Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

#4399 - Allow open nlp multi token sequence classifier to work for cross sentence layers #4417

Conversation

reckart
Copy link
Member

@reckart reckart commented Dec 31, 2023

What's in the PR

  • Siding-window training for OpenNLP NER when cross-sentence annotations are allowed

How to test manually

  • Switch layer to cross-sentence mode and try recommender

Automatic testing

  • PR includes unit tests

Documentation

  • PR updates documentation

…ss-sentence layers

- Towards supporting a sliding-window approach
…ss-sentence layers

- Reduce window size to 100 chars for the moment
- Allow predicting spans with no label
- Fix endless loop bug in sliding window sample generation
…ss-sentence layers

- Use var in some places
…nce-Classifier-to-work-for-cross-sentence-layers

* main:
  #4400 - Display recoomender name in log instead of RecommenderContext
  #4397 - Better error message when PMC document cannot be found
…nce-Classifier-to-work-for-cross-sentence-layers

* main:
  #4402 - Some suggestions are not hidden even though they cannot be accepted
  #4406 - Useless "not in tagset" message on suggestions without a label
  #4406 - Useless "not in tagset" message on suggestions without a label
  #4404 - Some suggestions are not shown right away
…nce-Classifier-to-work-for-cross-sentence-layers

* main:
  #4408 - String Matching Recommender does not evaluate on annotations without label
  #4402 - Some suggestions are not hidden even though they cannot be accepted
…nce-Classifier-to-work-for-cross-sentence-layers

* main:
  #4410 - OpenNLP multi-token sequence classifier does not learn from annotations without labels
  #4412 - PMC search returns some results that cannot be imported

% Conflicts:
%	inception/inception-imls-opennlp/src/main/java/de/tudarmstadt/ukp/inception/recommendation/imls/opennlp/ner/OpenNlpNerRecommender.java
…nce-Classifier-to-work-for-cross-sentence-layers

* main:
  #4414 - Number of new suggestions not displayed correctly
…nce-Classifier-to-work-for-cross-sentence-layers

* main:
  [maven-release-plugin] prepare for next development iteration
  [maven-release-plugin] prepare release inception-30.1
…ss-sentence layers

- Adjust window size depending on document size
- Improve API of AnnotationBuilder
@reckart reckart added this to the 31.0 milestone Dec 31, 2023
@reckart reckart self-assigned this Dec 31, 2023
@reckart reckart merged commit 9bdc272 into main Dec 31, 2023
@reckart reckart deleted the feature/4399-Allow-OpenNLP-Multi-Token-Sequence-Classifier-to-work-for-cross-sentence-layers branch December 31, 2023 12:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

1 participant