Hacker News Reader

Comment by stingraycharles | Hacker News Reader

Back in the day - maybe two decades ago - I implemented language detection like this.

I seeded gzip compressors’ dictionaries with Wikipedia articles in different languages.

I would then try to use said dictionaries on any random text, and the one that was best able to compress it, was the correct language.

Absolutely totally not the best approach, but very fast and super simple to implement.

View on HN

Or maybe make a list of the most used 1000 words in each language. And see which list has the most occurrences.

That requires you to decide what a "word" is, which is not trivial (if you think that ignoring punctuation gets you to a clean "letters surrounded by spaces" you will get lots of issues with various Asian languages)

Also some languages have a lot of prefixes and suffixes on their verbs or even nouns, which dilutes your list of 1000 words by just adding the same common words over and over again with different suffixes designating grammatical tense, grammatical gender, etc.

The gzip version sounds more general and more obviously correct

Instead of deciding on words, maybe you can break them up into smaller, subword parts – let's call them "quantums". And these quantums can be the units the quantumizer works on to operate on inputs and outputs. We can then use them to build Expansive Dictionary Models, or EDMs. I suppose we'd need a software library to mak working on this easier, think something speedy, fast, hot, like fire: we can call it PHPFlame...

I'm guessing this is an allusion to reinventing something that already exists, but do you mind explaining what that is to me, since I don't know?

I suspect they're talking about LLM tokens.

It is describing essentially how tokenisation is done for LLMs (Large Language Model → Expansive Dictionary Model).

You mean Quantumnisation ;)

You can just use 2-grams of Unicode code points.

Very much agree. Character bigrams will solve this perfectly with tiny amounts of training data (like a couple KB).

Byte Pair Encoding [1] will be different for different languages. Application of the per-language BPEs to the input text will produce encodings with different lengths.

[1] https://en.wikipedia.org/wiki/Byte-pair_encoding

It naturally takes care of common prefixes and suffixes.

It is easy and fast to apply using radix tree or with finite automata. Even without radix tree, it is possible to have processing speed in the range of hundredths of thousands of bytes per second.

Even German has issues with "letters surrounded by spaces". They love to smash words together to get one giant word.

https://www.youtube.com/watch?v=m8niIHChc1Y

Just collect common bi- and trigrams and a naive bayesian classifier.

See: Fast Static Symbol Table: https://github.com/duckdb/duckdb/pull/4366

FSST is based on a fixed size (255 items) dictionary of high frequency variable length strings/substrings (learned from the corpus) encoded as one byte.

Sounds like the best approach. :)

Reply on news.ycombinator.com