def build_embeddings(opt, text_field, for_encoder=True):
"""
Args:
opt: the option in current environment.
text_field(TextMultiField): word and feats field.
for_encoder(bool): build Embeddings for encoder or decoder?
"""
emb_dim = opt.src_word_vec_size if for_encoder else opt.tgt_word_vec_size
if opt.model_type == "vec" and for_encoder:
return VecEmbedding(
opt.feat_vec_size,
emb_dim,
position_encoding=opt.position_encoding,
dropout=(opt.dropout[0]
if type(opt.dropout) is list else opt.dropout),
)
pad_indices = [f.vocab.stoi[f.pad_token] for _, f in text_field]
word_padding_idx, feat_pad_indices = pad_indices[0], pad_indices[1:]
num_embs = [len(f.vocab) for _, f in text_field]
num_word_embeddings, num_feat_embeddings = num_embs[0], num_embs[1:]
fix_word_vecs = opt.fix_word_vecs_enc if for_encoder \
else opt.fix_word_vecs_dec
# if seg_token_id is None, it indicates that segment_embedding is False.
if opt.segment_embedding and for_encoder:
seg_token_id = opt.seg_token_id
else:
seg_token_id = None
# wei 20200723
if opt.flat_layers > 0 and for_encoder:
flat_layer_flag = opt.flat_layers
else:
flat_layer_flag = -1
# end wei
emb = Embeddings(
word_vec_size=emb_dim,
position_encoding=opt.position_encoding,
seg_token_id=seg_token_id,
# wei 20200723
flat_layer_flag=flat_layer_flag,
# end wei
feat_merge=opt.feat_merge,
feat_vec_exponent=opt.feat_vec_exponent,
feat_vec_size=opt.feat_vec_size,
dropout=opt.dropout[0] if type(opt.dropout) is list else opt.dropout,
word_padding_idx=word_padding_idx,
feat_padding_idx=feat_pad_indices,
word_vocab_size=num_word_embeddings,
feat_vocab_sizes=num_feat_embeddings,
sparse=opt.optim == "sparseadam",
fix_word_vecs=fix_word_vecs)
return emb
def build_embeddings(opt, text_field, for_encoder=True, aux_field=None):
"""
Args:
opt: the option in current environment.
text_field(TextMultiField): word and feats field.
for_encoder(bool): build Embeddings for encoder or decoder?
"""
emb_dim = opt.src_word_vec_size if for_encoder else opt.tgt_word_vec_size
if opt.model_type == "vec" and for_encoder:
return VecEmbedding(
opt.feat_vec_size,
emb_dim,
position_encoding=opt.position_encoding,
dropout=(opt.dropout[0]
if type(opt.dropout) is list else opt.dropout),
)
pad_indices = [f.vocab.stoi[f.pad_token] for _, f in text_field]
word_padding_idx, feat_pad_indices = pad_indices[0], pad_indices[1:]
def get_num_embs(field):
num_embs = [len(f.vocab) for _, f in field]
num_word_embeddings, num_feat_embeddings = num_embs[0], num_embs[1:]
return num_word_embeddings, num_feat_embeddings
num_word_embeddings, num_feat_embeddings = get_num_embs(text_field)
fix_word_vecs = opt.fix_word_vecs_enc if for_encoder \
else opt.fix_word_vecs_dec
if opt.crosslingual:
cls = XEmbeddings
word_vec_size = [emb_dim, emb_dim]
aux_num_word_embeddings, _ = get_num_embs(aux_field)
word_vocab_size = [num_word_embeddings, aux_num_word_embeddings]
else:
cls = Embeddings
word_vec_size = emb_dim
word_vec_size = num_word_embeddings
emb = cls(
word_vec_size,
word_vocab_size,
word_padding_idx,
position_encoding=opt.position_encoding,
feat_merge=opt.feat_merge,
feat_vec_exponent=opt.feat_vec_exponent,
feat_vec_size=opt.feat_vec_size,
dropout=opt.dropout[0] if type(opt.dropout) is list else opt.dropout,
feat_padding_idx=feat_pad_indices,
feat_vocab_sizes=num_feat_embeddings,
sparse=opt.optim == "sparseadam",
fix_word_vecs=fix_word_vecs)
return emb
def build_embeddings(opt, text_field, for_encoder=True):
"""
Args:
opt: the option in current environment.
text_field(TextMultiField): word and feats field.
for_encoder(bool): build Embeddings for encoder or decoder?
"""
if opt.is_bert:
token_fields_vocab = text_field.base_field.vocab
vocab_size = len(token_fields_vocab)
emb_dim = opt.word_vec_size
return BertEmbeddings(
vocab_size,
emb_dim,
dropout=(opt.dropout[0]
if type(opt.dropout) is list else opt.dropout))
emb_dim = opt.src_word_vec_size if for_encoder else opt.tgt_word_vec_size
if opt.model_type == "vec" and for_encoder:
return VecEmbedding(
opt.feat_vec_size,
emb_dim,
position_encoding=opt.position_encoding,
dropout=(opt.dropout[0]
if type(opt.dropout) is list else opt.dropout),
)
pad_indices = [f.vocab.stoi[f.pad_token] for _, f in text_field]
word_padding_idx, feat_pad_indices = pad_indices[0], pad_indices[1:]
num_embs = [len(f.vocab) for _, f in text_field]
num_word_embeddings, num_feat_embeddings = num_embs[0], num_embs[1:]
fix_word_vecs = opt.fix_word_vecs_enc if for_encoder \
else opt.fix_word_vecs_dec
emb = Embeddings(
word_vec_size=emb_dim,
position_encoding=opt.position_encoding,
feat_merge=opt.feat_merge,
feat_vec_exponent=opt.feat_vec_exponent,
feat_vec_size=opt.feat_vec_size,
dropout=opt.dropout[0] if type(opt.dropout) is list else opt.dropout,
word_padding_idx=word_padding_idx,
feat_padding_idx=feat_pad_indices,
word_vocab_size=num_word_embeddings,
feat_vocab_sizes=num_feat_embeddings,
sparse=opt.optim == "sparseadam",
fix_word_vecs=fix_word_vecs)
return emb
def build_embeddings(opt, text_field, for_encoder=True):
"""
Args:
opt: the option in current environment.
text_field(TextMultiField): word and feats field.
for_encoder(bool): build Embeddings for encoder or decoder?
"""
emb_dim = opt.src_word_vec_size if for_encoder else opt.tgt_word_vec_size
if opt.model_type == "vec" and for_encoder:
return VecEmbedding(
opt.feat_vec_size,
emb_dim,
position_encoding=opt.position_encoding,
dropout=(opt.dropout[0]
if type(opt.dropout) is list else opt.dropout),
)
pad_indices = [f.vocab.stoi[f.pad_token] for _, f in text_field]
word_padding_idx, feat_pad_indices = pad_indices[0], pad_indices[1:]
num_embs = [len(f.vocab) for _, f in text_field]
num_word_embeddings, num_feat_embeddings = num_embs[0], num_embs[1:]
fix_word_vecs = opt.fix_word_vecs_enc if for_encoder \
else opt.fix_word_vecs_dec
conmt = False
out_vec_size = None
if ("continuous" in opt.generator_function) and not for_encoder:
out_vec_size = text_field.base_field.vocab.vectors.size(1)
conmt = True
emb = Embeddings(
word_vec_size=emb_dim,
position_encoding=opt.position_encoding,
feat_merge=opt.feat_merge,
feat_vec_exponent=opt.feat_vec_exponent,
feat_vec_size=opt.feat_vec_size,
dropout=opt.dropout[0] if type(opt.dropout) is list else opt.dropout,
word_padding_idx=word_padding_idx,
feat_padding_idx=feat_pad_indices,
word_vocab_size=num_word_embeddings,
feat_vocab_sizes=num_feat_embeddings,
sparse=opt.optim == "sparseadam",
fix_word_vecs=fix_word_vecs,
tie_embeddings=opt.share_decoder_embeddings and conmt,
out_vec_size=out_vec_size)
return emb
