japanese_tagger.py 文件源码

def __init__(self, model_path, word_dim=None, char_dim=None):
        self.model_path = model_path
        defs_file = model_path + "/tagger_defs.txt"
        if word_dim is None:
            # use as supertagger
            with open(defs_file) as f:
                defs = json.load(f)
            self.word_dim = defs["word_dim"]
            self.char_dim = defs["char_dim"]
        else:
            # training
            self.word_dim = word_dim
            self.char_dim = char_dim
            with open(defs_file, "w") as f:
                json.dump({"model": self.__class__.__name__,
                           "word_dim": self.word_dim,
                           "char_dim": self.char_dim}, f)

        self.extractor = FeatureExtractor(model_path)
        self.targets = read_model_defs(model_path + "/target.txt")
        self.train = True

        hidden_dim = 1000
        in_dim = WINDOW_SIZE * (self.word_dim + self.char_dim)
        super(JaCCGEmbeddingTagger, self).__init__(
                emb_word=L.EmbedID(len(self.extractor.words), self.word_dim),
                emb_char=L.EmbedID(len(self.extractor.chars),
                            self.char_dim, ignore_label=IGNORE),
                linear1=L.Linear(in_dim, hidden_dim),
                linear2=L.Linear(hidden_dim, len(self.targets)),
                )