User:Popcorndude

From Apertium
Revision as of 18:06, 23 December 2022 by Popcorndude (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Hi! I'm Daniel. IRC is generally the fastest way to contact me. I'm usually in US central or eastern time (UTC-4 - UTC-6), but I read the logs, so leave messages whenever.

The rest of this page is my project list. Feel free to steal ideas from it, especially if you want to collaborate.

Also, because prioritizing is hard, User:Popcorndude/What_should_Daniel_work_on exists so that other people can vote on what order I do this stuff in.

Things I (think I) know how to do

Modernizing old pairs

Some of the old pairs are a mess. There's some monolingualizing to be done, random files are missing, and there are workarounds to missing features that now exist. Also the READMEs are terrible. Basically the plan is to make most things look more like what Apertium-init generates.

Nicer UI for contributing

See Ideas_for_Google_Summer_of_Code/Bidix_lookup_and_maintenance. I'm much less certain about similar contributions to monodix. For transfer though you could probably make something that shows the tree that gets built and then have a drag-and-drop interface to fix errors.

Automate transition to -separable

Some monodixes have slightly horrifying multiwords in them, such as this one:

<e lm="you can lead a horse to water but you can't make it drink"><i>you<b/>can<b/>lead<b/>a<b/>horse<b/>to<b/>water<b/>but<b/>you<b/>can't<b/>make<b/>it<b/>drink</i><par n="hello__ij"/></e>

It shouldn't be too hard to extract the multiwords from a monodix and convert them to -separable entries. The fact that they're in the monodix means they're contiguous so there's no information lost.

Updating documentation

This should be reasonably self-explanatory.

UD parsing

See below for notes on doing this with rtx, but really it would probably be easier to do it separately.

UD parsing in -recursive

DET @det:3 ADJ @amod:3 NOUN
^the<det>$ ^green<adj>$ ^dragon<n>$
-> ^the<det>$ ^dragon<n><@@amod>{^green<adj><@amod>$ ^dragon<n>$}$
-> ^dragon<n><@@amod><@@det>{^the<det><@det>$ ^green<adj><@amod>$ ^dragon<n>$}$

Tricky things: non-projective stuff? transfer?

(the double atted tags are to keep track of (e.g.) if you need a rule that applies to a noun with case marking)

Transfer system based on UD

Basically a system for writing tree/graph rewrite operations for the handful of pair-specific things that remain after implementing a UD parser and un-parser.

UD un-parsing

Some sort of language model that takes a list of LUs and dependency relations and determines the appropriate order (and agreement info?) for them, possibly taking source order into account. In conjunction with a UD parser, this should produce at least somewhat functional transfer between any pair of languages with a bidix.

Rule-Explainer

Using https://github.com/tree-sitter/tree-sitter/tree/master/lib/binding_web it should be possible to make a web page that parses a rule file and explains what each piece is doing (bonus points for live updating and hovering over code or explanation to highlight the relevant section of the other one). Would make a nice teaching and debugging tool.

Unordered Generation

Something that operates like lt-proc -g but tries all tags in the input at all possible points so that it doesn't matter where they're supposed to be (start, end, middle, reverse order, ...) as long as the right set is present. Probably helpful for the prefix-tags debate.

Things I don't know how to do

Better tokenization

Multiwords and space-less orthographies.

Learning transfer rules from small corpora

Given a syntactic parser for one language and a fairly small parallel corpus it seems like it should be possible to learn decent transfer rules. (This turns out to be a lot harder than I thought.)

Import data from FieldWorks

SIL FieldWorks processes things like lexical and morphological data. It might be possible to take data from it and build a transducer.

Learn morphology from small corpora

Most of the things on this page are components of the translation memory idea, which will need to be able to learn some amount of morphology as it goes, though I currently have very little idea how to do that.

Translation Memory ++

A translation memory remembers phrases as you translate so you don't have to translate them again. This idea would be like that but would build an Apertium pair rather than just storing phrases. It could give you a draft of one page, and then improve the draft of the next page based on your postedits.

Rule-based semantics

If we used -recursive's tree output as the input to some sort of semantics system, could we do anything interesting with information extraction?

See rule effect

A tool that takes a rule in any module and finds every line in a corpus where it would apply.

Things I've already done

Apertium-recursive

I really don't like XML or finite-state chunking, hence the new transfer module.

Unicode everywhere

Pretty much all the main modules should handle non-ASCII characters correctly now.

Using -separable for Postgen

Have lsx-proc -p read things like ^lemma<tags>/surface$ and output the same, with LUs in the rules matching either surface or lemma<tags>/surface (with literal / - shouldn't require an updates to the compiler), and output the same. Might have to restrict it to not adding or deleting anything, but not sure.

See Postgenerator

Capitalization Restoration

Move capitalization handling out of transfer and into a separate post-processor. See Capitalization restoration.

Relevant Pages

Automated_extraction_of_lexical_resources