Your English writing platform
Discover LudwigSuggestions(1)
Exact(6)
This list then underwent various stages of processing, all of which related to the features provided by the participants and left the relation words untouched.
The feature set finally selected through this process includes 27 relation words.
However, we soon observed that some important but low-frequency relation words were not captured.
The relation words were is, has, does, made of, and "…" (participants were instructed to use "…" when they wished to use any other relation).
As for the relation words, we compiled 67 keywords that clearly describe various types of interactions between a pair of proteins.
The features (namely, relation words) were compiled, as follows: 1) we extract the verbs from the corpus, 2) compute the frequencies of all verbs, 3) and choose top-k frequent words and manually screen the list to eliminate inappropriate words.
Similar(53)
The participants were asked to add a relation word chosen from a drop down menu.
We first find a relation word "binding" and follow the prep_of dependency to retrieve the first protein P0.
Note that we also handle negation by checking if a negation (neg) dependency exists on either the relation word or the subject.
First, as in the example, "no interaction of P0 with P1 was found," the negation (neg) dependency must be checked on the relation word ("interaction").
In the example, P0 is the subject of "interacts," a relation word, and P1 is the prepositional modifier of "interacts," and hence P0 - P1 matches the rule.
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com