Repository navigation
CRF ablations and learning curve - #46
Merged
Merged
Conversation
The CRF gains use_context and max_train_documents options, and the experiment runner now runs CRF configs (family = "crf"). configs/experiments/crf-ablations.toml and scripts/experiments/crf_ablations.sh measure, as agreement with the 172 model-drafted dev records, that neither feature group makes a clear difference and that typed agreement stops rising at about 120 training documents. The full-data run reproduces the released crf-batches-01-02 predictions exactly.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds CRF context/part-of-speech ablations and a training-size learning curve, run from
configs/experiments/crf-ablations.tomlviascripts/experiments/crf_ablations.sh.CrfExtractor.train(use_context=, max_train_documents=),train --no-context --max-train-documents, andexperimentrunsfamily = "crf"configs (unknown settings rejected; bundles reused on resume). Old bundles load with context on.crf-batches-01-02predictions.