We’re going to look at: Distributional Similarity Clustering (Hierarchical and flat) Distributional Hypothesis states that words that occur in the same contexts tend to have similar meanings. Two words are similar to the extent that they share similar contexts. But … Continue reading →

What is lexical semantics? It is the study of the meaning of words, and how these combine to form the meaning of longer contexts (paragraphs, etc.). Words and concepts are a many-to-many relation. This results in lexical ambiguity; one phrase … Continue reading →

Sort of recap: S -> NP VP S' -> VP'(NP') Today looking at quantified expressions; expressions with quantifiers such as ‘Everyone’. ‘Everyone sleeps’, where ‘everyone’ is the set of people, you would represent it as: S' = forall x (person'(x) … Continue reading →

Parsers Chart parsers are better than backtracking parsers because they are more efficient. This is because in a backtracking parser partial successful parses are thrown away, and so have to be parsed again. A chart parser maintains all sub-parses. Active … Continue reading →

Previously we were talking about control verbs, e.g. ‘promise’ and ‘persuade’. These have different ‘controllers’. E.g. Sandy persuaded Kim to come home early. The VP ‘to come home early’ is related to Kim, but. Sandy promised Kim to come home … Continue reading →