def find_tags(self, tokens, **kwargs):
if kwargs.get("tagset") in (PENN, None):
kwargs.setdefault("map", lambda token, tag: stts2penntreebank(token, tag))
if kwargs.get("tagset") == UNIVERSAL:
kwargs.setdefault("map", lambda token, tag: stts2universal(token, tag))
if kwargs.get("tagset") is STTS:
kwargs.setdefault("map", lambda token,tag: (token, tag))
# The lexicon uses Swiss spelling: "ss" instead of "ß".
# We restore the "ß" after parsing.
tokens_ss = [t.replace(u"ß", "ss") for t in tokens]
tokens_ss = _Parser.find_tags(self, tokens_ss, **kwargs)
return [[w] + tokens_ss[i][1:] for i, w in enumerate(tokens)]
def find_tags(self, tokens, **kwargs):
if kwargs.get("tagset") in (PENN, None):
kwargs.setdefault("map",
lambda token, tag: stts2penntreebank(token, tag))
if kwargs.get("tagset") == UNIVERSAL:
kwargs.setdefault("map",
lambda token, tag: stts2universal(token, tag))
if kwargs.get("tagset") is STTS:
kwargs.setdefault("map", lambda token, tag: (token, tag))
# The lexicon uses Swiss spelling: "ss" instead of "ß".
# We restore the "ß" after parsing.
tokens_ss = [t.replace(u"ß", "ss") for t in tokens]
tokens_ss = _Parser.find_tags(self, tokens_ss, **kwargs)
return [[w] + tokens_ss[i][1:] for i, w in enumerate(tokens)]
def find_tokens(self, tokens, **kwargs):
kwargs.setdefault("abbreviations", ABBREVIATIONS)
kwargs.setdefault("replace", {})
return _Parser.find_tokens(self, tokens, **kwargs)
def find_tokens(self, tokens, **kwargs):
kwargs.setdefault("abbreviations", ABBREVIATIONS)
kwargs.setdefault("replace", {})
return _Parser.find_tokens(self, tokens, **kwargs)