# map from common En characters (encoded as integers in the first column) and a unique index to be used by neural LMs. These characters were extracted from the 1-billion-word-language-modeling-benchmark-r13output. We use two special characters: 0, which stands for UNKNOWN, and 1, which stands for EOS
0	0
1	1
32	2
33	3
34	4
35	5
36	6
37	7
38	8
39	9
40	10
41	11
42	12
43	13
44	14
45	15
46	16
47	17
48	18
49	19
50	20
51	21
52	22
53	23
54	24
55	25
56	26
57	27
58	28
59	29
60	30
61	31
62	32
63	33
64	34
65	35
66	36
67	37
68	38
69	39
70	40
71	41
72	42
73	43
74	44
75	45
76	46
77	47
78	48
79	49
80	50
81	51
82	52
83	53
84	54
85	55
86	56
87	57
88	58
89	59
90	60
91	61
93	62
95	63
97	64
98	65
99	66
100	67
101	68
102	69
103	70
104	71
105	72
106	73
107	74
108	75
109	76
110	77
111	78
112	79
113	80
114	81
115	82
116	83
117	84
118	85
119	86
120	87
121	88
122	89
124	90
163	91
174	92
187	93
189	94
194	95
225	96
231	97
232	98
233	99
237	100
241	101
243	102
246	103
252	104
700	105
8226	106
8364	107
65533	108

