help="Embedding dimension")
parser.add_argument("--normalize_embeddings",
type=str,
default="",
help="Normalize embeddings before training")
# parse parameters
params = parser.parse_args()
# check parameters
assert params.src_lang, "source language undefined"
assert os.path.isfile(params.src_emb)
assert not params.tgt_lang or os.path.isfile(params.tgt_emb)
assert params.dico_eval == 'default' or os.path.isfile(params.dico_eval)
# build logger / model / trainer / evaluator
logger = initialize_exp(params)
src_emb, tgt_emb, mapping, _ = build_model(params, False)
trainer = Trainer(src_emb, tgt_emb, mapping, None, params)
evaluator = Evaluator(trainer)
# run evaluations
to_log = OrderedDict({'n_iter': 0})
evaluator.monolingual_wordsim(to_log)
# evaluator.monolingual_wordanalogy(to_log)
if params.tgt_lang:
evaluator.crosslingual_wordsim(to_log)
evaluator.word_translation(to_log)
evaluator.sent_translation(to_log)
# evaluator.dist_mean_cosine(to_log)
parser.add_argument("--src_emb", type=str, default="data/fastText/wiki.en.vec", help="Reload source embeddings")
parser.add_argument("--tgt_emb", type=str, default="data/fastText/wiki.it.vec", help="Reload target embeddings")
parser.add_argument("--max_vocab", type=int, default=200000, help="Maximum vocabulary size (-1 to disable)")
parser.add_argument("--emb_dim", type=int, default=300, help="Embedding dimension")
parser.add_argument("--normalize_embeddings", type=str, default="renorm", help="Normalize embeddings before training")
parser.add_argument("--alpha", type=float, default=0.23, help="Reload the hyper-param alpha")
parser.add_argument("--inv_K", type=int, default=4, help="Reload the hyper-param inv_K")
# parse parameters
params = parser.parse_args()
# check parameters
assert params.src_lang, "source language undefined"
assert os.path.isfile(params.src_emb)
assert not params.tgt_lang or os.path.isfile(params.tgt_emb)
assert params.dico_eval == 'default' or os.path.isfile(params.dico_eval)
# build logger / model / trainer / evaluator
logger = initialize_exp(params)
src_emb, tgt_emb, mapping, _ = build_model(params, False)
trainer = Trainer(src_emb, tgt_emb, mapping, None, params)
evaluator = Evaluator(trainer)
# run evaluations
to_log = OrderedDict({'n_iter': 0})
if params.tgt_lang:
evaluator.crosslingual_wordsim(to_log, 'row')
evaluator.word_translation(to_log, 'row')
evaluator.dist_mean_cosine(to_log, 'row')
# reload pre-trained embeddings
parser.add_argument("--src_emb", type=str, default="", help="Reload source embeddings")
parser.add_argument("--tgt_emb", type=str, default="", help="Reload target embeddings")
parser.add_argument("--max_vocab", type=int, default=200000, help="Maximum vocabulary size")
parser.add_argument("--emb_dim", type=int, default=300, help="Embedding dimension")
parser.add_argument("--normalize_embeddings", type=str, default="", help="Normalize embeddings before training")
# parse parameters
params = parser.parse_args()
# check parameters
assert params.src_lang, "source language undefined"
assert os.path.isfile(params.src_emb)
assert not params.tgt_lang or os.path.isfile(params.tgt_emb)
# build logger / model / trainer / evaluator
logger = initialize_exp(params)
src_emb, tgt_emb, mapping, _ = build_model(params, False)
trainer = Trainer(src_emb, tgt_emb, mapping, None, params)
evaluator = Evaluator(trainer)
# run evaluations
to_log = OrderedDict({'n_iter': 0})
evaluator.monolingual_wordsim(to_log)
if params.tgt_lang:
evaluator.crosslingual_wordsim(to_log)
evaluator.word_translation(to_log)
evaluator.sent_translation(to_log)
# evaluator.dist_mean_cosine(to_log)
params.eval_pairs.append(f'{lang1}-{lang2}')
# check parameters
assert len(params.src_langs) > 0, "source language undefined"
assert all([os.path.isfile(emb) for emb in params.src_embs])
assert not params.tgt_lang or os.path.isfile(params.tgt_emb)
assert params.dico_eval == 'default' or os.path.isfile(params.dico_eval)
# build logger / model / trainer / evaluator
logger = initialize_exp(params, dump_params=False, log_name='evaluate.log')
embs, mappings, _ = build_model(params, False)
trainer = Trainer(embs, mappings, None, params)
trainer.reload_best()
evaluator = Evaluator(trainer)
# run evaluations
to_log = OrderedDict({'n_iter': 0})
all_wt = []
evaluator.monolingual_wordsim(to_log)
for eval_pair in params.eval_pairs:
parts = eval_pair.split('-')
assert len(parts) == 2, 'Invalid format for evaluation pairs.'
src_lang, tgt_lang = parts[0], parts[1]
logger.info(f'Evaluating language pair: {src_lang} - {tgt_lang}')
evaluator.crosslingual_wordsim(to_log, src_lang=src_lang, tgt_lang=tgt_lang)
evaluator.word_translation(to_log, src_lang=src_lang, tgt_lang=tgt_lang)
all_wt.append(to_log[f'{src_lang}-{tgt_lang}_precision_at_1-csls_knn_10'])
evaluator.sent_translation(to_log, src_lang=src_lang, tgt_lang=tgt_lang)
logger.info(f"Overall Word Translation Precision@1 over {len(all_wt)} language pairs: {sum(all_wt)/len(all_wt)}")