Skip to content

v0.21.2

Choose a tag to compare

@spranab spranab released this 07 Sep 02:28
· 14 commits to main since this release
32379e8

v0.21.2 — a sentence-final name ends at the period; a contraction is never a name

Schema unchanged (v52). Two extractor precision fixes (#221), no API change.

  • Sentence boundary. The chunker joined consecutive capitalized tokens across a period, so a name that ended a sentence welded to the capitalized word opening the next: moved to Munich. Assistant: ok minted the entity Munich Assistant and no lives_in claim could fire; works at Fennwick Labs. Alice Moreau lives in Berlin minted Fennwick Labs Alice Moreau. Chat transcripts end nearly every turn that way, and ordinary prose has the same shape. A period followed by whitespace now ends a name unless the token before it is an initial (J. K. Rowling) or a title (St. Louis, Dr. Smith, Gen.); company suffixes deliberately split; decimals are untouched.
  • Contractions. I'm, I'd, We'll, Don't, It's no longer open or extend a name, and the admission predicate refuses stored names containing one; O'Brien and D'Arcy stay names.
  • Measured on a 6,458-text production export (both arms drained to a fixed point): entities 14,614 → 13,733, four-plus-word names 346 → 326, heuristic claims 46 → 49 with one welded claim lost and four correct facts gained (Walmart Global Tech -headquartered_in-> Ramsey NJ, Pranab -lives_in-> Bentonville, …). On BEAM 100K the engine now mints Alice Moreau -lives_in-> Munich from a turn-formatted line it could not read before; the retrieved set changes on 21 of 400 contexts.

Deploying to an existing store: install, then reextract_claims() once so previously welded sentences yield their claims (idempotent). reextract_entities() is unchanged and also idempotent.