Papers › Extracting RDF Triples from Raw Text
Extracting RDF Triples from Raw Text
Yeasmin Ara Akter, Md. Ataur Rahman
This manuscript manifests the results of our work on extracting RDF triples from raw text data. We took a corpus of news articles and applied several methods for extracting “subject - verb - object” relationships from texts. The first method that we used is syntactic parsing and constructing triples from nsubj and obj syntactic relations. The second approach incorporates extracting semantic roles with the help of frame parser and constructing triples from agent, patient and predicate relationships. After applying the aforementioned methods, a manual evaluation was done over a small number of hand labeled samples. Our system achieved a Precision score of 0.34, Recall of 0.46 and a combined score of 0.39 for F-measure as the final result.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections