def load_linear_maps():
zmap_basic = torch_load(fewshot_filename(DATADIR+"/maps", "Zmap_20k_w2v_words_alpha0.pt"))
zmap_optimized = torch_load(fewshot_filename(DATADIR+"/maps", "Zmap_20k_w2v_words_alpha10_news.pt"))
wmap = torch_load(fewshot_filename(DATADIR+"/maps", "Wmap_agnews_lr0.1_lam500_500expercat.pt"))
MAPPINGS = {
'Zmap (standard)': zmap_basic,
'Zmap (optimized for AG News)' : zmap_optimized,
'Wmap (trained on 2000 AG News examples)': wmap
}
return MAPPINGS
def test_on_the_fly(self):
# Test should only be run if the necessary files already exist.
self._assert_files_exist()
# Load dataset
dataset = load_or_cache_data(DATADIR, DATASET_NAME)
# Load w2v embeddings
w2v_model = load_word_vector_model(small=True, cache_dir=W2VDIR)
vocab_w2v_embeddings, vocab = get_topk_w2v_vectors(w2v_model, k=VOCAB_SIZE)
vocab_w2v_embeddings = to_tensor(vocab_w2v_embeddings)
# Load SBERT embeddings
vocab_sbert_filename = fewshot_filename(
W2VDIR, f"sbert_embeddings_for_{VOCAB_SIZE}_words.pt"
)
cached_data = torch_load(vocab_sbert_filename)
vocab_sbert_embeddings = cached_data["embeddings"]
# Calculate linear map of best fit between maps.
Zmap = OLS_with_l2_regularization(
vocab_sbert_embeddings, vocab_w2v_embeddings
)
# Predict and score
score, predictions = predict_and_score(dataset, linear_maps=[Zmap], return_predictions=True)
score3 = simple_topk_accuracy(dataset.labels, predictions)
self.assertAlmostEqual(score, 65.5657894736842)
self.assertAlmostEqual(score3, 96.01315789473685)
VOCAB_SIZE = 20000
import pdb
pdb.set_trace()
# We found that using a vocabulary size of 20,000 words is good for most applications
vocab_w2v_embeddings, vocab = get_topk_w2v_vectors(w2v_model, k=VOCAB_SIZE)
vocab_w2v_embeddings = to_tensor(vocab_w2v_embeddings)
# Passing 20k words through SBERT can be time-consuming, even with a GPU.
# Fortunately, we've already performed this step and include precomputed embeddings.
vocab_sbert_filename = fewshot_filename(
W2VDIR, f"sbert_embeddings_for_{VOCAB_SIZE}_words.pt")
if os.path.exists(vocab_sbert_filename):
cached_data = torch_load(vocab_sbert_filename)
vocab_sbert_embeddings = cached_data["embeddings"]
else:
model, tokenizer = load_transformer_model_and_tokenizer()
vocab_sbert_embeddings = get_transformer_embeddings(
vocab, model, tokenizer, output_filename=vocab_sbert_filename)
# Perform ordinary least-squares linear regression to learn Zmap
Zmap = OLS_with_l2_regularization(vocab_sbert_embeddings, vocab_w2v_embeddings)
score, predictions = predict_and_score(dataset,
linear_maps=[Zmap],
return_predictions=True)
score3 = simple_topk_accuracy(dataset.labels, predictions)
print(
f"Score using projection matrix with top {VOCAB_SIZE} w2v words: {score}")