ACE //nn_u_unknown

Hi,

While parsing with ACE for some Sentences we get “unknown” on some words.
for exemple in this sentence : “The spacecraft consists of two main elements: the NASA Cassini Orbiter, named after the Italian-French astronomer Giovanni Domenico Cassini, and the ESA Huygens probe, named after the Dutch astronomer, mathematician and physicist Christiaan Huygens.”

the world “astronomer” the first time is recognized but i get “unknown” on the second one.
any idea on what’s generating this problem.

{
“nodes”: [
{
“nodeid”: 10000,
“predicate”: “_the_q”,
“lnk”: {
“from”: 0,
“to”: 3
}
},
{
“nodeid”: 10001,
“predicate”: “_spacecraft_n_1”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“lnk”: {
“from”: 4,
“to”: 14
}
},
{
“nodeid”: 10002,
“predicate”: “_consist_v_of”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “pres”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 15,
“to”: 23
}
},
{
“nodeid”: 10003,
“predicate”: “udef_q”,
“lnk”: {
“from”: 27,
“to”: 30
}
},
{
“nodeid”: 10004,
“predicate”: “card”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“carg”: “2”,
“lnk”: {
“from”: 27,
“to”: 30
}
},
{
“nodeid”: 10005,
“predicate”: “_main_a_1”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 31,
“to”: 35
}
},
{
“nodeid”: 10006,
“predicate”: “_element_n_1”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “pl”,
“IND”: “+”,
“cvarsort”: “x”
},
“lnk”: {
“from”: 36,
“to”: 44
}
},
{
“nodeid”: 10007,
“predicate”: “_colon_p_namely”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 44,
“to”: 45
}
},
{
“nodeid”: 10008,
“predicate”: “udef_q”,
“lnk”: {
“from”: 46,
“to”: 249
}
},
{
“nodeid”: 10009,
“predicate”: “_the_q”,
“lnk”: {
“from”: 46,
“to”: 49
}
},
{
“nodeid”: 10010,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 50,
“to”: 71
}
},
{
“nodeid”: 10011,
“predicate”: “proper_q”,
“lnk”: {
“from”: 50,
“to”: 62
}
},
{
“nodeid”: 10012,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 50,
“to”: 62
}
},
{
“nodeid”: 10013,
“predicate”: “proper_q”,
“lnk”: {
“from”: 50,
“to”: 54
}
},
{
“nodeid”: 10014,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “NASA”,
“lnk”: {
“from”: 50,
“to”: 54
}
},
{
“nodeid”: 10015,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Cassini”,
“lnk”: {
“from”: 55,
“to”: 62
}
},
{
“nodeid”: 10016,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Orbiter”,
“lnk”: {
“from”: 63,
“to”: 71
}
},
{
“nodeid”: 10017,
“predicate”: “_name_v_1”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 72,
“to”: 77
}
},
{
“nodeid”: 10018,
“predicate”: “parg_d”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 72,
“to”: 77
}
},
{
“nodeid”: 10019,
“predicate”: “_after_p”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 78,
“to”: 83
}
},
{
“nodeid”: 10020,
“predicate”: “appos”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 84,
“to”: 140
}
},
{
“nodeid”: 10021,
“predicate”: “_the_q”,
“lnk”: {
“from”: 84,
“to”: 87
}
},
{
“nodeid”: 10022,
“predicate”: “_italian_a_1”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 88,
“to”: 102
}
},
{
“nodeid”: 10023,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “French”,
“lnk”: {
“from”: 88,
“to”: 102
}
},
{
“nodeid”: 10024,
“predicate”: “proper_q”,
“lnk”: {
“from”: 103,
“to”: 140
}
},
{
“nodeid”: 10025,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 103,
“to”: 140
}
},
{
“nodeid”: 10026,
“predicate”: “proper_q”,
“lnk”: {
“from”: 103,
“to”: 131
}
},
{
“nodeid”: 10027,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 103,
“to”: 131
}
},
{
“nodeid”: 10028,
“predicate”: “proper_q”,
“lnk”: {
“from”: 103,
“to”: 122
}
},
{
“nodeid”: 10029,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 103,
“to”: 122
}
},
{
“nodeid”: 10030,
“predicate”: “proper_q”,
“lnk”: {
“from”: 103,
“to”: 113
}
},
{
“nodeid”: 10031,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “astronomer”,
“lnk”: {
“from”: 103,
“to”: 113
}
},
{
“nodeid”: 10032,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Giovanni”,
“lnk”: {
“from”: 114,
“to”: 122
}
},
{
“nodeid”: 10033,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Domenico”,
“lnk”: {
“from”: 123,
“to”: 131
}
},
{
“nodeid”: 10034,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Cassini”,
“lnk”: {
“from”: 132,
“to”: 140
}
},
{
“nodeid”: 10035,
“predicate”: “_and_c”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “pl”,
“cvarsort”: “x”
},
“lnk”: {
“from”: 141,
“to”: 144
}
},
{
“nodeid”: 10036,
“predicate”: “_the_q”,
“lnk”: {
“from”: 145,
“to”: 148
}
},
{
“nodeid”: 10037,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 149,
“to”: 167
}
},
{
“nodeid”: 10038,
“predicate”: “proper_q”,
“lnk”: {
“from”: 149,
“to”: 160
}
},
{
“nodeid”: 10039,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 149,
“to”: 160
}
},
{
“nodeid”: 10040,
“predicate”: “proper_q”,
“lnk”: {
“from”: 149,
“to”: 152
}
},
{
“nodeid”: 10041,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “ESA”,
“lnk”: {
“from”: 149,
“to”: 152
}
},
{
“nodeid”: 10042,
“predicate”: “named”,
“sortinfo”: {
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Huygens”,
“lnk”: {
“from”: 153,
“to”: 160
}
},
{
“nodeid”: 10043,
“predicate”: “_probe_n_1”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“lnk”: {
“from”: 161,
“to”: 167
}
},
{
“nodeid”: 10044,
“predicate”: “_name_v_1”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 168,
“to”: 173
}
},
{
“nodeid”: 10045,
“predicate”: “parg_d”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 168,
“to”: 173
}
},
{
“nodeid”: 10046,
“predicate”: “_after_p”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 174,
“to”: 179
}
},
{
“nodeid”: 10047,
“predicate”: “appos”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 180,
“to”: 249
}
},
{
“nodeid”: 10048,
“predicate”: “_the_q”,
“lnk”: {
“from”: 180,
“to”: 183
}
},
{
“nodeid”: 10049,
“predicate”: “_dutch_a_1”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 184,
“to”: 189
}
},
{
“nodeid”: 10050,
“predicate”: “_astronomer/nn_u_unknown”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“cvarsort”: “x”
},
“lnk”: {
“from”: 190,
“to”: 201
}
},
{
“nodeid”: 10051,
“predicate”: “udef_q”,
“lnk”: {
“from”: 202,
“to”: 249
}
},
{
“nodeid”: 10052,
“predicate”: “proper_q”,
“lnk”: {
“from”: 202,
“to”: 215
}
},
{
“nodeid”: 10053,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “mathematician”,
“lnk”: {
“from”: 202,
“to”: 215
}
},
{
“nodeid”: 10054,
“predicate”: “_and_c”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “pl”,
“cvarsort”: “x”
},
“lnk”: {
“from”: 216,
“to”: 219
}
},
{
“nodeid”: 10055,
“predicate”: “proper_q”,
“lnk”: {
“from”: 220,
“to”: 249
}
},
{
“nodeid”: 10056,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 220,
“to”: 249
}
},
{
“nodeid”: 10057,
“predicate”: “proper_q”,
“lnk”: {
“from”: 220,
“to”: 240
}
},
{
“nodeid”: 10058,
“predicate”: “compound”,
“sortinfo”: {
“SF”: “prop”,
“TENSE”: “untensed”,
“MOOD”: “indicative”,
“PROG”: “-”,
“PERF”: “-”,
“cvarsort”: “e”
},
“lnk”: {
“from”: 220,
“to”: 240
}
},
{
“nodeid”: 10059,
“predicate”: “proper_q”,
“lnk”: {
“from”: 220,
“to”: 229
}
},
{
“nodeid”: 10060,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “physicist”,
“lnk”: {
“from”: 220,
“to”: 229
}
},
{
“nodeid”: 10061,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Christiaan”,
“lnk”: {
“from”: 230,
“to”: 240
}
},
{
“nodeid”: 10062,
“predicate”: “named”,
“sortinfo”: {
“PERS”: “3”,
“NUM”: “sg”,
“IND”: “+”,
“cvarsort”: “x”
},
“carg”: “Huygens”,
“lnk”: {
“from”: 241,
“to”: 249
}
}
],
“links”: [
{
“from”: 10000,
“to”: 10001,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10002,
“to”: 10001,
“rargname”: “ARG1”,
“post”: “NEQ”
},
{
“from”: 10002,
“to”: 10006,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10003,
“to”: 10006,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10004,
“to”: 10006,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10005,
“to”: 10006,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10007,
“to”: 10002,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10007,
“to”: 10035,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10008,
“to”: 10035,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10009,
“to”: 10016,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10010,
“to”: 10016,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10010,
“to”: 10015,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10011,
“to”: 10015,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10012,
“to”: 10015,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10012,
“to”: 10014,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10013,
“to”: 10014,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10017,
“to”: 10016,
“rargname”: “ARG2”,
“post”: “EQ”
},
{
“from”: 10017,
“to”: 10019,
“rargname”: “ARG3”,
“post”: “H”
},
{
“from”: 10018,
“to”: 10017,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10018,
“to”: 10016,
“rargname”: “ARG2”,
“post”: “EQ”
},
{
“from”: 10019,
“to”: 10016,
“rargname”: “ARG1”,
“post”: “NEQ”
},
{
“from”: 10019,
“to”: 10023,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10020,
“to”: 10023,
“rargname”: “ARG1”,
“post”: “NEQ”
},
{
“from”: 10020,
“to”: 10034,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10021,
“to”: 10023,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10022,
“to”: 10023,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10024,
“to”: 10034,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10025,
“to”: 10034,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10025,
“to”: 10033,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10026,
“to”: 10033,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10027,
“to”: 10033,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10027,
“to”: 10032,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10028,
“to”: 10032,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10029,
“to”: 10032,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10029,
“to”: 10031,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10030,
“to”: 10031,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10035,
“to”: 10016,
“rargname”: “L-INDEX”,
“post”: “NEQ”
},
{
“from”: 10035,
“to”: 10043,
“rargname”: “R-INDEX”,
“post”: “NEQ”
},
{
“from”: 10036,
“to”: 10043,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10037,
“to”: 10043,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10037,
“to”: 10042,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10038,
“to”: 10042,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10039,
“to”: 10042,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10039,
“to”: 10041,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10040,
“to”: 10041,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10044,
“to”: 10043,
“rargname”: “ARG2”,
“post”: “EQ”
},
{
“from”: 10044,
“to”: 10046,
“rargname”: “ARG3”,
“post”: “H”
},
{
“from”: 10045,
“to”: 10044,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10045,
“to”: 10043,
“rargname”: “ARG2”,
“post”: “EQ”
},
{
“from”: 10046,
“to”: 10043,
“rargname”: “ARG1”,
“post”: “NEQ”
},
{
“from”: 10046,
“to”: 10050,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10047,
“to”: 10050,
“rargname”: “ARG1”,
“post”: “NEQ”
},
{
“from”: 10047,
“to”: 10054,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10048,
“to”: 10050,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10049,
“to”: 10050,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10051,
“to”: 10054,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10052,
“to”: 10053,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10054,
“to”: 10053,
“rargname”: “L-INDEX”,
“post”: “NEQ”
},
{
“from”: 10054,
“to”: 10062,
“rargname”: “R-INDEX”,
“post”: “NEQ”
},
{
“from”: 10055,
“to”: 10062,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10056,
“to”: 10062,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10056,
“to”: 10061,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10057,
“to”: 10061,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10058,
“to”: 10061,
“rargname”: “ARG1”,
“post”: “EQ”
},
{
“from”: 10058,
“to”: 10060,
“rargname”: “ARG2”,
“post”: “NEQ”
},
{
“from”: 10059,
“to”: 10060,
“rargname”: “RSTR”,
“post”: “H”
},
{
“from”: 10020,
“to”: 10019,
“rargname”: “MOD”,
“post”: “EQ”
},
{
“from”: 10047,
“to”: 10046,
“rargname”: “MOD”,
“post”: “EQ”
}
],
“top”: 10002,
“index”: 10002,
“surface”: “The spacecraft consists of two main elements: the NASA Cassini Orbiter, named after the Italian-French astronomer Giovanni Domenico Cassini, and the ESA Huygens probe, named after the Dutch astronomer, mathematician and physicist Christiaan Huygens.”
}

Thanks for your answers

`

Is telling you that the PoS tagger pre-processor tagged the astronomer as nn (noun). The ERG grammar does not have this word in its lexicon, but the PoS tagger was able to help the grammar. ERG has generic rules to deal with those lexical units that we analyzed by the pre-processor. So it is not a problem, right the opposite, this shows that the process is robust.

What version of the ERG grammar are you using? The inconsistency of the analysis of the occurences do not happen in the demo:

http://delph-in.github.io/delphin-viz/demo/#input=The%20spacecraft%20consists%20of%20two%20main%20elements:%20the%20NASA%20Cassini%20Orbiter,%20named%20after%20the%20Italian-French%20astronomer%20Giovanni%20Domenico%20Cassini,%20and%20the%20ESA%20Huygens%20probe,%20named%20after%20the%20Dutch%20astronomer,%20mathematician%20and%20physicist%20Christiaan%20Huygens.&count=5&grammar=erg2018-uw&mrs=true&dmrs=true

I got _astronomer_n_1 for both occurrences in the first result. In the first case, the Italian-French astronomer makes a compound. In the second case, the dutch was taken as an adjective modifying the word astronomer. The difference is probably due to the capitalization of the words Italian and French.

Actually, in your case, the first occurrence was understood as a proper noun and the second occurrence was the one tagged automatically by the PoS tagger.

1 Like

I’m actually using the 1214 ERG grammar.
thank you for the explanation.

1 Like

Oh, this is a old version. You can find the last version and the trunk version in ErgTop · delph-in/docs Wiki · GitHub.