Language Looks Simple. It Isn't.

Click each sentence to reveal its hidden ambiguity — and what that means for any NLP system trying to process it.

“I went to the bank.”

Lexical
Reading A

A financial institution — I need to deposit money or see a cashier.

Reading B

The edge of a river — I walked down to the water's edge.

Word sense disambiguation — same string, two unrelated dictionary entries. Without context, any system must guess.

“I saw the man with the telescope.”

Syntactic
Reading A

I used a telescope to observe him.

Reading B

The man I saw was carrying a telescope.

Prepositional Phrase (PP) attachment ambiguity — “with the telescope” can modify the verb or the noun. Two valid parse trees; two different events.

“The police stopped the protesters because they were becoming violent.”

Referential
Reading A

The protesters were becoming violent, so the police intervened.

Reading B

The police were becoming violent, and they stopped the protesters.

Coreference resolution — who does they refer to? Getting it wrong doesn’t just fail linguistically — it assigns blame to the wrong party.

“Every student speaks two languages.”

Scope
Reading A

There are two specific languages — say English and French — that every student speaks.

Reading B

Each student speaks some two languages — not necessarily the same ones as other students.

Quantifier scope — identical words, identical order, two different logical propositions. Formal semantics is required to distinguish them.

“Visiting relatives can be boring.”

Structural
Reading A

Relatives who come to visit — those people — can be boring.

Reading B

The activity of going to visit relatives can be boring.

Category ambiguity — “visiting” is simultaneously a modifier (adjective-like) and a gerund (noun phrase head). The parse trees diverge completely.

0 of 5 revealed

Course Structure

Ten units building from word structure to sentence structure, meaning, and AI applications. Based on Bender (2013), Linguistic Fundamentals for Natural Language Processing.

Phase 1 — Word Structure
Units 1–4

From what language is, to morphemes, phonological alternations, and grammatical feature systems. Concepts #0–#43.

Phase 2 — Sentence Structure
Units 5–8

Syntax, parts of speech, heads, arguments, adjuncts, and grammatical functions. Concepts #44–#82.

Phase 3 — Meaning & Mismatches
Unit 9

When linguistic form and meaning diverge — passives, expletives, long-distance dependencies, argument drop. Concepts #83–#97.

Phase 4 — Review & Future Directions
Unit 10

Morphological analysers, deep parsers, typological databases, and the future of linguistically informed AI. Concepts #98–#100.

Start Course — Unit 1