| { |
| "padding": true, |
| "return_lengths": true, |
| "return_word_embeddings": true, |
| "return_casing": false, |
| "return_features": false, |
| "return_chars": true, |
| "return_bert_embeddings": false, |
| "vocab_char": { |
| "<PAD>": 0, |
| "<UNK>": 1, |
| "\"": 2, |
| "%": 3, |
| "(": 4, |
| ")": 5, |
| "*": 6, |
| ",": 7, |
| "-": 8, |
| ".": 9, |
| "/": 10, |
| "0": 11, |
| "1": 12, |
| "2": 13, |
| "3": 14, |
| "4": 15, |
| "5": 16, |
| "6": 17, |
| "7": 18, |
| "8": 19, |
| "A": 20, |
| "B": 21, |
| "C": 22, |
| "D": 23, |
| "F": 24, |
| "G": 25, |
| "H": 26, |
| "I": 27, |
| "J": 28, |
| "K": 29, |
| "L": 30, |
| "M": 31, |
| "N": 32, |
| "O": 33, |
| "P": 34, |
| "R": 35, |
| "S": 36, |
| "T": 37, |
| "U": 38, |
| "V": 39, |
| "W": 40, |
| "Y": 41, |
| "Z": 42, |
| "^": 43, |
| "_": 44, |
| "a": 45, |
| "b": 46, |
| "c": 47, |
| "d": 48, |
| "e": 49, |
| "f": 50, |
| "g": 51, |
| "h": 52, |
| "i": 53, |
| "k": 54, |
| "l": 55, |
| "m": 56, |
| "n": 57, |
| "o": 58, |
| "p": 59, |
| "q": 60, |
| "r": 61, |
| "s": 62, |
| "t": 63, |
| "u": 64, |
| "v": 65, |
| "w": 66, |
| "x": 67, |
| "y": 68, |
| "z": 69, |
| "{": 70, |
| "}": 71, |
| "~": 72, |
| "\u00b0": 73, |
| "\u00b2": 74, |
| "\u00b3": 75, |
| "\u00b5": 76, |
| "\u00c1": 77, |
| "\u00c5": 78, |
| "\u00d7": 79, |
| "\u03a9": 80, |
| "\u03bc": 81, |
| "\u03c3": 82, |
| "\u2022": 83, |
| "\u2032": 84, |
| "\u20ac": 85, |
| "\u2113": 86, |
| "\u2215": 87, |
| "\u221a": 88, |
| "\u25a1": 89, |
| "\u25fb": 90, |
| "\u29e0": 91 |
| }, |
| "vocab_tag": { |
| "<PAD>": 0, |
| "B-<base>": 1, |
| "B-<pow>": 2, |
| "B-<prefix>": 3, |
| "I-<base>": 4, |
| "I-<pow>": 5, |
| "O": 6 |
| }, |
| "vocab_case": [ |
| "<PAD>", |
| "numeric", |
| "allLower", |
| "allUpper", |
| "initialUpper", |
| "other", |
| "mainly_numeric", |
| "contains_digit" |
| ], |
| "max_char_length": 30, |
| "feature_preprocessor": null, |
| "indice_tag": { |
| "0": "<PAD>", |
| "1": "B-<base>", |
| "2": "B-<pow>", |
| "3": "B-<prefix>", |
| "4": "I-<base>", |
| "5": "I-<pow>", |
| "6": "O" |
| } |
| } |