class EnglishUralicNLPMorphologicalRealizer(LanguageSpecificMorphologicalRealizer):
def __init__(self):
super().__init__("fi")
self.case_map: Dict[str, str] = {"genitive": "GEN"}
def realize(self, slot: Slot) -> str:
case: Optional[str] = slot.attributes.get("case")
if case is None:
return slot.value
log.debug("Realizing {} to Finnish")
case = self.case_map.get(case.lower(), case.upper())
log.debug("Normalized case {} to {}".format(slot.attributes.get("case"), case))
possible_analyses = uralicApi.analyze(slot.value, "eng")
log.debug("Identified {} possible analyses".format(len(possible_analyses)))
if len(possible_analyses) == 0:
log.warning(
"No valid morphological analysis for {}, unable to realize despite case attribute".format(slot.value)
)
return slot.value
analysis = possible_analyses[0][0]
log.debug("Picked {} as the morphological analysis of {}".format(analysis, slot.value))
analysis = "{}+{}".format(analysis, case)
log.debug("Modified analysis to {}".format(analysis))
modified_value = uralicApi.generate(analysis, "eng")[0][0]
log.debug("Realized value is {}".format(modified_value))
return modified_value
async def generate(ctx, arg):
response = []
lines = uralicApi.generate(arg, "fin")
if len(lines) > 0:
for line in lines:
response.append(line[0])
response = ('\n'.join(response))
await ctx.send(response)
else:
await ctx.send('generation not possible')
def create_first_verse(verb_candidates, probability_distribution, lemmas,
verse):
''' Picks a verb from the candidates and then creates and outputs the first verse of the stanza '''
draw = choice(verb_candidates, 1, p=probability_distribution)
verb = uralicApi.generate(draw[0] + "+V+Act+Ind+Prs+Sg3", "fin")[0][0]
verse = " ".join(verse)
# print('verse: ' + verse)
# verse += " " + verb
verse = verse.replace(
verse.split(" ")[0],
verse.split(" ")[0] + " " + verb + " ")
return fix_syllables(verse, False)
class FinnishUralicNLPMorphologicalRealizer(
LanguageSpecificMorphologicalRealizer):
def __init__(self):
super().__init__("fi")
self.case_map: Dict[str, str] = {
"ssa": "Ine",
"ssä": "Ine",
"inessive": "Ine",
"genitive": "Gen"
}
def realize(self, slot: Slot) -> str:
case: Optional[str] = slot.attributes.get("case")
if case is None:
return slot.value
log.debug("Realizing {} to Finnish")
case = self.case_map.get(case.lower(), case.capitalize())
log.debug("Normalized case {} to {}".format(
slot.attributes.get("case"), case))
possible_analyses = uralicApi.analyze(slot.value, "fin")
log.debug("Identified {} possible analyses".format(
len(possible_analyses)))
if len(possible_analyses) == 0:
log.warning(
"No valid morphological analysis for {}, unable to realize despite case attribute"
.format(slot.value))
return slot.value
analysis = possible_analyses[0][0]
log.debug("Picked {} as the morphological analysis of {}".format(
analysis, slot.value))
# We only want to replace the last occurence of "Nom", as otherwise all parts of compound words, rather than
# only the last, get transformed to genitive. This is simply wrong for, e.g. "tyvipari". Simply doing a global
# replacement results in *"tyvenparin", rather than "tyviparin". Unfortunately, python lacks a replace() which
# starts from the right, so we need to identify the correct instance of "Nom" with rfind() and then manually
# fiddle with slices.
gen_start_idx = analysis.rfind("Nom")
analysis = analysis[:gen_start_idx] + "Gen" + analysis[
gen_start_idx + 4:] # 4 = 1 + len("Nom")
log.debug("Modified analysis to {}".format(analysis))
modified_value = uralicApi.generate(analysis, "fin")[0][0]
log.debug("Realized value is {}".format(modified_value))
return modified_value
def test_generate(self):
result = uralicApi.generate("äkkipikainen+A+Sg+Gen",
"fin",
force_local=True)
self.assertEqual(result[0][0], 'äkkipikaisen')
def dictionary_entry(grouped_relation):
'''
:param grouped_relation: Lexeme ID with all Relation objects linked to it
:return: A latex string to represent the relation as an entry in the dictionary
'''
lexeme_from_id, relations = grouped_relation
relations = list(relations)
lexeme_from = relations[0].lexeme_from
dictionary_entry_text = []
entry_content = (
lexeme_from.lexeme,
lexeme_from.pos,
lexeme_from.specification,
)
entry_content = tuple([tex_escape(c) for c in entry_content])
dictionary_entry_text.append("\entry{%s}{%s}{%s}" % entry_content)
inflection_table = {
'V': [
'V+Ind+Prs+ConNeg', 'V+Ind+Prs+Sg3', 'V+Ind+Prt+Sg1',
'V+Ind+Prt+Sg3'
],
'N': ['N+Sg+Loc', 'N+Sg+Ill', 'N+Pl+Gen'],
'A': ['A+Attr'],
'Prop': [
'N+Prop+Sg+Loc', 'N+Prop+Sem/Mal+Sg+Loc', 'N+Prop+Sem/Fem+Sg+Loc',
'N+Prop+Sem/Plc+Sg+Loc'
]
}
contelex_inflexType_cases = {
'V': {
r'(YD,1)': ['V+Ind+Prs+Sg1', 'V+Ind+Prs+Sg3'],
r'(AD,1)': ['V+Ind+Prs+Sg1', 'V+Ind+Prt+Sg1'],
r'(ED,1)': ['V+Ind+Prs+Sg1', 'V+Ind+Prt+Sg1', 'V+Ind+Prt+Sg3'],
r'(,[2-4])': ['V+Ind+Prs+ConNeg']
},
'N': {
r'(Q[^,\n]*)(,1)': ['N+Sg+Loc', 'N+Sg+Ill', 'N+Pl+Gen'],
r'(_[^Q,\n]*)(,1)': ['N+Sg+Loc', 'N+Sg+Ill'],
r'(,3|[^D],2|ID,2)': ['N+Sg+Gen', 'N+Sg+IllN+Sg+Gen', 'N+Sg+Ill'],
r'(,4|[YAE]D,2)': ['N+Sg+Loc', 'N+Sg+Ill'],
}
}
translation_lemma_map = {
'V': '+Inf',
'N': '+N+Sg+Nom',
'A': '+Sg+Nom',
'Adv': ''
}
relations = list(
sorted(relations,
key=lambda r: (
r.relationmetadata_set.all().count() != 0,
r.lexeme_to.lexeme_lang,
)))
for r in relations:
translation = r.lexeme_to
translation_text = translation.lexeme
pos = '' if translation.pos == lexeme_from.pos else translation.pos
if translation.pos in translation_lemma_map:
result = uralicApi.generate(
translation.lexeme + '+' + 'Hom{}+'.format(translation.homoId)
if translation.homoId > 0 else '' + translation.pos +
translation_lemma_map[translation.pos],
translation.language,
dictionary_forms=True)
if result:
translation_text = result[0][0]
# LaTeX escape the content
inflections = []
MP_forms = translation.miniparadigm_set.all()
existing_MP_forms = defaultdict(list)
for form in MP_forms:
existing_MP_forms[form.msd].append(form.wordform)
if translation.id not in nti_ids: # ignore certain translations
# custom transducer
generated_MP_forms = defaultdict(list)
if synthetiser:
try:
queries, _ = _inflector.__generator_queries__(
translation.lexeme, translation.pos)
for i in range(len(queries)):
MP_form = '+'.join(queries[i].split('+')[1:])
try:
generated_MP_forms[MP_form].append(
synthetiser.lookup(
queries[i])[0][0].split("@")[0])
except:
raise
except: # POS is empty or no queries
pass
else: # default (uralicNLP)
generated_MP_forms = _inflector.generate_uralicNLP(
translation.language,
translation.lexeme,
translation.pos,
dictionary_forms=True)
if translation.pos in inflection_table:
inflection_forms = inflection_table[
translation.pos] # default inflections
# specific inflections based on contlex
if translation.contlex and translation.pos in contelex_inflexType_cases:
for re_pattern, _inflections in contelex_inflexType_cases[
translation.pos].items():
if re.search(
re_pattern,
"{},{}".format(translation.contlex,
translation.inflexType_str())):
inflection_forms = _inflections
break
for inflection_form in inflection_forms:
generated_form = None
if inflection_form in existing_MP_forms:
generated_form = existing_MP_forms[inflection_form]
elif inflection_form in generated_MP_forms:
generated_form = generated_MP_forms[inflection_form]
if generated_form:
if inflection_form == 'A+Attr':
generated_form = [
"#{}".format(gf) for gf in generated_form
]
elif inflection_form == 'V+Ind+Prs+ConNeg':
generated_form[0] = "ij {}".format(
generated_form[0])
inflections.extend(generated_form)
if not inflections and translation.pos == 'N' and re.match(
r'[A-Z](.+)', translation.lexeme):
for inflection_form in inflection_table['Prop']:
generated_results = uralicApi.generate(
"{}+{}".format(translation.lexeme, inflection_form),
translation.language)
generated_form = [
gr[0].split('@')[0] for gr in generated_results
]
if generated_form:
inflections.extend(generated_form)
break
source_specification = r.relationmetadata_set.values_list('text', flat=True) \
.filter(type=SPECIFICATION, language=lexeme_from.language) \
.order_by('text').all()
target_specification = r.relationmetadata_set.values_list('text', flat=True) \
.filter(type=SPECIFICATION, language=translation.language) \
.order_by('text').all()
source_example = r.relationexample_set.values_list('text', flat=True) \
.filter(language=lexeme_from.language).order_by('text').all()
target_example = r.relationexample_set.values_list('text', flat=True) \
.filter(language=translation.language).order_by('text').all()
content = (translation_text, translation.specification, pos,
", ".join(inflections), ", ".join(source_specification),
", ".join(target_specification), ", ".join(source_example),
", ".join(target_example), "")
content = tuple([tex_escape(c) for c in content])
dictionary_entry_text.append(
"\\translation{%s}{%s}{%s}{%s}{%s}{%s}{%s}{%s}{%s}" % content)
return "\n".join(dictionary_entry_text)
def create_verb_probabilities(usr_input):
''' Uses the first input noun to find a verbs that are semantically similar. Outputs verb candidates and their probability distribution. '''
lemmas = tokenize_and_lemmatize(usr_input)
input_posses = get_pos_template(lemmas)
# print("Input POSes: " + input_posses + "\n")
# If both input words are noun. Other alternatives are not implemented.
if input_posses == 'NN':
lemma_dict = {'subject': lemmas[0], 'object': lemmas[1]}
verse = []
# Loop through both lemmas and inflect them depending on their syntactic role
for lemma in lemmas:
# print_some_input_info(lemma) # FOR DEBUGGING
for analysis in uralicApi.analyze(lemma, "fin"):
ms_desc = analysis[0].lstrip(analysis[0].split('+')[0])
# print("Analysis of the lemma: " + lemma + ms_desc + "\n") # FOR DEBUGGING
if ms_desc[1] == 'N':
if lemma == lemma_dict['subject']:
generated = uralicApi.generate(lemma + "+N+Sg+Nom",
"fin")
if lemma == lemma_dict['object']:
generated = uralicApi.generate(lemma + "+N+Sg+Gen",
"fin")
if len(generated) > 0:
verse.append(generated[0][0])
else:
print("Try with other words.")
# If the lemma is subject, choose a verb using its word relations. There's probably a better alternative for this.
if lemma == lemma_dict['subject']:
word = semfi.get_word(lemma, "N", "fin")
while True:
try:
relations = semfi.get_by_relation(word,
"dobj",
"fin",
sort=True)
break
except Exception as e:
print(
"At least one of the input words was not recognized, try with other words.\n\n"
+ e)
exit()
verbs_and_probs = []
for relation in relations:
try:
if relation['word2']['pos'] == 'V':
inflected_form = uralicApi.generate(
relation['word2']['word'] +
"+V+Act+Ind+Prs+Sg3", "fin")[0][0]
first_syllable = finmeter.hyphenate(
inflected_form).split("-")[0]
if count_syllables(
inflected_form
) == 2 and not finmeter.is_short_syllable(
first_syllable):
verbs_and_probs.append(
(relation['word2']['word'],
relation['word2']['frequency']))
except:
pass
# Sort the verb by frequency (descending order) and get rid of the top 5% frequent and the half that is least frequent
verbs_and_probs = sorted(
verbs_and_probs, key=lambda x: x[-1], reverse=True)[round((
(len(verbs_and_probs) / 100) *
5)):round(((len(verbs_and_probs) / 100) * 50))]
if len(verbs_and_probs) == 0:
print("Try with other words.")
exit()
else:
# Normalize the probabilities and choose the verb randomly
verb_candidates, probability_distribution = map(
list, zip(*verbs_and_probs))
probability_distribution = np.array(
np.array(probability_distribution) /
sum(probability_distribution))
return verb_candidates, probability_distribution, lemmas, lemma_dict, verse
else:
pos = "A"
if "CASE" not in args:
args["CASE"] = "NOM"
else:
args["CASE"] = args["CASE"].upper()
if "DEGREE" in args:
degree = "+" + args["DEGREE"]
possessive = ""
if "POSS" in args:
possessive = "+" + args["POSS"]
#omorfi_query = "[WORD_ID="+word+"][POS="+pos+"][NUM="+args["NUM"]+"][CASE="+args["CASE"]+"]"
omorfi_query = word + "+" + pos + degree + "+" + args["NUM"].title(
) + "+" + args["CASE"].title() + possessive + c**t
word_form = _filter_generated(uralicApi.generate(omorfi_query, "fin"),
word)
if len(word_form) == 0:
#Generation failed!
if pos == "N":
return inflect(beginning + "|" + word, "N+Prop", args)
else:
return beginning + backup_inflect(word, pos, args)
else:
return beginning + word_form[0][0]
def _filter_generated(res, lemma):
if len(res) < 2:
return res
for r in res: