vocab_size = 50000 word_pos_morph_embeddings = torch.nn.Embedding( num_embeddings=len(itos) + 3, embedding_dim=args.emb_dim).cuda() outVocabSize = 3 + len(itos) itos_total = ["EOS", "OOV", "SOS" ] + itos #+ itos_lemmas[:vocab_size] + itos_morph assert len(itos_total) == outVocabSize # could also provide per-word subcategorization frames from the treebank as input??? #baseline = nn.Linear(args.emb_dim, 1).cuda() dropout = nn.Dropout(args.dropout_rate).cuda() rnn_both = nn.GRU(2 * args.emb_dim, args.rnn_dim, args.rnn_layers).cuda() for name, param in rnn_both.named_parameters(): if 'bias' in name: nn.init.constant(param, 0.0) elif 'weight' in name: nn.init.xavier_normal(param) decoder = nn.Linear(args.rnn_dim, outVocabSize).cuda() #pos_ptb_decoder = nn.Linear(128,len(posFine)+3).cuda() startHidden = nn.Linear(1, args.rnn_dim).cuda() startHidden.bias.data.fill_(0) components = [rnn_both, decoder, word_pos_morph_embeddings, startHidden] hiddenToLogSDHidden = nn.Linear(args.rnn_dim, args.rnn_dim).cuda()
vocab_size = 50000 word_pos_morph_embeddings = torch.nn.Embedding( num_embeddings=len(itos) + 3, embedding_dim=args.emb_dim).cuda() outVocabSize = 3 + len(itos) #+vocab_size+len(morphKeyValuePairs)+3 itos_total = ["EOS", "OOV", "SOS" ] + itos #+ itos_lemmas[:vocab_size] + itos_morph assert len(itos_total) == outVocabSize # could also provide per-word subcategorization frames from the treebank as input??? #baseline = nn.Linear(args.emb_dim, 1).cuda() dropout = nn.Dropout(args.dropout_rate).cuda() rnn_both = nn.GRU(2 * args.emb_dim, args.rnn_dim, args.rnn_layers).cuda() for name, param in rnn_both.named_parameters(): if 'bias' in name: nn.init.constant(param, 0.0) elif 'weight' in name: nn.init.xavier_normal(param) decoder = nn.Linear(args.rnn_dim, outVocabSize).cuda() #pos_ptb_decoder = nn.Linear(128,len(posFine)+3).cuda() startHidden = nn.Linear(1, args.rnn_dim).cuda() startHidden.bias.data.fill_(0) components = [rnn_both, decoder, word_pos_morph_embeddings, startHidden] char_embeddings = torch.nn.Embedding(num_embeddings=len(itos_chars_total) + 3,