def test_rcs_tcc_ceaf():
"Examples from Luo (2005)"
for system, response, expected in RCS14_TCM_RESPS:
actual = dict(_get_coref_fscore(RCS14_TCM_GOLD, response,
LUO_MEASURES))
check_correct(expected, actual)
def test_luo_ceaf():
"Examples from Luo (2005)"
for system, response, expected in LUO05_RESPS:
actual = dict(_get_coref_fscore(LUO05_GOLD, response, LUO_MEASURES))
check_correct(expected, actual)
def test_rcs_tca_ceaf():
"Examples from Luo (2005)"
for system, response, expected in RCS14_TCA_RESPS:
actual = dict(_get_coref_fscore(RCS14_TCA_GOLD, response, LUO_MEASURES))
check_correct(expected, actual)
def test_luo_ceaf():
"Examples from Luo (2005)"
for system, response, expected in LUO05_RESPS:
actual = dict(_get_coref_fscore(LUO05_GOLD, response, LUO_MEASURES))
check_correct(expected, actual)
def test_conll_multi_sysa():
assert check_correct(
EXPECTED_CONLL_MULTI_SYSA,
_get_stats(CONLL_MULTI_GOLD_UNSTITCHED, CONLL_MULTI_SYSA_UNSTITCHED))
def test_conll_multi_selfeval():
assert check_correct(
EXPECTED_CONLL_MULTI_SELFEVAL,
_get_stats(CONLL_MULTI_GOLD_UNSTITCHED, CONLL_MULTI_GOLD_UNSTITCHED))
def test_tac_eval():
check_correct(EXPECTED_TAC_SYS, _get_stats(TAC_GOLD_COMB, TAC_SYS_COMB))