Translation
Miscellaneous
ASR/TTS
Sounds and Letters
Spellcheckers
100

The relationship of sofa to couch

What is synonym?

100

Babbling is a stage in this type of language acquisition.

What is first language acquisition?

100

Turning written text into speech is this process.

What is text-to-speech synthesis?

100

These are two media types that computers can store and represent human language.

What are audio and text?

100

This type of spelling error are easier for spellcheckers to find and correct because the resulting string cannot be found in a dictionary.

What is a non-word error?

200

The relationship of cell to sell

What is a homophone?

200

To find word boundaries in a text is this.

What is tokenization?

200

These properties of speech sounds are easier to quantify but do not tell us how the sounds are articulated (physically created).

What are acoustic (phonetic) properties?

200

This numbering system has only two possible values, 0 and 1.

What is binary?

200

A table indicating how often one letter is mistyped for another.

What is a confusion matrix?

300

The approach of modeling the entire machine translation process via one big artificial "neural network".

What is Neural machine translation?

300

The process of automatically identifying dates, addresses, and names.

What is named entity recognition?

300
ASR systems learn to do this automatically by training on lots of this specific type of data which takes hours to produce by hand.


What is to transcribe speech?

300

It provides a unique number for every character, no matter what the platform, no matter what the program, no matter what the language.

What is Unicode?

300

Insertion, deletion, substitution, and transposition are types of this.

What are string edit operations?

400

When a speaker alternates between two or more languages, or language varieties, in the context of a single conversation or situation.

What is codeswitching?

400

The fraction of relevant instances among the retrieved instances.

What is precision?

400

This occurs when digitally sampling speech because speech is continuous but data must be stored discretely.

What is information loss?

400

These two main types of writing systems are meaning-based or sound-based.

What are logographics and letters?

400

The words "jumps", "jumping", "jump", and "jumped" are an example of this systematic change to a word form where each change expresses slightly different grammatical meanings such as tense or plurality.

What is morphological inflection?