spaCy/spacy/syntax/ner.pyx

389 lines
12 KiB
Cython
Raw Normal View History

2015-02-02 05:38:52 +00:00
from __future__ import unicode_literals
2015-03-09 05:46:22 +00:00
from .transition_system cimport Transition
from .transition_system cimport do_func_t
2015-02-02 05:38:52 +00:00
2015-03-09 05:46:22 +00:00
from ..structs cimport TokenC, Entity
2015-02-02 05:38:52 +00:00
2015-03-09 05:46:22 +00:00
from thinc.typedefs cimport weight_t
from ..gold cimport GoldParseC
from ..gold cimport GoldParse
from ..attrs cimport ENT_TYPE, ENT_IOB
2015-02-02 05:38:52 +00:00
from .stateclass cimport StateClass
2015-02-02 05:38:52 +00:00
cdef enum:
MISSING
BEGIN
IN
LAST
UNIT
OUT
N_MOVES
2015-03-23 14:34:08 +00:00
MOVE_NAMES = [None] * N_MOVES
MOVE_NAMES[MISSING] = 'M'
MOVE_NAMES[BEGIN] = 'B'
MOVE_NAMES[IN] = 'I'
MOVE_NAMES[LAST] = 'L'
MOVE_NAMES[UNIT] = 'U'
MOVE_NAMES[OUT] = 'O'
2015-02-02 05:38:52 +00:00
2015-03-09 05:46:22 +00:00
cdef do_func_t[N_MOVES] do_funcs
2015-06-10 05:09:17 +00:00
cdef bint _entity_is_sunk(StateClass st, Transition* golds) nogil:
if not st.entity_is_open():
2015-03-09 05:46:22 +00:00
return False
cdef const Transition* gold = &golds[st.E(0)]
2015-03-09 05:46:22 +00:00
if gold.move != BEGIN and gold.move != UNIT:
return True
elif gold.label != st.E_(0).ent_type:
2015-03-09 05:46:22 +00:00
return True
else:
return False
2015-08-09 00:31:53 +00:00
2015-03-09 05:46:22 +00:00
cdef class BiluoPushDown(TransitionSystem):
@classmethod
def get_labels(cls, gold_tuples):
move_labels = {MISSING: {'': True}, BEGIN: {}, IN: {}, LAST: {}, UNIT: {},
OUT: {'': True}}
moves = ('M', 'B', 'I', 'L', 'U')
for raw_text, sents in gold_tuples:
for (ids, words, tags, heads, labels, biluo), _ in sents:
for i, ner_tag in enumerate(biluo):
if ner_tag != 'O' and ner_tag != '-':
if ner_tag.count('-') != 1:
raise ValueError(ner_tag)
_, label = ner_tag.split('-')
for move_str in ('B', 'I', 'L', 'U'):
move_labels[moves.index(move_str)][label] = True
2015-03-09 05:46:22 +00:00
return move_labels
def move_name(self, int move, int label):
if move == OUT:
return 'O'
elif move == 'MISSING':
return 'M'
else:
return MOVE_NAMES[move] + '-' + self.strings[label]
cdef int preprocess_gold(self, GoldParse gold) except -1:
for i in range(gold.length):
gold.c.ner[i] = self.lookup_transition(gold.ner[i])
# Count frequencies, for use in encoder
if gold.c.ner[i].move in (BEGIN, UNIT):
self.freqs[ENT_IOB][3] += 1
self.freqs[ENT_TYPE][gold.c.ner[i].label] += 1
elif gold.c.ner[i].move in (IN, LAST):
self.freqs[ENT_IOB][2] += 1
self.freqs[ENT_TYPE][0] += 1
elif gold.c.ner[i].move == OUT:
self.freqs[ENT_IOB][1] += 1
self.freqs[ENT_TYPE][0] += 1
else:
self.freqs[ENT_IOB][1] += 1
self.freqs[ENT_TYPE][0] += 1
cdef Transition lookup_transition(self, object name) except *:
if name == '-':
move_str = 'M'
label = 0
elif '-' in name:
move_str, label_str = name.split('-', 1)
label = self.strings[label_str]
else:
move_str = name
label = 0
move = MOVE_NAMES.index(move_str)
for i in range(self.n_moves):
if self.c[i].move == move and self.c[i].label == label:
return self.c[i]
else:
2015-04-15 23:36:22 +00:00
raise KeyError(name)
2015-03-09 05:46:22 +00:00
cdef Transition init_transition(self, int clas, int move, int label) except *:
# TODO: Apparent Cython bug here when we try to use the Transition()
# constructor with the function pointers
cdef Transition t
t.score = 0
t.clas = clas
t.move = move
t.label = label
if move == MISSING:
t.is_valid = Missing.is_valid
t.do = Missing.transition
t.get_cost = Missing.cost
elif move == BEGIN:
t.is_valid = Begin.is_valid
t.do = Begin.transition
t.get_cost = Begin.cost
elif move == IN:
t.is_valid = In.is_valid
t.do = In.transition
t.get_cost = In.cost
elif move == LAST:
t.is_valid = Last.is_valid
t.do = Last.transition
t.get_cost = Last.cost
elif move == UNIT:
t.is_valid = Unit.is_valid
t.do = Unit.transition
t.get_cost = Unit.cost
elif move == OUT:
t.is_valid = Out.is_valid
t.do = Out.transition
t.get_cost = Out.cost
else:
raise Exception(move)
2015-03-09 05:46:22 +00:00
return t
2015-06-01 21:05:25 +00:00
cdef class Missing:
@staticmethod
2015-06-10 05:09:17 +00:00
cdef bint is_valid(StateClass st, int label) nogil:
return False
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int transition(StateClass s, int label) nogil:
pass
2015-03-09 05:46:22 +00:00
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int cost(StateClass s, const GoldParseC* gold, int label) nogil:
2015-03-09 05:46:22 +00:00
return 9000
cdef class Begin:
@staticmethod
2015-06-10 05:09:17 +00:00
cdef bint is_valid(StateClass st, int label) nogil:
# Ensure we don't clobber preset entities. If no entity preset,
# ent_iob is 0
cdef int preset_ent_iob = st.B_(0).ent_iob
if preset_ent_iob == 1:
return False
elif preset_ent_iob == 2:
return False
elif preset_ent_iob == 3 and st.B_(0).ent_type != label:
return False
# If the next word is B or O, we can't B now
elif st.B_(1).ent_iob == 2 or st.B_(1).ent_iob == 3:
return False
# Don't allow entities to extend across sentence boundaries
elif st.B_(1).sent_start:
return False
else:
return label != 0 and not st.entity_is_open()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int transition(StateClass st, int label) nogil:
st.open_ent(label)
st.set_ent_tag(st.B(0), 3, label)
st.push()
st.pop()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int cost(StateClass s, const GoldParseC* gold, int label) nogil:
2015-06-10 04:57:41 +00:00
cdef int g_act = gold.ner[s.B(0)].move
cdef int g_tag = gold.ner[s.B(0)].label
2015-06-05 15:11:26 +00:00
if g_act == MISSING:
return 0
2015-06-05 21:48:43 +00:00
elif g_act == BEGIN:
2015-02-02 05:38:52 +00:00
# B, Gold B --> Label match
return label != g_tag
2015-02-02 05:38:52 +00:00
else:
# B, Gold I --> False (P)
# B, Gold L --> False (P)
# B, Gold O --> False (P)
# B, Gold U --> False (P)
return 1
cdef class In:
@staticmethod
2015-06-10 05:09:17 +00:00
cdef bint is_valid(StateClass st, int label) nogil:
cdef int preset_ent_iob = st.B_(0).ent_iob
if preset_ent_iob == 2:
return False
elif preset_ent_iob == 3:
return False
# TODO: Is this quite right?
# I think it's supposed to be ensuring the gazetteer matches are maintained
elif st.B_(1).ent_iob != preset_ent_iob:
return False
# Don't allow entities to extend across sentence boundaries
elif st.B_(1).sent_start:
return False
return st.entity_is_open() and label != 0 and st.E_(0).ent_type == label
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int transition(StateClass st, int label) nogil:
st.set_ent_tag(st.B(0), 1, label)
st.push()
st.pop()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int cost(StateClass s, const GoldParseC* gold, int label) nogil:
2015-06-05 15:11:26 +00:00
move = IN
2015-06-10 04:57:41 +00:00
cdef int next_act = gold.ner[s.B(1)].move if s.B(0) < s.length else OUT
cdef int g_act = gold.ner[s.B(0)].move
cdef int g_tag = gold.ner[s.B(0)].label
cdef bint is_sunk = _entity_is_sunk(s, gold.ner)
2015-06-05 15:11:26 +00:00
if g_act == MISSING:
return 0
elif g_act == BEGIN:
2015-02-02 05:38:52 +00:00
# I, Gold B --> True (P of bad open entity sunk, R of this entity sunk)
return 0
2015-02-02 05:38:52 +00:00
elif g_act == IN:
# I, Gold I --> True (label forced by prev, if mismatch, P and R both sunk)
return 0
2015-02-02 05:38:52 +00:00
elif g_act == LAST:
# I, Gold L --> True iff this entity sunk and next tag == O
return not (is_sunk and (next_act == OUT or next_act == MISSING))
2015-02-02 05:38:52 +00:00
elif g_act == OUT:
# I, Gold O --> True iff next tag == O
return not (next_act == OUT or next_act == MISSING)
2015-02-02 05:38:52 +00:00
elif g_act == UNIT:
# I, Gold U --> True iff next tag == O
return next_act != OUT
2015-06-05 15:11:26 +00:00
else:
return 1
cdef class Last:
@staticmethod
2015-06-10 05:09:17 +00:00
cdef bint is_valid(StateClass st, int label) nogil:
if st.B_(1).ent_iob == 1:
return False
return st.entity_is_open() and label != 0 and st.E_(0).ent_type == label
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int transition(StateClass st, int label) nogil:
st.close_ent()
st.set_ent_tag(st.B(0), 1, label)
st.push()
st.pop()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int cost(StateClass s, const GoldParseC* gold, int label) nogil:
2015-06-05 15:11:26 +00:00
move = LAST
2015-06-10 04:57:41 +00:00
cdef int g_act = gold.ner[s.B(0)].move
cdef int g_tag = gold.ner[s.B(0)].label
2015-06-05 15:11:26 +00:00
if g_act == MISSING:
return 0
elif g_act == BEGIN:
2015-02-02 05:38:52 +00:00
# L, Gold B --> True
return 0
2015-02-02 05:38:52 +00:00
elif g_act == IN:
# L, Gold I --> True iff this entity sunk
return not _entity_is_sunk(s, gold.ner)
2015-02-02 05:38:52 +00:00
elif g_act == LAST:
# L, Gold L --> True
return 0
2015-02-02 05:38:52 +00:00
elif g_act == OUT:
# L, Gold O --> True
return 0
2015-02-02 05:38:52 +00:00
elif g_act == UNIT:
# L, Gold U --> True
return 0
2015-06-05 15:11:26 +00:00
else:
return 1
cdef class Unit:
@staticmethod
2015-06-10 05:09:17 +00:00
cdef bint is_valid(StateClass st, int label) nogil:
cdef int preset_ent_iob = st.B_(0).ent_iob
if preset_ent_iob == 2:
return False
elif preset_ent_iob == 1:
return False
elif preset_ent_iob == 3 and st.B_(0).ent_type != label:
return False
elif st.B_(1).ent_iob == 1:
return False
return label != 0 and not st.entity_is_open()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int transition(StateClass st, int label) nogil:
st.open_ent(label)
st.close_ent()
st.set_ent_tag(st.B(0), 3, label)
st.push()
st.pop()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int cost(StateClass s, const GoldParseC* gold, int label) nogil:
2015-06-10 04:57:41 +00:00
cdef int g_act = gold.ner[s.B(0)].move
cdef int g_tag = gold.ner[s.B(0)].label
2015-06-05 15:11:26 +00:00
if g_act == MISSING:
return 0
elif g_act == UNIT:
2015-02-02 05:38:52 +00:00
# U, Gold U --> True iff tag match
return label != g_tag
2015-02-02 05:38:52 +00:00
else:
# U, Gold B --> False
# U, Gold I --> False
# U, Gold L --> False
# U, Gold O --> False
return 1
2015-02-02 05:38:52 +00:00
cdef class Out:
@staticmethod
2015-06-10 05:09:17 +00:00
cdef bint is_valid(StateClass st, int label) nogil:
cdef int preset_ent_iob = st.B_(0).ent_iob
if preset_ent_iob == 3:
return False
elif preset_ent_iob == 1:
return False
return not st.entity_is_open()
2015-02-02 05:38:52 +00:00
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int transition(StateClass st, int label) nogil:
st.set_ent_tag(st.B(0), 2, 0)
st.push()
st.pop()
@staticmethod
2015-06-10 05:09:17 +00:00
cdef int cost(StateClass s, const GoldParseC* gold, int label) nogil:
2015-06-10 04:57:41 +00:00
cdef int g_act = gold.ner[s.B(0)].move
cdef int g_tag = gold.ner[s.B(0)].label
2015-03-09 05:46:22 +00:00
2015-06-05 15:11:26 +00:00
if g_act == MISSING:
return 0
elif g_act == BEGIN:
# O, Gold B --> False
return 1
elif g_act == IN:
# O, Gold I --> True
return 0
elif g_act == LAST:
# O, Gold L --> True
return 0
elif g_act == OUT:
# O, Gold O --> True
return 0
elif g_act == UNIT:
# O, Gold U --> False
return 1
2015-06-05 15:11:26 +00:00
else:
return 1
2015-02-02 05:38:52 +00:00
class OracleError(Exception):
pass
class UnknownMove(Exception):
pass