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

Multi sentence input ignoring first sentences [including workaround] #27

Open
SophieSiebert opened this issue Feb 26, 2020 · 0 comments

Comments

@SophieSiebert
Copy link

SophieSiebert commented Feb 26, 2020

While feeding multiple sentences to knews, we noticed an error. If we feed in, e.g. four sentences at once, or four sentences one after another, the output of 'all sentences' is quite similar (sometimes even exact similar) to the output of only the last sentence. The differences merely appear in the synsets (different sysnset ids, or no found synset) never in the structure.

However, if we replace the periods within the text (not the last one) with a semicolon, we get a more expected result, which is longer and holds information of all the four sentences. We do not yet know, however, if this comes with other downsides.

Also, we found it conspicuous, that in the 'all sentence semicolon' variant, an exzessiv amount of variables seems to be generated.
Look here for detailed in and output
The example is from https://cs.rochester.edu/nlp/rocstories/

Configuration:
[semantics] : boxer
[wsd], [el]: babelfy
[net]: wordnet
[boxer]: soap

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant