In Toradocu the input sentence shape is <= 0 or scale is <= 0. is preprocessed into shape is INEQUALITY_0 or scale is INEQUALITY_1.
The semantic graph produced by the Stanford parser is the following:
The difference in the graphs is due to the different POS tagging of the inequalities placeholders.
I suggest to modify the current proposition extractor to:
Preprocess-text like we currently do.
Ad-hoc POS-tag the inequalities placeholder words as JJ (adjective) or another tag that make sense and cause the Stanford Parser to behave correctly.
In Toradocu the input sentence
shape is <= 0 or scale is <= 0.
is preprocessed intoshape is INEQUALITY_0 or scale is INEQUALITY_1.
The semantic graph produced by the Stanford parser is the following:Instead, we expect a graph like the following:
The difference in the graphs is due to the different POS tagging of the inequalities placeholders. I suggest to modify the current proposition extractor to:
More information about how to add custom POS tags can be found here: https://nlp.stanford.edu/software/parser-faq.shtml#f