ENIAMlexSemanticsTypes.ml
4.29 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
(*
* ENIAMlexSemantics is a library that assigns tokens with lexicosemantic information.
* Copyright (C) 2016-2017 Wojciech Jaworski <wjaworski atSPAMfree mimuw dot edu dot pl>
* Copyright (C) 2016-2017 Institute of Computer Science Polish Academy of Sciences
*
* This library is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*)
open ENIAMtokenizerTypes
open Xstd
(* FIXME: usunąć *)
(*type labels = {
number: string;
case: string;
gender: string;
person: string;
aspect: string;
}*)
type semantics =
Normal
| Special of string list
(* | SpecialNoun of type_arg list * type_term
| SpecialMod of string * (type_arg list * type_term)*)
| PrepSemantics of (string * string * string * StringSet.t * string list) list (* case,role,role_attr,hipero,sel_prefs *)
type frame = {
selectors: (ENIAM_LCGlexiconTypes.selector * ENIAM_LCGlexiconTypes.selector_relation * string list) list;
meanings: ((*ENIAMwalTypes.meaning **) string * (string * int) list * float) list;
positions: ENIAMwalTypes.position list;
arole: string;
arole_attr: string;
arev: bool;
sopinion: ENIAMwalTypes.opinion;
fopinion: ENIAMwalTypes.opinion;
}
let empty_frame = {selectors=[]; meanings=[]; positions=[]; arole=""; arole_attr=""; arev=false;
sopinion=ENIAMwalTypes.Nieokreslony; fopinion=ENIAMwalTypes.Nieokreslony}
type lex_sem = {
schemata: ((ENIAM_LCGlexiconTypes.selector * ENIAM_LCGlexiconTypes.selector_relation * string list) list *
(ENIAM_LCGtypes.direction * ENIAM_LCGtypes.grammar_symbol) list) list;
lex_entries: ((ENIAM_LCGlexiconTypes.selector * ENIAM_LCGlexiconTypes.selector_relation * string list) list *
ENIAM_LCGtypes.grammar_symbol) list;
frames: frame list;
cats: string list;
(* e: labels; *)
(* valence: (int * ENIAMwalTypes.frame) list;
simple_valence: (int * ENIAMwalTypes.frame) list;
very_simple_valence: ((ENIAM_LCGgrammarPLtypes.cat * ENIAM_LCGgrammarPLtypes.selector_relation * string list) list * ENIAM_LCGtypes.grammar_symbol) list; *)
(* senses: (string * (string * int) list * float) list; *)
(* lroles: string * string; *)
semantics: semantics;
}
(*let empty_labels = {
number="";
case="";
gender="";
person="";
aspect="";
}*)
let empty_lex_sem = {
schemata=[]; lex_entries=[]; frames=[]; cats=["X"];
(*e=empty_labels;*) (*valence=[]; simple_valence=[]; very_simple_valence=[];*) (*senses=[];*)
(*lroles="","";*) semantics=Normal}
(* FIXME: poprawić katalog *)
(*let subst_uncountable_lexemes_filename = resource_path ^ "/lexSemantics/subst_uncountable.dat"
let subst_uncountable_lexemes_filename2 = resource_path ^ "/lexSemantics/subst_uncountable_stare.dat"
let subst_container_lexemes_filename = resource_path ^ "/lexSemantics/subst_container.dat"
let subst_numeral_lexemes_filename = resource_path ^ "/lexSemantics/subst_numeral.dat"
let subst_time_lexemes_filename = resource_path ^ "/lexSemantics/subst_time.dat"*)
(* let subst_uncountable_lexemes_filename = resource_path ^ "/Walenty/subst_uncountable.dat"
let subst_uncountable_lexemes_filename2 = resource_path ^ "/Walenty/subst_uncountable_stare.dat"
let subst_container_lexemes_filename = resource_path ^ "/Walenty/subst_container.dat"
let subst_numeral_lexemes_filename = resource_path ^ "/Walenty/subst_numeral.dat"
let subst_time_lexemes_filename = resource_path ^ "/Walenty/subst_time.dat" *)
let hipero_threshold = 3
let unknown_meaning_weight = -1.
let lu_filename = resource_path ^ "/plWordnet/lu.tab"
let ex_hipo_filename = resource_path ^ "/plWordnet/ex_hipo.tab"
let syn_filename = resource_path ^ "/plWordnet/syn.tab"
let predef_filename = resource_path ^ "/lexSemantics/predef_prefs.tab"
let proper_classes_filename = resource_path ^ "/lexSemantics/proper_classes.tab"