ja_lstm_parser_bi.py 文件源码

def __init__(self, model_path, word_dim=None, char_dim=None, nlayers=2,
            hidden_dim=128, dep_dim=100, dropout_ratio=0.5):
        self.model_path = model_path
        defs_file = model_path + "/tagger_defs.txt"
        if word_dim is None:
            self.train = False
            Param.load(self, defs_file)
            self.extractor = FeatureExtractor(model_path)
        else:
            self.train = True
            p = Param(self)
            p.dep_dim = dep_dim
            p.word_dim = word_dim
            p.char_dim = char_dim
            p.hidden_dim = hidden_dim
            p.nlayers = nlayers
            p.n_words = len(read_model_defs(model_path + "/words.txt"))
            p.n_chars = len(read_model_defs(model_path + "/chars.txt"))
            p.targets = read_model_defs(model_path + "/target.txt")
            p.dump(defs_file)

        self.in_dim = self.word_dim + self.char_dim
        self.dropout_ratio = dropout_ratio
        super(BiaffineJaLSTMParser, self).__init__(
                emb_word=L.EmbedID(self.n_words, self.word_dim),
                emb_char=L.EmbedID(self.n_chars, 50, ignore_label=IGNORE),
                conv_char=L.Convolution2D(1, self.char_dim,
                    (3, 50), stride=1, pad=(1, 0)),
                lstm_f=L.NStepLSTM(self.nlayers, self.in_dim,
                    self.hidden_dim, 0.32),
                lstm_b=L.NStepLSTM(self.nlayers, self.in_dim,
                    self.hidden_dim, 0.32),
                arc_dep=L.Linear(2 * self.hidden_dim, self.dep_dim),
                arc_head=L.Linear(2 * self.hidden_dim, self.dep_dim),
                rel_dep=L.Linear(2 * self.hidden_dim, self.dep_dim),
                rel_head=L.Linear(2 * self.hidden_dim, self.dep_dim),
                biaffine_arc=Biaffine(self.dep_dim),
                biaffine_tag=L.Bilinear(self.dep_dim, self.dep_dim, len(self.targets))
                )