def all_features(parse_dict, constituent, i, constituents):
syntax_tree = constituent.syntax_tree
conn_category = Connectives_dict().conn_category
connective = constituent.connective
''' feat dict '''
feat_dict_CON_Str = {}
feat_dict_CON_LStr = {}
feat_dict_NT_Ctx = {}
feat_dict_CON_NT_Path = {}
feat_dict_CON_NT_Path_iLsib = {}
''' load dict '''
dict_CON_Str = NT_dict().dict_CON_Str
dict_CON_LStr = NT_dict().dict_CON_LStr
dict_NT_Ctx = NT_dict().dict_NT_Ctx
dict_CON_NT_Path = NT_dict().dict_CON_NT_Path
dict_CON_NT_Path_iLsib = NT_dict().dict_CON_NT_Path_iLsib
''' feature '''
conn_indices = connective.token_indices
DocID = connective.DocID
sent_index = connective.sent_index
conn_node = dict_util.get_conn_node(syntax_tree, conn_indices)
CON_Str = dict_util.get_CON_Str(parse_dict, DocID, sent_index,
conn_indices)
CON_LStr = CON_Str.lower()
CON_Cat = conn_category[connective.name]
CON_iLSib = dict_util.get_CON_iLSib(syntax_tree, conn_node)
CON_iRSib = dict_util.get_CON_iRSib(syntax_tree, conn_node)
NT_Ctx = dict_util.get_NT_Ctx(constituent)
CON_NT_Path = dict_util.get_CON_NT_Path(conn_node, constituent)
CON_NT_Position = dict_util.get_CON_NT_Position(conn_node, constituent)
if CON_iLSib > 1:
CON_NT_Path_iLsib = CON_NT_Path + ":>1"
else:
CON_NT_Path_iLsib = CON_NT_Path + ":<=1"
features = []
features.append(get_feature(feat_dict_CON_Str, dict_CON_Str, CON_Str))
features.append(get_feature(feat_dict_CON_LStr, dict_CON_LStr, CON_LStr))
features.append(get_feature(feat_dict_NT_Ctx, dict_NT_Ctx, NT_Ctx))
features.append(
get_feature(feat_dict_CON_NT_Path, dict_CON_NT_Path, CON_NT_Path))
features.append(
get_feature(feat_dict_CON_NT_Path_iLsib, dict_CON_NT_Path_iLsib,
CON_NT_Path_iLsib))
# cat
dict_category = {"subordinator": 1, "coordinator": 2, "adverbial": 3}
features.append(get_feature({}, dict_category, CON_Cat))
#number
features.append(Feature("", 1, {1: CON_iLSib}))
features.append(Feature("", 1, {1: CON_iRSib}))
#position
dict_position = {"right": 1, "left": 2}
features.append(get_feature({}, dict_position, CON_NT_Position))
return util.mergeFeatures(features)
def NT_parent_linked_ctx(parse_dict, constituent, i, constituents):
# load dict
dict_NT_parent_linked_ctx = NT_dict().dict_NT_parent_linked_ctx
# feature
NT_parent_linked_ctx = dict_util.get_NT_parent_linked_ctx(constituent)
return get_feature_by_feat(dict_NT_parent_linked_ctx, NT_parent_linked_ctx)
def NT_to_root_path(parse_dict, constituent, i, constituents):
# load dict
dict_NT_to_root_path = NT_dict().dict_NT_to_root_path
# feature
NT_to_root_path = dict_util.get_NT_to_root_path(constituent)
return get_feature_by_feat(dict_NT_to_root_path, NT_to_root_path)
def NT_prev_curr_Path(parse_dict, constituent, i, constituents):
# load dict
dict_NT_prev_curr_Path = NT_dict().dict_NT_prev_curr_Path
# feature
NT_prev_curr_Path = dict_util.get_NT_prev_curr_Path(i, constituents)
return get_feature_by_feat(dict_NT_prev_curr_Path, NT_prev_curr_Path)
def CON_NT_Path(parse_dict, constituent, i, constituents):
# load dict
dict_CON_NT_Path = NT_dict().dict_CON_NT_Path
# feature
syntax_tree = constituent.syntax_tree
connective = constituent.connective
conn_indices = connective.token_indices
conn_node = dict_util.get_conn_node(syntax_tree, conn_indices)
CON_NT_Path = dict_util.get_CON_NT_Path(conn_node, constituent)
return get_feature_by_feat(dict_CON_NT_Path, CON_NT_Path)
def CON_Str(parse_dict, constituent, i, constituents):
# load dict
dict_CON_Str = NT_dict().dict_CON_Str
# feature
connective = constituent.connective
DocID = connective.DocID
sent_index = connective.sent_index
conn_indices = connective.token_indices
CON_Str = dict_util.get_CON_Str(parse_dict, DocID, sent_index,
conn_indices)
return get_feature_by_feat(dict_CON_Str, CON_Str)
def parent_category(parse_dict, constituent, i, constituents):
# load dict
dict_parent_category = NT_dict().dict_parent_category
# feature
connective = constituent.connective
DocID = connective.DocID
sent_index = connective.sent_index
conn_indices = connective.token_indices
parent_category = dict_util.get_parent_category(parse_dict, DocID,
sent_index, conn_indices)
return get_feature_by_feat(dict_parent_category, parent_category)
def conn_rightSiblingCtx(parse_dict, constituent, i, constituents):
# load dict
dict_conn_rightSiblingCtx = NT_dict().dict_conn_rightSiblingCtx
# feature
connective = constituent.connective
DocID = connective.DocID
sent_index = connective.sent_index
conn_indices = connective.token_indices
conn_rightSiblingCtx = dict_util.get_conn_rightSiblingCtx(
parse_dict, DocID, sent_index, conn_indices)
return get_feature_by_feat(dict_conn_rightSiblingCtx, conn_rightSiblingCtx)
def CParent_to_root_path(parse_dict, constituent, i, constituents):
# load dict
dict_CParent_to_root_path = NT_dict().dict_CParent_to_root_path
# feature
connective = constituent.connective
DocID = connective.DocID
sent_index = connective.sent_index
conn_indices = connective.token_indices
CParent_to_root_path = dict_util.get_CParent_to_root_path(
parse_dict, DocID, sent_index, conn_indices)
return get_feature_by_feat(dict_CParent_to_root_path, CParent_to_root_path)
def CON_NT_Path_iLsib(parse_dict, constituent, i, constituents):
# load dict
dict_CON_NT_Path_iLsib = NT_dict().dict_CON_NT_Path_iLsib
# feature
syntax_tree = constituent.syntax_tree
connective = constituent.connective
conn_indices = connective.token_indices
conn_node = dict_util.get_conn_node(syntax_tree, conn_indices)
CON_NT_Path = dict_util.get_CON_NT_Path(conn_node, constituent)
CON_iLSib = dict_util.get_CON_iLSib(syntax_tree, conn_node)
if CON_iLSib > 1:
CON_NT_Path_iLsib = CON_NT_Path + ":>1"
else:
CON_NT_Path_iLsib = CON_NT_Path + ":<=1"
return get_feature_by_feat(dict_CON_NT_Path_iLsib, CON_NT_Path_iLsib)