explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-06 06:03:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

Adjust Candidate to support and mandate numerical entity IDs.

Browse Source
This commit is contained in:
Raphael Mitsch 2023-03-01 14:50:58 +01:00
parent 49abf4fb3a
commit fa390618c8
1 changed files with 20 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
spacy/kb/candidate.py
View File

@ -12,26 +12,33 @@ class Candidate(abc.ABC):
""" """
def __init__( def __init__(
self, mention: str, entity_id: Union[int, str], entity_vector: List[float] self, mention: str, entity_id: int, entity_name: str, entity_vector: List[float], prior_prob: float
): ):
"""Initializes properties of `Candidate` instance. """Initializes properties of `Candidate` instance.
mention (str): Mention text for this candidate. mention (str): Mention text for this candidate.
entity_id (Union[int, str]): Unique entity ID. entity_id (int): Unique entity ID.
entity_name (str): Entity name.
entity_vector (List[float]): Entity embedding. entity_vector (List[float]): Entity embedding.
prior_prob (float): Prior probability of entity for this mention - i.e. the probability that, independent of
the context, this mention resolves to this entity_id in the corpus used to build the knowledge base. In
cases in which this isn't always possible (e.g.: the corpus to analyse contains mentions that the KB corpus
doesn't) it might be better to eschew this information and always supply the same value.
""" """
self._mention = mention self._mention = mention
self._entity_id = entity_id self._entity_id = entity_id
self._entity_name = entity_name
self._entity_vector = entity_vector self._entity_vector = entity_vector
self._prior_prob = prior_prob
@property @property
def entity(self) -> Union[int, str]: def entity(self) -> int:
"""RETURNS (Union[int, str]): Entity ID.""" """RETURNS (int): Unique entity ID."""
return self._entity_id return self._entity_id
@property @property
@abc.abstractmethod
def entity_(self) -> str: def entity_(self) -> str:
"""RETURNS (str): Entity name.""" """RETURNS (int): Entity name."""
return self._entity_name
@property @property
def mention(self) -> str: def mention(self) -> str:
@ -43,6 +50,11 @@ class Candidate(abc.ABC):
"""RETURNS (List[float]): Entity vector.""" """RETURNS (List[float]): Entity vector."""
return self._entity_vector return self._entity_vector
@property
def prior_prob(self) -> float:
"""RETURNS (List[float]): Entity vector."""
return self._prior_prob
class InMemoryCandidate(Candidate): class InMemoryCandidate(Candidate):
"""Candidate for InMemoryLookupKB.""" """Candidate for InMemoryLookupKB."""
@ -71,7 +83,9 @@ class InMemoryCandidate(Candidate):
super().__init__( super().__init__(
mention=retrieve_string_from_hash(alias_hash), mention=retrieve_string_from_hash(alias_hash),
entity_id=entity_hash, entity_id=entity_hash,
entity_name=retrieve_string_from_hash(entity_hash),
entity_vector=entity_vector, entity_vector=entity_vector,
prior_prob=prior_prob,
) )
self._retrieve_string_from_hash = retrieve_string_from_hash self._retrieve_string_from_hash = retrieve_string_from_hash
self._entity_hash = entity_hash self._entity_hash = entity_hash
@ -84,11 +98,6 @@ class InMemoryCandidate(Candidate):
"""RETURNS (int): hash of the entity_id's KB ID/name""" """RETURNS (int): hash of the entity_id's KB ID/name"""
return self._entity_hash return self._entity_hash
@property
def entity_(self) -> str:
"""RETURNS (str): ID/name of this entity_id in the KB"""
return self._retrieve_string_from_hash(self._entity_hash)
@property @property
def alias(self) -> int: def alias(self) -> int:
"""RETURNS (int): hash of the alias""" """RETURNS (int): hash of the alias"""
@ -102,8 +111,3 @@ class InMemoryCandidate(Candidate):
@property @property
def entity_freq(self) -> float: def entity_freq(self) -> float:
return self._entity_freq return self._entity_freq
@property
def prior_prob(self) -> float:
"""RETURNS (List[float]): Entity vector."""
return self._prior_prob