Topics

A page per concept of language technology: what it is in plain words, how Mova does it, and the cards of the papers on it from the Research library, best first. The cards are also listed by author and on the papers front.

𒀭

Akkadian and cuneiform NLP

The language of Babylon and Assyria and the wedge-shaped script it was written in.

15 cards 🏷️

Named entity recognition

Finding the names in a text and saying what each names: a person, a place, an organization.

10 cards 🧵

Discourse analysis

How the sentences of a text hang together: what follows from what, and why.

86 cards 💬

Speech act theory

Saying as doing: asking, promising, ordering, thanking.

34 cards 😉

Implicature

What a speaker means beyond what the words say.

19 cards 🔗

Coreference resolution

Which words of a text name the same person or thing.

96 cards 🔀

Word sense disambiguation

Choosing the meaning a word has in its sentence.

22 cards 🌳

Dependency parsing

Every word of a sentence attached to the word it depends on.

98 cards 🌐

Universal Dependencies

One way to annotate the grammar of every language.

74 cards 🗂️

Treebanks

Corpora where every sentence comes with its grammatical tree.

139 cards 🎭

Semantic role labeling

Who did what to whom, where, when and why.

46 cards 🔤

Part-of-speech tagging

Noun, verb, adjective: the part of speech of every word in its context.

80 cards 🔁

Machine translation

Translating text from one language to another by program.

326 cards

Fields

The topics above are concepts of language; every field of the library has its shelf.

🗣️

Linguistics & languages

Grammar, treebanks and parsing, pragmatics and discourse, the lexicon, and the languages themselves — English, French, Latin, Ancient Greek, Hebrew, Aramaic, Semitic and more.

3577 papers 🌐