def __init__(self, args):
super(MyModel, self).__init__()
self.args = args
self.embedding_dim = 300
self.embedding = nn.Embedding(len(vocab),
self.embedding_dim,
padding_idx=0)
self.embedding.weight.data.fill_(0)
self.embedding.weight.data[:2].normal_(0, 0.1)
self.pos_embedding = nn.Embedding(len(pos_vocab),
args.pos_emb_dim,
padding_idx=0)
self.pos_embedding.weight.data.normal_(0, 0.1)
self.ner_embedding = nn.Embedding(len(ner_vocab),
args.ner_emb_dim,
padding_idx=0)
self.ner_embedding.weight.data.normal_(0, 0.1)
self.rel_embedding = nn.Embedding(len(rel_vocab),
args.rel_emb_dim,
padding_idx=0)
self.rel_embedding.weight.data.normal_(0, 0.1)
#self.emb_match = layers.SeqAttnMatch(self.embedding_dim)
#self.q_emb_match = layers.SeqAttnMatch(self.embedding_dim)
#self.c_emb_match = layers.SeqAttnMatch(self.embedding_dim)
#self.p_q_emb_match = layers.SeqAttnMatch(self.embedding_dim)
#self.c_q_emb_match = layers.SeqAttnMatch(self.embedding_dim)
#self.c_p_emb_match = layers.SeqAttnMatch(self.embedding_dim)
self.RNN_TYPES = {'lstm': nn.LSTM, 'gru': nn.GRU}
print("###########self.args.matching_order: %s " %
(self.args.matching_order))
# RNN context encoder
#rnn_input_size = self.embedding_dim+ args.pos_emb_dim + args.ner_emb_dim +5+ 2*args.rel_emb_dim
rnn_input_size = self.embedding_dim + args.pos_emb_dim + args.ner_emb_dim + 5 + 2 * args.rel_emb_dim
#rnn_input_size = self.embedding_dim+ 5
self.context_rnn = layers.StackedBRNN(
input_size=rnn_input_size,
#input_size=self.embedding_dim,
hidden_size=args.hidden_size,
num_layers=args.doc_layers,
dropout_rate=0,
dropout_output=args.dropout_rnn_output,
concat_layers=False,
rnn_type=self.RNN_TYPES[args.rnn_type],
padding=args.rnn_padding)
self.hidden_match = layers.SeqDotAttnMatch()
self.mtinfer = layers.MultiTurnInference(args, self.RNN_TYPES)
#mtinfer output size
if args.use_multiturn_infer or args.use_bilstm:
choice_infer_hidden_size = 2 * args.hidden_size
#choice_infer_hidden_size = 2 * args.hidden_size * len(args.matching_order)
else:
#choice_infer_hidden_size = args.hidden_size * len(args.matching_order)
choice_infer_hidden_size = 2 * args.hidden_size
#self.c_infer_self_attn = layers.LinearSeqAttn(choice_infer_hidden_size)
self.q_self_attn = layers.LinearSeqAttn(2 * args.hidden_size)
if args.use_multiturn_infer == True:
self.c_infer_linear = nn.Linear(4 * choice_infer_hidden_size,
args.hidden_size)
#elif args.use_bilstm == True:
else:
self.c_infer_linear = nn.Linear(
2 * choice_infer_hidden_size + 2 * 2 * args.hidden_size,
args.hidden_size)
self.logits_linear = nn.Linear(args.hidden_size, 1)
def __init__(self, args):
super(MyModel, self).__init__()
self.args = args
self.embedding_dim = 300
self.embedding = nn.Embedding(len(vocab),
self.embedding_dim,
padding_idx=0)
self.embedding.weight.data.fill_(0)
self.embedding.weight.data[:2].normal_(0, 0.1)
self.pos_embedding = nn.Embedding(len(pos_vocab),
args.pos_emb_dim,
padding_idx=0)
self.pos_embedding.weight.data.normal_(0, 0.1)
self.ner_embedding = nn.Embedding(len(ner_vocab),
args.ner_emb_dim,
padding_idx=0)
self.ner_embedding.weight.data.normal_(0, 0.1)
self.rel_embedding = nn.Embedding(len(rel_vocab),
args.rel_emb_dim,
padding_idx=0)
self.rel_embedding.weight.data.normal_(0, 0.1)
self.RNN_TYPES = {'lstm': nn.LSTM, 'gru': nn.GRU}
print("###########self.args.matching_order: %s " %
(self.args.matching_order))
# RNN context encoder
#rnn_input_size = self.embedding_dim+ args.pos_emb_dim + args.ner_emb_dim +5+ 2*args.rel_emb_dim
rnn_input_size = self.embedding_dim + args.pos_emb_dim + args.ner_emb_dim + 5 + 2 * args.rel_emb_dim
#rnn_input_size = self.embedding_dim+ 5
self.context_rnn = layers.StackedBRNN(
input_size=rnn_input_size,
hidden_size=args.hidden_size,
num_layers=args.doc_layers,
dropout_rate=args.dropout_rnn_output, # float
dropout_output=args.rnn_output_dropout, #True or False
concat_layers=False,
rnn_type=self.RNN_TYPES[args.rnn_type],
padding=args.rnn_padding)
self.Hq_BiLstm = layers.StackedBRNN(
input_size=rnn_input_size + args.hidden_size,
hidden_size=args.hidden_size,
num_layers=1,
dropout_rate=args.dropout_rnn_output, # float
dropout_output=args.rnn_output_dropout, #True or False
concat_layers=False,
rnn_type=self.RNN_TYPES[args.rnn_type],
padding=args.rnn_padding)
self.hidden_match = layers.SeqDotAttnMatch()
self.mtinfer = layers.MultiTurnInference(args, self.RNN_TYPES)
if self.args.tri_input == 'NA':
self.mfunction = self.NA_TriMatching
elif self.args.tri_input == 'CA':
self.mfunction = self.CA_TriMatching
else:
self.mfunction = self.NA_CA_TriMatching
#mtinfer output size
if args.use_multiturn_infer or args.use_bilstm:
choice_infer_hidden_size = 2 * args.hidden_size
#choice_infer_hidden_size = 2 * args.hidden_size * len(args.matching_order)
else:
#choice_infer_hidden_size = args.hidden_size * len(args.matching_order)
choice_infer_hidden_size = 2 * args.hidden_size
#self.c_infer_self_attn = layers.LinearSeqAttn(choice_infer_hidden_size)
self.q_self_attn = layers.LinearSeqAttn(2 * args.hidden_size)
'''my:'''
self.linearlayer = nn.Linear(rnn_input_size, args.hidden_size) ##my
self.pre_y = nn.Linear(
2 * args.hidden_size + args.pos_emb_dim + args.ner_emb_dim + 5 +
2 * args.rel_emb_dim, 1)
if args.use_multiturn_infer == True:
#self.c_infer_linear= nn.Linear(4*choice_infer_hidden_size,args.hidden_size)
self.c_infer_linear = nn.Linear(
4 * choice_infer_hidden_size + 2 * 2 * args.hidden_size,
args.hidden_size)
#elif args.use_bilstm == True:
else:
infer_input_size = 2 * 2 * args.hidden_size
if self.args.p_channel == True:
infer_input_size += 2 * choice_infer_hidden_size
if self.args.q_channel == True:
infer_input_size += 2 * choice_infer_hidden_size
if self.args.c_channel == True:
infer_input_size += 2 * choice_infer_hidden_size
self.c_infer_linear = nn.Linear(infer_input_size, args.hidden_size)