this repo has no description
at main 169 lines 2.3 kB view raw
1[ 2 { 3 "text": "Barack Obama visited Paris.", 4 "tokens": [ 5 "Barack", 6 "Obama", 7 "visited", 8 "Paris", 9 "." 10 ] 11 }, 12 { 13 "text": "Apple Inc. is worth $2.5 trillion.", 14 "tokens": [ 15 "Apple", 16 "Inc.", 17 "is", 18 "worth", 19 "$", 20 "2.5", 21 "trillion", 22 "." 23 ] 24 }, 25 { 26 "text": "I can't believe it's not butter!", 27 "tokens": [ 28 "I", 29 "ca", 30 "n't", 31 "believe", 32 "it", 33 "'s", 34 "not", 35 "butter", 36 "!" 37 ] 38 }, 39 { 40 "text": "Dr. Smith's office (room 42) is closed.", 41 "tokens": [ 42 "Dr.", 43 "Smith", 44 "'s", 45 "office", 46 "(", 47 "room", 48 "42", 49 ")", 50 "is", 51 "closed", 52 "." 53 ] 54 }, 55 { 56 "text": "U.S.A. and U.K. are allies.", 57 "tokens": [ 58 "U.S.A.", 59 "and", 60 "U.K.", 61 "are", 62 "allies", 63 "." 64 ] 65 }, 66 { 67 "text": "They're going to the store.", 68 "tokens": [ 69 "They", 70 "'re", 71 "going", 72 "to", 73 "the", 74 "store", 75 "." 76 ] 77 }, 78 { 79 "text": "He said \"hello\" and left.", 80 "tokens": [ 81 "He", 82 "said", 83 "\"", 84 "hello", 85 "\"", 86 "and", 87 "left", 88 "." 89 ] 90 }, 91 { 92 "text": "The cost is $500.00/month.", 93 "tokens": [ 94 "The", 95 "cost", 96 "is", 97 "$", 98 "500.00", 99 "/", 100 "month", 101 "." 102 ] 103 }, 104 { 105 "text": "New York-based company", 106 "tokens": [ 107 "New", 108 "York", 109 "-", 110 "based", 111 "company" 112 ] 113 }, 114 { 115 "text": "e-mail: test@example.com", 116 "tokens": [ 117 "e", 118 "-", 119 "mail", 120 ":", 121 "test@example.com" 122 ] 123 }, 124 { 125 "text": "10,000 people", 126 "tokens": [ 127 "10,000", 128 "people" 129 ] 130 }, 131 { 132 "text": "3.14159 is pi", 133 "tokens": [ 134 "3.14159", 135 "is", 136 "pi" 137 ] 138 }, 139 { 140 "text": "state-of-the-art technology", 141 "tokens": [ 142 "state", 143 "-", 144 "of", 145 "-", 146 "the", 147 "-", 148 "art", 149 "technology" 150 ] 151 }, 152 { 153 "text": "Mr. and Mrs. Jones", 154 "tokens": [ 155 "Mr.", 156 "and", 157 "Mrs.", 158 "Jones" 159 ] 160 }, 161 { 162 "text": "it's 5:30pm", 163 "tokens": [ 164 "it", 165 "'s", 166 "5:30pm" 167 ] 168 } 169]