-sense disambiguation, anaphora resolution or co-reference resolution examples in the Winograd Schema Challenge and generally in natural language understanding. How far ahead do we look when parsing and understanding text? As you essentially show in your examples where the necessary information is not in the sentence, ...


3

A specific term is unknown to me, but the task of disentangling the meanings of a word is named word sense disambiguation in computational linguistics. So I think word sense is usable for the pair (word, meaning) even without being a formal term.


1

Since you seem to be interested in reading, you may find the following overview of "The science of word recognition" (written in 2017, by Kevin Larson) to be an interesting read. Larson says that the best supported model of how words are read is parallel recognition of multiple letters. Larson also talks about the phenomenon of eye "saccades", which ...


1

You have two input choices: 1. analyze dictionaries (wordnet, worknik or wiktionary), 2. use word embeddings (word2vec, glove, elmo). Use this data with a WSD (word sense disambiguation) solution. Search github for WSD. Also, this is worth looking at: https://blog.openai.com/discovering-types-for-entity-disambiguation/


Only top voted, non community-wiki answers of a minimum length are eligible