Skip to content

Releases: CUNY-CL/udtube

Adds parser head

14 Jun 01:53
e86f9e0

Choose a tag to compare

Adds parser task using deep biaffine parser (#120)

* Adds metrics for parsing

* Beginning integration

* Adds metrics test.

One major issue is that this requires us to use negative indices for
specials, which breaks assumptions in the indexes. Will have to come
back and fix this.

* Draft of parser and its integration

* More work.

Known issues:

1. I don't think the metrics test is going to work; I will need to shift
   all the head indices by special.OFFSET.
2. I am not passing a parser mask. Do I need to? I think maybe yes.

* Applies shift to metrics test to avoid collisions.

* Moves reverse_edits to data, where it belongs.

It has no effect in the model, so let's get rid of it.

* Days' debugging work

* More work; still debugging

* Optimizes mmap instructions (#116)

* Updates Black version

* Adds logging for vocabularies (#117)

* Adds logging for vocabularies

Sample output:

INFO: 22-Feb-26 17:56:27 - UPOS vocabulary (21): '[PAD]', '[UNK]', '_', 'ADJ', 'ADP', 'ADV', 'AUX', 'CCONJ', 'DET', 'INTJ', 'NOUN', 'NUM', 'PART', 'PRON', 'PROPN', 'PUNCT', 'SCONJ', 'SYM', 'VERB', 'X', '_'
INFO: 22-Feb-26 17:56:27 - XPOS vocabulary (53): '[PAD]', '[UNK]', '_', '$', "''", ',', '-LRB-', '-RRB-', '.', ':', 'ADD', 'AFX', 'CC', 'CD', 'DT', 'EX', 'FW', 'GW', 'HYPH', 'IN', 'JJ', 'JJR', 'JJS', 'LS', 'MD', 'NFP', 'NN', 'NNP', 'NNPS', 'NNS', 'PDT', 'POS', 'PRP', 'PRP$', 'RB', 'RBR', 'RBS', 'RP', 'SYM', 'TO', 'UH', 'VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ', 'WDT', 'WP', 'WP$', 'WRB', '_', '``'
INFO: 22-Feb-26 17:56:27 - Lemma vocabulary (533): [omitted]
INFO: 22-Feb-26 17:56:27 - Features vocabulary (235): [omitted]

Closes #115.

* black update

* f-string fix

* driveby: silence more warnings

* Avoids "Crashed" status in sweeps. (#118)

See Yoyodyne [#369](https://github.com/CUNY-CL/yoyodyne/pull/369) for
context.

Closes #79.

* Pooling layer efficiency (#119)

* Fix pooling layer regression in UDTubeEncoder.forward

Special cases pooling_layers=1 to use last_hidden_state directly, avoiding
unnecessary allocation of all hidden states. This seems to save a lot of
GPU memory.

A few drive-bys:

1. suppress progress bar during test data generation
2. add "not human-readable" to "[omitted]" when logging lemmas
3. actually log features; why not?
4. pass information about which heads to build to the data module too,
   so it logs properly
5. removes _ from "special", since it doesn't require any special
   treatment in actuality; it's just another tag as far as we're
   concerned.
6. Standardizes trailing """: it's on its own line if the comment is
   more than one line.

* regeneration last-minute fix

* Update special.py

* fix typo

* Optimizes mmap instructions (#116)

* Adds logging for vocabularies (#117)

* Adds logging for vocabularies

Sample output:

INFO: 22-Feb-26 17:56:27 - UPOS vocabulary (21): '[PAD]', '[UNK]', '_', 'ADJ', 'ADP', 'ADV', 'AUX', 'CCONJ', 'DET', 'INTJ', 'NOUN', 'NUM', 'PART', 'PRON', 'PROPN', 'PUNCT', 'SCONJ', 'SYM', 'VERB', 'X', '_'
INFO: 22-Feb-26 17:56:27 - XPOS vocabulary (53): '[PAD]', '[UNK]', '_', '$', "''", ',', '-LRB-', '-RRB-', '.', ':', 'ADD', 'AFX', 'CC', 'CD', 'DT', 'EX', 'FW', 'GW', 'HYPH', 'IN', 'JJ', 'JJR', 'JJS', 'LS', 'MD', 'NFP', 'NN', 'NNP', 'NNPS', 'NNS', 'PDT', 'POS', 'PRP', 'PRP$', 'RB', 'RBR', 'RBS', 'RP', 'SYM', 'TO', 'UH', 'VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ', 'WDT', 'WP', 'WP$', 'WRB', '_', '``'
INFO: 22-Feb-26 17:56:27 - Lemma vocabulary (533): [omitted]
INFO: 22-Feb-26 17:56:27 - Features vocabulary (235): [omitted]

Closes #115.

* black update

* f-string fix

* driveby: silence more warnings

* Avoids "Crashed" status in sweeps. (#118)

See Yoyodyne [#369](https://github.com/CUNY-CL/yoyodyne/pull/369) for
context.

Closes #79.

* Pooling layer efficiency (#119)

* Fix pooling layer regression in UDTubeEncoder.forward

Special cases pooling_layers=1 to use last_hidden_state directly, avoiding
unnecessary allocation of all hidden states. This seems to save a lot of
GPU memory.

A few drive-bys:

1. suppress progress bar during test data generation
2. add "not human-readable" to "[omitted]" when logging lemmas
3. actually log features; why not?
4. pass information about which heads to build to the data module too,
   so it logs properly
5. removes _ from "special", since it doesn't require any special
   treatment in actuality; it's just another tag as far as we're
   concerned.
6. Standardizes trailing """: it's on its own line if the comment is
   more than one line.

* regeneration last-minute fix

* Beginning integration

* Adds metrics test.

One major issue is that this requires us to use negative indices for
specials, which breaks assumptions in the indexes. Will have to come
back and fix this.

* Draft of parser and its integration

* More work.

Known issues:

1. I don't think the metrics test is going to work; I will need to shift
   all the head indices by special.OFFSET.
2. I am not passing a parser mask. Do I need to? I think maybe yes.

* Moves reverse_edits to data, where it belongs.

It has no effect in the model, so let's get rid of it.

* Days' debugging work

* More work; still debugging

* Optimizes mmap instructions (#116)

* Pooling layer efficiency (#119)

* Fix pooling layer regression in UDTubeEncoder.forward

Special cases pooling_layers=1 to use last_hidden_state directly, avoiding
unnecessary allocation of all hidden states. This seems to save a lot of
GPU memory.

A few drive-bys:

1. suppress progress bar during test data generation
2. add "not human-readable" to "[omitted]" when logging lemmas
3. actually log features; why not?
4. pass information about which heads to build to the data module too,
   so it logs properly
5. removes _ from "special", since it doesn't require any special
   treatment in actuality; it's just another tag as far as we're
   concerned.
6. Standardizes trailing """: it's on its own line if the comment is
   more than one line.

* regeneration last-minute fix

* Manual merge

* README and bibliography

* stashing incomplete work

* updates parser

* Parser testing

* Expands grid for biaffine parsing hparams

* Adds the parser itself

* Updates tests

Eliminates a test bug where the file comparisons were against the
hypothesis file!

* reflows README

* updates encoder special-casing logic slightly

* Update mappers.py

* Daniel's suggestion

Optimization for using last hidden layer pooling

05 Apr 23:23
332f98e

Choose a tag to compare

Pooling layer efficiency (#119)

* Fix pooling layer regression in UDTubeEncoder.forward

Special cases pooling_layers=1 to use last_hidden_state directly, avoiding
unnecessary allocation of all hidden states. This seems to save a lot of
GPU memory.

A few drive-bys:

1. suppress progress bar during test data generation
2. add "not human-readable" to "[omitted]" when logging lemmas
3. actually log features; why not?
4. pass information about which heads to build to the data module too,
   so it logs properly
5. removes _ from "special", since it doesn't require any special
   treatment in actuality; it's just another tag as far as we're
   concerned.
6. Standardizes trailing """: it's on its own line if the comment is
   more than one line.

* regeneration last-minute fix

Improvements to W&B sweep logging

18 Mar 13:28
3c79442

Choose a tag to compare

Avoids "Crashed" status in sweeps. (#118)

See Yoyodyne [#369](https://github.com/CUNY-CL/yoyodyne/pull/369) for
context.

Closes #79.

v0.1.9: Adds logging for vocabularies (#117)

22 Feb 23:40
069fbcc

Choose a tag to compare

* Adds logging for vocabularies

Sample output:

INFO: 22-Feb-26 17:56:27 - UPOS vocabulary (21): '[PAD]', '[UNK]', '_', 'ADJ', 'ADP', 'ADV', 'AUX', 'CCONJ', 'DET', 'INTJ', 'NOUN', 'NUM', 'PART', 'PRON', 'PROPN', 'PUNCT', 'SCONJ', 'SYM', 'VERB', 'X', '_'
INFO: 22-Feb-26 17:56:27 - XPOS vocabulary (53): '[PAD]', '[UNK]', '_', '$', "''", ',', '-LRB-', '-RRB-', '.', ':', 'ADD', 'AFX', 'CC', 'CD', 'DT', 'EX', 'FW', 'GW', 'HYPH', 'IN', 'JJ', 'JJR', 'JJS', 'LS', 'MD', 'NFP', 'NN', 'NNP', 'NNPS', 'NNS', 'PDT', 'POS', 'PRP', 'PRP$', 'RB', 'RBR', 'RBS', 'RP', 'SYM', 'TO', 'UH', 'VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ', 'WDT', 'WP', 'WP$', 'WRB', '_', '``'
INFO: 22-Feb-26 17:56:27 - Lemma vocabulary (533): [omitted]
INFO: 22-Feb-26 17:56:27 - Features vocabulary (235): [omitted]

Closes #115.

* black update

* f-string fix

* driveby: silence more warnings

Adds memory mapping support

01 Jan 20:35

Choose a tag to compare

v0.1.8

bumps version number

v0.1.7: Adds Omegaconf support and migrates Yoyodyne version (#111)

30 Dec 16:57
5422a3a

Choose a tag to compare

* omegaconf support and yoyodyne migration

* version bump

v0.1.6: Many small updates (#108)

10 Dec 16:12
c8dc434

Choose a tag to compare

* Correctly compare evaluation results.

Previously, the generated evaluation results were compared with
themselves, which always passes (of course).

I also converted test data regeneration to a proper script.

* Updates test config

* Updates README.md

* narrows versions

* Loosen numpy requirement slightly.

* Lightning,

* Many small improvements.

* Bumps version number
* Adds Python 3.14 support
* Uses Yoyodyne elements where appropriate
* Updates README to reflect the previous
* Uses `transpose` instead of `permute` where the former is clearer
* Migrates sweeping to `yoyodyne_sweep`, which does everything we need

* Renames cli function

* Removes filename from logging

* more cli

v0.1.2: Merge pull request #95 from kylebgorman/version

23 Jan 22:33
705233e

Choose a tag to compare

v0.1.1: Merge pull request #91 from CUNY-CL/version

18 Jan 22:08
ca3d1dc

Choose a tag to compare

v0.1.0

28 Oct 21:55
19bbee7

Choose a tag to compare

This is the first open-source release of UDTube.