Rifqi Hafizuddin
[NOTICKET] feat(knowledge_extraction): free stages — models, seam adapter, filters, cluster, ranking
024c30a
Raw
History Blame
1.08 kB
# Discourse cues (definitional) and legend-block patterns.
# Used by cue_filter (rule candidates) and evidence ranking (+5.0 signal).
definitional_id:
- '\badalah kondisi ketika\b'
- '\badalah\b'
- '\bmerupakan\b'
- '\byaitu\b'
- '\bdidefinisikan sebagai\b'
- '\bdimaksud dengan\b'
definitional_en:
- '\bis defined as\b'
- '\brefers to\b'
- '\bis the\b'
- '\bmeans\b'
conditional_id:
- '\bapabila\b'
- '\bjika\b.{0,80}\bmaka\b'
- '\bbila\b'
- '\bharus\b'
- '\btidak boleh\b'
- '\bwajib\b'
conditional_en:
- '\bif\b.{0,80}\bthen\b'
- '\bmust\b'
- '\bshall\b'
- '\bNote that\b'
note_id:
- '^\s*Catatan\b'
- '^\s*Sebagai contoh\b'
- '^\s*Contoh\b'
# Legend blocks: 'Keterangan:' / 'Dimana:' / 'where' introduce symbol tables.
legend_headers:
- '^\s*Keterangan\s*[::]'
- '^\s*Dimana\s*[::]'
- '^\s*Di\s*mana\s*[::]'
- '^\s*[Ww]here\s*[::]'
legend_entry: '^\s*([A-Za-z][A-Za-z0-9_\.]{0,12})\s*[:=]\s*(.+)$'
# A chunk is 'formula present' if any of these appear.
formula_markers:
- '='
- '×'
- '\bx\s*100\s*%'
- '/'