explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-03-12 15:25:47 +03:00
Code Issues Packages Projects Releases Wiki Activity

Use get_aligned_parse in ArcEager

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-21 17:17:34 +02:00
parent 87f5348e17
commit ecf192aa70
1 changed files with 17 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
spacy/syntax/arc_eager.pyx
View File

@ -75,31 +75,20 @@ cdef GoldParseStateC create_gold_state(Pool mem, StateClass stcls, Example examp
gs.n_kids_in_buffer = <int32_t*>mem.alloc(gs.length, sizeof(gs.n_kids_in_buffer[0])) gs.n_kids_in_buffer = <int32_t*>mem.alloc(gs.length, sizeof(gs.n_kids_in_buffer[0]))
gs.n_kids_in_stack = <int32_t*>mem.alloc(gs.length, sizeof(gs.n_kids_in_stack[0])) gs.n_kids_in_stack = <int32_t*>mem.alloc(gs.length, sizeof(gs.n_kids_in_stack[0]))
cand_to_gold = example.alignment.cand_to_gold heads, labels = example.get_aligned_parse(projectivize=True)
gold_to_cand = example.alignment.cand_to_gold
cdef TokenC ref_tok cdef TokenC ref_tok
for cand_i in range(example.x.length): for i, (head, label) in enumerate(zip(heads, labels)):
gold_i = cand_to_gold[cand_i] if head is not None:
if gold_i is not None: # Alignment found gs.heads[i] = head
ref_tok = example.y.c[gold_i] gs.labels[i] = example.x.vocab.strings.add(label)
gold_head = gold_to_cand[gold_i + ref_tok.head] gs.state_bits[i] = set_state_flag(
if gold_head is not None: gs.state_bits[i],
gs.heads[cand_i] = gold_head
gs.labels[cand_i] = ref_tok.dep
gs.state_bits[cand_i] = set_state_flag(
gs.state_bits[cand_i],
HEAD_UNKNOWN, HEAD_UNKNOWN,
0 0
) )
else: else:
gs.state_bits[cand_i] = set_state_flag( gs.state_bits[i] = set_state_flag(
gs.state_bits[cand_i], gs.state_bits[i],
HEAD_UNKNOWN,
1
)
else:
gs.state_bits[cand_i] = set_state_flag(
gs.state_bits[cand_i],
HEAD_UNKNOWN, HEAD_UNKNOWN,
1 1
) )
@ -529,10 +518,11 @@ cdef class ArcEager(TransitionSystem):
for label in kwargs.get('right_labels', []): for label in kwargs.get('right_labels', []):
actions[RIGHT][label] = 1 actions[RIGHT][label] = 1
actions[REDUCE][label] = 1 actions[REDUCE][label] = 1
for example in kwargs.get('gold_parses', []): for example in kwargs.get('examples', []):
heads, labels = nonproj.projectivize(example.get_aligned("HEAD"), heads, labels = example.get_aligned_parse(projectivize=True)
example.get_aligned("DEP")) for child, (head, label) in enumerate(zip(heads, labels)):
for child, head, label in zip(example.get_aligned("ID"), heads, labels): if head is None or label is None:
continue
if label.upper() == 'ROOT' : if label.upper() == 'ROOT' :
label = 'ROOT' label = 'ROOT'
if head == child: if head == child: