Why do semantic roles matter to AI models?
A model extracts facts as “who - does what - to what”. A passive sentence with the actor dropped leaves a gap in that structure, which the model has to fill with a guess or skip the fact entirely. An active sentence delivers the complete set of information and can be quoted without modification.
What will you see in the report?
You get the share of sentences where the main topic is the actor, plus a list of sentences that need editing - with a ready active-voice proposal.
This is usually the fastest dimension to act on: the fixes are mechanical and require no new content.
Sample recommendations
Fragments of a report from an audit of a gaming mice category page in an electronics store.
Problem: The main topic is the object of the reader’s action: the agent of the sentence is “you”, not the product being described.
In our store you will find a wide choice of wired and wireless models optimised for different game genres.
Wired and wireless gaming mice cover every game genre - from FPS, through strategy, to MMO.
Problem: The sentence says what “you can do” instead of what the product does.
Thanks to varied sensors you can match the mouse to your needs.
Sensors with up to 26,000 DPI match the mouse sensitivity to your play style.
How do we measure semantic roles?
The reference point is the share of sentences in which the main topic acts as the agent. A well-written page reaches over 70% of the sentences where the topic appears at all. Below that threshold the content describes the topic from the outside instead of attributing actions to it, and the model loses the links between the entity and the facts.
How a role counts in a sentence
| Role of the central entity | Value |
|---|---|
| Actor (“The bank grants the loan”) | full |
| Object (“The loan is granted by the bank”) | half |
| Absent from the sentence | none |
What raises and what lowers the score?
Raises
- Active voice with an explicit actor
- The main topic named directly instead of replaced by a pronoun
- Concrete verbs (“lowers”, “shortens”) instead of constructions built on “is”
- A consistent perspective across the text - the same protagonist in the sentences
Lowers
- Passive voice with the actor dropped (“was implemented”, “is applied”)
- Subjectless constructions (“one should remember”, “it is worth considering”)
- Replacing the topic with a pronoun for whole paragraphs
- A shifting protagonist - product, then customer, then company, with no reason
The most common fix is turning the passive voice active
| Instead of | Write |
|---|---|
| “The loan is granted for up to 30 years” | “The bank grants the loan for up to 30 years” |
| “The panel was installed” | “The crew installs the panel in a single day” |
| “Servicing should be remembered” | “A heat pump needs servicing once a year” |
Frequently asked questions
Is the passive voice always a mistake?
No - the problem starts when the actor is dropped. “The bank makes the decision” is fine; “a decision is made” leaves the model with no information about who makes it.
What if the topic is a service rather than a company?
Then the actor is often the service or product itself: “the policy covers treatment costs”, “the heat pump cuts the bill by 40%”. The point is an unambiguous role for the main topic, not inserting the company name everywhere.
How quickly can this be fixed?
It is usually the cheapest dimension to repair. The fixes are mechanical - reordering a sentence - and need no new content or new data.