def __init__(self, word_dim, num_words, char_dim, num_chars, pos_dim, num_pos, rnn_mode, hidden_size, num_layers, num_labels, arc_space, type_space,
embedd_word=None, embedd_char=None, embedd_pos=None, p_in=0.33, p_out=0.33, p_rnn=(0.33, 0.33), pos=True, activation='elu'):
super(DeepBiAffine, self).__init__()
self.word_embed = nn.Embedding(num_words, word_dim, _weight=embedd_word, padding_idx=1)
self.pos_embed = nn.Embedding(num_pos, pos_dim, _weight=embedd_pos, padding_idx=1) if pos else None
self.char_embed = nn.Embedding(num_chars, char_dim, _weight=embedd_char, padding_idx=1)
self.char_cnn = CharCNN(2, char_dim, char_dim, hidden_channels=char_dim * 4, activation=activation)
self.dropout_in = nn.Dropout2d(p=p_in)
self.dropout_out = nn.Dropout2d(p=p_out)
self.num_labels = num_labels
if rnn_mode == 'RNN':
RNN = VarRNN
elif rnn_mode == 'LSTM':
RNN = VarLSTM
elif rnn_mode == 'FastLSTM':
RNN = VarFastLSTM
elif rnn_mode == 'GRU':
RNN = VarGRU
else:
raise ValueError('Unknown RNN mode: %s' % rnn_mode)
dim_enc = word_dim + char_dim
if pos:
dim_enc += pos_dim
self.rnn = RNN(dim_enc, hidden_size, num_layers=num_layers, batch_first=True, bidirectional=True, dropout=p_rnn)
out_dim = hidden_size * 2
self.arc_h = nn.Linear(out_dim, arc_space)
self.arc_c = nn.Linear(out_dim, arc_space)
self.biaffine = BiAffine(arc_space, arc_space)
self.type_h = nn.Linear(out_dim, type_space)
self.type_c = nn.Linear(out_dim, type_space)
self.bilinear = BiLinear(type_space, type_space, self.num_labels)
assert activation in ['elu', 'tanh']
if activation == 'elu':
self.activation = nn.ELU(inplace=True)
else:
self.activation = nn.Tanh()
self.criterion = nn.CrossEntropyLoss(reduction='none')
self.reset_parameters(embedd_word, embedd_char, embedd_pos)
def __init__(self,
word_dim,
num_words,
char_dim,
num_chars,
pos_dim,
num_pos,
rnn_mode,
hidden_size,
encoder_layers,
decoder_layers,
num_labels,
arc_space,
type_space,
embedd_word=None,
embedd_char=None,
embedd_pos=None,
p_in=0.33,
p_out=0.33,
p_rnn=(0.33, 0.33),
pos=True,
prior_order='inside_out',
grandPar=False,
sibling=False,
activation='elu'):
super(StackPtrNet, self).__init__()
self.word_embed = nn.Embedding(num_words,
word_dim,
_weight=embedd_word,
padding_idx=1)
self.pos_embed = nn.Embedding(
num_pos, pos_dim, _weight=embedd_pos,
padding_idx=1) if pos else None
self.char_embed = nn.Embedding(num_chars,
char_dim,
_weight=embedd_char,
padding_idx=1)
self.char_cnn = CharCNN(2,
char_dim,
char_dim,
hidden_channels=char_dim * 4,
activation=activation)
self.dropout_in = nn.Dropout2d(p=p_in)
self.dropout_out = nn.Dropout2d(p=p_out)
self.num_labels = num_labels
if prior_order in ['deep_first', 'shallow_first']:
self.prior_order = PriorOrder.DEPTH
elif prior_order == 'inside_out':
self.prior_order = PriorOrder.INSIDE_OUT
elif prior_order == 'left2right':
self.prior_order = PriorOrder.LEFT2RIGTH
else:
raise ValueError('Unknown prior order: %s' % prior_order)
self.grandPar = grandPar
self.sibling = sibling
if rnn_mode == 'RNN':
RNN_ENCODER = VarRNN
RNN_DECODER = VarRNN
elif rnn_mode == 'LSTM':
RNN_ENCODER = VarLSTM
RNN_DECODER = VarLSTM
elif rnn_mode == 'FastLSTM':
RNN_ENCODER = VarFastLSTM
RNN_DECODER = VarFastLSTM
elif rnn_mode == 'GRU':
RNN_ENCODER = VarGRU
RNN_DECODER = VarGRU
else:
raise ValueError('Unknown RNN mode: %s' % rnn_mode)
dim_enc = word_dim + char_dim
if pos:
dim_enc += pos_dim
self.encoder_layers = encoder_layers
self.encoder = RNN_ENCODER(dim_enc,
hidden_size,
num_layers=encoder_layers,
batch_first=True,
bidirectional=True,
dropout=p_rnn)
dim_dec = hidden_size // 2
self.src_dense = nn.Linear(2 * hidden_size, dim_dec)
self.decoder_layers = decoder_layers
self.decoder = RNN_DECODER(dim_dec,
hidden_size,
num_layers=decoder_layers,
batch_first=True,
bidirectional=False,
dropout=p_rnn)
self.hx_dense = nn.Linear(2 * hidden_size, hidden_size)
self.arc_h = nn.Linear(hidden_size, arc_space) # arc dense for decoder
self.arc_c = nn.Linear(hidden_size * 2,
arc_space) # arc dense for encoder
self.biaffine = BiAffine(arc_space, arc_space)
self.type_h = nn.Linear(hidden_size,
type_space) # type dense for decoder
self.type_c = nn.Linear(hidden_size * 2,
type_space) # type dense for encoder
self.bilinear = BiLinear(type_space, type_space, self.num_labels)
assert activation in ['elu', 'tanh']
if activation == 'elu':
self.activation = nn.ELU(inplace=True)
else:
self.activation = nn.Tanh()
self.criterion = nn.CrossEntropyLoss(reduction='none')
self.reset_parameters(embedd_word, embedd_char, embedd_pos)