def __init__(self, params, vocab):
super(SLUTagger, self).__init__()
self.lstm = Lstm(params, vocab)
self.num_slot = params.num_slot
self.hidden_dim = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
self.linear = nn.Linear(self.hidden_dim, self.num_slot)
self.crf_layer = CRF(self.num_slot)
def __init__(self, params, vocab):
super(BiLSTMCRFTagger, self).__init__()
self.lstm = Lstm(params, vocab)
self.num_entity_label = params.num_entity_label
self.hidden_dim = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
self.linear = nn.Linear(self.hidden_dim, self.num_entity_label)
self.crf_layer = CRF(self.num_entity_label)
def __init__(self, params, vocab):
super(SentRepreGenerator, self).__init__()
self.hidden_size = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
self.template_encoder = Lstm(params, vocab)
self.input_atten_layer = Attention(attention_size=self.hidden_size)
self.template_attn_layer = Attention(attention_size=self.hidden_size)
def __init__(self, params, vocab):
super(SentRepreGenerator, self).__init__()
self.hidden_size = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
# LSTM Encoder for template
self.template_encoder = Lstm(params, vocab)
# attention layers for templates and input sequences
self.input_atten_layer = Attention(attention_size=self.hidden_size)
self.template_attn_layer = Attention(attention_size=self.hidden_size)
def __init__(self, params, vocab):
super(CoarseSLUTagger, self).__init__()
self.lstm = Lstm(params, vocab)
self.num_binslot = params.num_binslot
self.hidden_dim = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
self.linear = nn.Linear(self.hidden_dim, self.num_binslot)
self.linear_chunking = nn.Linear(self.hidden_dim, 3)
self.crf_layer_chunking = CRF(3)
self.crf_layer = CRF(self.num_binslot)
self.domain_coarse_mask = self.gen_emission_mask()
def __init__(self, params, vocab_en, vocab_trans):
super(ModelSLU, self).__init__()
self.label_reg = params.la_reg
self.adversarial = params.adv
self.intent_adv = params.intent_adv
self.zeroshot = params.zs
if self.label_reg == True:
self.label_encoder = LabelEncoder(params)
self.lstm = Lstm(params, vocab_en, vocab_trans)
self.intent_predictor = IntentPredictor(params)
self.slot_predictor = SlotPredictor(params)
def __init__(self, params, vocab):
super(ConceptTagger, self).__init__()
self.use_example = params.use_example
if self.use_example:
hidden_dim = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
self.w_a = nn.Parameter(torch.FloatTensor(hidden_dim))
torch.nn.init.uniform(self.w_a.data, -0.01, 0.01)
self.softmax = nn.Softmax(dim=-1)
self.lstm_encoder = Lstm(params, vocab)
self.lstm_predictor = LstmBasedSlotPredictor(params)
self.slot_embs = load_embedding_from_pkl(params.slot_emb_file)
self.example_embs = load_embedding_from_pkl(params.example_emb_file)
def __init__(self, params, vocab):
super(ConceptTagger, self).__init__()
self.use_example = params.use_example
if self.use_example:
hidden_dim = params.hidden_dim * 2 if params.bidirection else params.hidden_dim
self.w_a = nn.Parameter(torch.FloatTensor(hidden_dim))
torch.nn.init.uniform(self.w_a.data, -0.01, 0.01)
self.softmax = nn.Softmax(dim=-1)
self.example_embs = torch.cuda.FloatTensor(
load_embedding_from_npy(
params.ner_example_emb_file)) # (num_entity, emb_dim, 2)
self.lstm_encoder = Lstm(params, vocab)
self.lstm_predictor = LstmBasedSlotPredictor(params)
self.entity_embs = torch.cuda.FloatTensor(
load_embedding_from_npy(
params.ner_entity_type_emb_file)) # (num_entity, emb_dim)
self.entity_embs_size = self.entity_embs.size()