spaCy/spacy/kb/candidate.pyx

75 lines
2.5 KiB
Cython
Raw Normal View History

Refactor KB for easier customization (#11268) * Add implementation of batching + backwards compatibility fixes. Tests indicate issue with batch disambiguation for custom singular entity lookups. * Fix tests. Add distinction w.r.t. batch size. * Remove redundant and add new comments. * Adjust comments. Fix variable naming in EL prediction. * Fix mypy errors. * Remove KB entity type config option. Change return types of candidate retrieval functions to Iterable from Iterator. Fix various other issues. * Update spacy/pipeline/entity_linker.py Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> * Update spacy/pipeline/entity_linker.py Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> * Update spacy/kb_base.pyx Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> * Update spacy/kb_base.pyx Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> * Update spacy/pipeline/entity_linker.py Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> * Add error messages to NotImplementedErrors. Remove redundant comment. * Fix imports. * Remove redundant comments. * Rename KnowledgeBase to InMemoryLookupKB and BaseKnowledgeBase to KnowledgeBase. * Fix tests. * Update spacy/errors.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Move KB into subdirectory. * Adjust imports after KB move to dedicated subdirectory. * Fix config imports. * Move Candidate + retrieval functions to separate module. Fix other, small issues. * Fix docstrings and error message w.r.t. class names. Fix typing for candidate retrieval functions. * Update spacy/kb/kb_in_memory.pyx Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/ml/models/entity_linker.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix typing. * Change typing of mentions to be Span instead of Union[Span, str]. * Update docs. * Update EntityLinker and _architecture docs. * Update website/docs/api/entitylinker.md Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> * Adjust message for E1046. * Re-add section for Candidate in kb.md, add reference to dedicated page. * Update docs and docstrings. * Re-add section + reference for KnowledgeBase.get_alias_candidates() in docs. * Update spacy/kb/candidate.pyx * Update spacy/kb/kb_in_memory.pyx * Update spacy/pipeline/legacy/entity_linker.py * Remove canididate.md. Remove mistakenly added config snippet in entity_linker.py. Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2022-09-08 11:38:07 +03:00
# cython: infer_types=True, profile=True
from typing import Iterable
from .kb cimport KnowledgeBase
from ..tokens import Span
cdef class Candidate:
"""A `Candidate` object refers to a textual mention (`alias`) that may or may not be resolved
to a specific `entity` from a Knowledge Base. This will be used as input for the entity linking
algorithm which will disambiguate the various candidates to the correct one.
Each candidate (alias, entity) pair is assigned a certain prior probability.
DOCS: https://spacy.io/api/kb/#candidate-init
"""
def __init__(self, KnowledgeBase kb, entity_hash, entity_freq, entity_vector, alias_hash, prior_prob):
self.kb = kb
self.entity_hash = entity_hash
self.entity_freq = entity_freq
self.entity_vector = entity_vector
self.alias_hash = alias_hash
self.prior_prob = prior_prob
@property
def entity(self) -> int:
"""RETURNS (uint64): hash of the entity's KB ID/name"""
return self.entity_hash
@property
def entity_(self) -> str:
"""RETURNS (str): ID/name of this entity in the KB"""
return self.kb.vocab.strings[self.entity_hash]
@property
def alias(self) -> int:
"""RETURNS (uint64): hash of the alias"""
return self.alias_hash
@property
def alias_(self) -> str:
"""RETURNS (str): ID of the original alias"""
return self.kb.vocab.strings[self.alias_hash]
@property
def entity_freq(self) -> float:
return self.entity_freq
@property
def entity_vector(self) -> Iterable[float]:
return self.entity_vector
@property
def prior_prob(self) -> float:
return self.prior_prob
def get_candidates(kb: KnowledgeBase, mention: Span) -> Iterable[Candidate]:
"""
Return candidate entities for a given mention and fetching appropriate entries from the index.
kb (KnowledgeBase): Knowledge base to query.
mention (Span): Entity mention for which to identify candidates.
RETURNS (Iterable[Candidate]): Identified candidates.
"""
return kb.get_candidates(mention)
def get_candidates_batch(kb: KnowledgeBase, mentions: Iterable[Span]) -> Iterable[Iterable[Candidate]]:
"""
Return candidate entities for the given mentions and fetching appropriate entries from the index.
kb (KnowledgeBase): Knowledge base to query.
mention (Iterable[Span]): Entity mentions for which to identify candidates.
RETURNS (Iterable[Iterable[Candidate]]): Identified candidates.
"""
return kb.get_candidates_batch(mentions)