feat(config): add new scoring parameters for phrase extraction and matching

python/ebook_search/config.py

@@ -91,6 +91,7 @@ class EbookSearchConfig(BaseSettings):
     phrase_min_tokens: int = 2
     phrase_max_tokens: int = 5
     phrase_max_entity_tokens: int = 8
+    phrase_yake_top_k: int = 1000
     phrase_raw_ngram_min_count: int = 2
     phrase_raw_count_score_threshold: int = 3
     phrase_raw_count_high_score_threshold: int = 10
@@ -99,6 +100,10 @@ class EbookSearchConfig(BaseSettings):
     phrase_target_protected_per_book: int = 100
     phrase_default_allow_nested: bool = False
     phrase_default_suppress_children: bool = True
+    phrase_bad_start_score_penalty: float = 10.0
+    phrase_bad_end_score_penalty: float = 10.0
+    phrase_multi_source_score_bonus: float = 2.0
+    phrase_multi_source_min_sources: int = 2
 
     @field_validator("library_paths", mode="before")
     @classmethod