def sent_rm_pos(sent):
finnpos_analys = get_finnpos_analys(sent)
anns = sent.xpath("./annotations/annotation")
new_anns = anns.copy()
for ann in anns:
tok, tok_len = get_ann_pos(ann)
if tok_len != 1:
continue
props = finnpos_analys[tok][1]
if any((match(props) for match in to_remove)):
new_anns.remove(ann)
trim_anns(anns, new_anns)
def sent_span_dom(sent):
anns = sent.xpath("./annotations/annotation")
token_positions = {}
for ann in anns:
if sup_only and not HasSupportTournament.rank(ann):
continue
tok, tok_len = get_ann_pos(ann)
token_positions.setdefault(tok, []).append((tok_len, ann))
new_anns = greedy_max_span(token_positions)
if sup_only:
for ann in anns:
if not HasSupportTournament.rank(ann):
new_anns.append(ann)
trim_anns(anns, new_anns)
def sent_rm_ambg(sent):
anns = sent.xpath("./annotations/annotation")
new_anns = anns.copy()
span_counts = {}
for ann in anns:
span = get_ann_pos(ann)
if span not in span_counts:
span_counts[span] = 0
span_counts[span] += 1
for ann in anns:
span = get_ann_pos(ann)
if span_counts[span] >= 2:
new_anns.remove(ann)
trim_anns(anns, new_anns)
def sent_span_dom(sent):
anns = sent.xpath("./annotations/annotation")
starts = []
for ann in anns:
anchor_pos = get_ann_pos_dict(ann)
anchor = ann.attrib["anchor"]
starts.append(int(anchor_pos["char"]))
starts.sort()
char_positions = {}
for ann in anns:
anchor_pos = get_ann_pos_dict(ann)
anchor = ann.attrib["anchor"]
cur_start = int(anchor_pos["char"])
cur_start_idx = starts.index(cur_start)
anchor_len = len(anchor)
span = 0
while (cur_start_idx + span < len(starts)
and starts[cur_start_idx + span] <= cur_start + anchor_len):
span += 1
char_positions.setdefault(cur_start, []).append((span, ann))
new_anns = greedy_max_span(char_positions)
trim_anns(anns, new_anns)