def __init__(self, name='PointerNet'):
super(PointerNet, self).__init__()
self.dense1_input = Dense(config.encoder_hidden_dim, config.ptrnet_hidden_dim, activation='linear', name='Dense1_input')
self.dense1_h = Dense(config.decoder_hidden_dim + config.encoder_hidden_dim, config.ptrnet_hidden_dim, activation='linear', name='Dense1_h')
self.dense2 = Dense(config.ptrnet_hidden_dim, 1, activation='linear', name='Dense2')
self.params += self.dense1_input.params + self.dense1_h.params + self.dense2.params
self.set_name(name)
def _set_layers(self, n_experts, hidden_dim, output_dim):
mixture = Dense(input_dim=1,
output_dim=n_experts,
activation=None,
use_bias=False,
weight_init='zero',
bias_init='zero')
hidden_layer = Dense(input_dim=hidden_dim,
output_dim=hidden_dim,
weight_init="identity")
output_layer = Dense(input_dim=hidden_dim, output_dim=output_dim)
self.hidden_dim = hidden_dim
self.layers = [mixture, hidden_layer, output_layer]
def __init__(self):
# self.node_embedding = Embedding(config.node_num, config.node_embed_dim, name='node_embed')
self.query_embedding = Embedding(config.source_vocab_size, config.word_embed_dim, name='query_embed')
if config.encoder_lstm == 'bilstm':
self.query_encoder_lstm = BiLSTM(config.word_embed_dim, config.encoder_hidden_dim / 2, return_sequences=True,
name='query_encoder_lstm')
else:
self.query_encoder_lstm = LSTM(config.word_embed_dim, config.encoder_hidden_dim, return_sequences=True,
name='query_encoder_lstm')
self.decoder_lstm = CondAttLSTM(config.rule_embed_dim + config.node_embed_dim + config.rule_embed_dim,
config.decoder_hidden_dim, config.encoder_hidden_dim, config.attention_hidden_dim,
name='decoder_lstm')
self.src_ptr_net = PointerNet()
self.terminal_gen_softmax = Dense(config.decoder_hidden_dim, 2, activation='softmax', name='terminal_gen_softmax')
self.rule_embedding_W = initializations.get('normal')((config.rule_num, config.rule_embed_dim), name='rule_embedding_W', scale=0.1)
self.rule_embedding_b = shared_zeros(config.rule_num, name='rule_embedding_b')
self.node_embedding = initializations.get('normal')((config.node_num, config.node_embed_dim), name='node_embed', scale=0.1)
self.vocab_embedding_W = initializations.get('normal')((config.target_vocab_size, config.rule_embed_dim), name='vocab_embedding_W', scale=0.1)
self.vocab_embedding_b = shared_zeros(config.target_vocab_size, name='vocab_embedding_b')
# decoder_hidden_dim -> action embed
self.decoder_hidden_state_W_rule = Dense(config.decoder_hidden_dim, config.rule_embed_dim, name='decoder_hidden_state_W_rule')
# decoder_hidden_dim -> action embed
self.decoder_hidden_state_W_token= Dense(config.decoder_hidden_dim + config.encoder_hidden_dim, config.rule_embed_dim,
name='decoder_hidden_state_W_token')
# self.rule_encoder_lstm.params
self.params = self.query_embedding.params + self.query_encoder_lstm.params + \
self.decoder_lstm.params + self.src_ptr_net.params + self.terminal_gen_softmax.params + \
[self.rule_embedding_W, self.rule_embedding_b, self.node_embedding, self.vocab_embedding_W, self.vocab_embedding_b] + \
self.decoder_hidden_state_W_rule.params + self.decoder_hidden_state_W_token.params
self.srng = RandomStreams()
def __init__(self):
# self.node_embedding = Embedding(config.node_num, config.node_embed_dim, name='node_embed')
self.query_embedding = Embedding(config.source_vocab_size,
config.word_embed_dim,
name='query_embed')
encoder_dim = config.word_embed_dim
logging.info("Concatenation type: %s" % config.concat_type)
logging.info("Include canon_id matrix: %s" % config.include_cid)
if config.concat_type == 'basic':
encoder_dim += 2
if config.include_cid == True:
encoder_dim += 1
else:
# define layers
self.query_phrase_embedding = Embedding(14,
8,
name='query_phrase_embed')
self.query_pos_embedding = Embedding(44,
32,
name='query_pos_embed')
self.query_canon_embedding = Embedding(
102, 64, name='query_canon_embedding')
aug_dim = 8 + 32
if config.include_cid == True:
aug_dim += 64
self.projector = Dense(config.word_embed_dim + aug_dim,
config.word_embed_dim,
activation='linear',
name='concat_projector')
if config.encoder == 'bilstm':
self.query_encoder_lstm = BiLSTM(encoder_dim,
config.encoder_hidden_dim / 2,
return_sequences=True,
name='query_encoder_lstm')
else:
self.query_encoder_lstm = LSTM(encoder_dim,
config.encoder_hidden_dim,
return_sequences=True,
name='query_encoder_lstm')
self.decoder_lstm = CondAttLSTM(config.rule_embed_dim +
config.node_embed_dim +
config.rule_embed_dim,
config.decoder_hidden_dim,
config.encoder_hidden_dim,
config.attention_hidden_dim,
name='decoder_lstm')
self.src_ptr_net = PointerNet()
self.terminal_gen_softmax = Dense(config.decoder_hidden_dim,
2,
activation='softmax',
name='terminal_gen_softmax')
self.rule_embedding_W = initializations.get('normal')(
(config.rule_num, config.rule_embed_dim),
name='rule_embedding_W',
scale=0.1)
self.rule_embedding_b = shared_zeros(config.rule_num,
name='rule_embedding_b')
self.node_embedding = initializations.get('normal')(
(config.node_num, config.node_embed_dim),
name='node_embed',
scale=0.1)
self.vocab_embedding_W = initializations.get('normal')(
(config.target_vocab_size, config.rule_embed_dim),
name='vocab_embedding_W',
scale=0.1)
self.vocab_embedding_b = shared_zeros(config.target_vocab_size,
name='vocab_embedding_b')
# decoder_hidden_dim -> action embed
self.decoder_hidden_state_W_rule = Dense(
config.decoder_hidden_dim,
config.rule_embed_dim,
name='decoder_hidden_state_W_rule')
# decoder_hidden_dim -> action embed
self.decoder_hidden_state_W_token = Dense(
config.decoder_hidden_dim + config.encoder_hidden_dim,
config.rule_embed_dim,
name='decoder_hidden_state_W_token')
# self.rule_encoder_lstm.params
self.params = self.query_embedding.params + self.query_encoder_lstm.params + \
self.decoder_lstm.params + self.src_ptr_net.params + self.terminal_gen_softmax.params + \
[self.rule_embedding_W, self.rule_embedding_b, self.node_embedding, self.vocab_embedding_W, self.vocab_embedding_b] + \
self.decoder_hidden_state_W_rule.params + self.decoder_hidden_state_W_token.params
self.srng = RandomStreams()
def _set_layers(self, hidden_dim, output_dim):
self.layers = [Dense(input_dim=hidden_dim,
output_dim=output_dim)]