def test_feature_extraction_d2_2():
global test_sent, gold, word_to_ix, vocab
torch.manual_seed(1)
feat_extractor = SimpleFeatureExtractor()
embedder = VanillaWordEmbedding(word_to_ix, TEST_EMBEDDING_DIM)
combiner = DummyCombiner()
embeds = embedder(test_sent)
state = ParserState(test_sent, embeds, combiner)
state.shift()
feats = feat_extractor.get_features(state)
feats_list = make_list(feats)
true = ([
-1.0276086330413818, -0.563052773475647, -0.8922905325889587,
-0.05825017765164375
], [
-0.4211951494216919, -0.510699987411499, -1.5726652145385742,
-0.12324775755405426
], [
3.586989402770996, -1.8312901258468628, 1.5987002849578857,
-1.277006983757019
])
pairs = zip(feats_list, true)
check_tensor_correctness(pairs)
def build_parser(DROPOUT, LSTM_NUM_LAYERS, word_to_ix, pretrained_embeds):
# Predef
TEST_EMBEDDING_DIM = 4
WORD_EMBEDDING_DIM = 64
STACK_EMBEDDING_DIM = 100
NUM_FEATURES = 3
# Build Model
feat_extractor = SimpleFeatureExtractor()
# BiLSTM word embeddings will probably work best, but feel free to experiment with the others you developed
word_embedding_lookup = BiLSTMWordEmbedding(word_to_ix,
WORD_EMBEDDING_DIM,
STACK_EMBEDDING_DIM,
num_layers=LSTM_NUM_LAYERS,
dropout=DROPOUT)
initialize_with_pretrained(pretrained_embeds, word_embedding_lookup)
action_chooser = LSTMActionChooser(STACK_EMBEDDING_DIM * NUM_FEATURES,
LSTM_NUM_LAYERS,
dropout=DROPOUT)
combiner = LSTMCombiner(STACK_EMBEDDING_DIM,
num_layers=LSTM_NUM_LAYERS,
dropout=DROPOUT)
parser = TransitionParser(feat_extractor, word_embedding_lookup,
action_chooser, combiner)
return parser
def test_feature_extraction_d2_2():
global test_sent, gold, word_to_ix, vocab
torch.manual_seed(1)
feat_extractor = SimpleFeatureExtractor()
embedder = VanillaWordEmbedding(word_to_ix, TEST_EMBEDDING_DIM)
combiner = DummyCombiner()
embeds = embedder(test_sent)
state = ParserState(test_sent, embeds, combiner)
state.shift()
feats = feat_extractor.get_features(state)
feats_list = make_list(feats)
true = ([-1.0276086330413818, -0.563052773475647, -0.8922905325889587, -0.05825017765164375],
[-0.4211951494216919, -0.510699987411499, -1.5726652145385742, -0.12324775755405426],
[3.586989402770996, -1.8312901258468628, 1.5987002849578857, -1.277006983757019])
pairs = zip(feats_list, true)
check_tensor_correctness(pairs)
def test_feature_extraction_d2_2():
""" 0.5 point(s) """
global test_sent, gold, word_to_ix, vocab
torch.manual_seed(1)
feat_extractor = SimpleFeatureExtractor()
embedder = VanillaWordEmbeddingLookup(word_to_ix, TEST_EMBEDDING_DIM)
combiner = DummyCombiner()
embeds = embedder(test_sent)
state = ParserState(test_sent, embeds, combiner)
state.shift()
state.shift()
feats = feat_extractor.get_features(state)
feats_list = make_list(feats)
true = ([ -1.8661, 1.4146, -1.8781, -0.4674 ], [ -0.9596, 0.5489, -0.9901, -0.3826 ], [ 0.5237, 0.0004, -1.2039, 3.5283 ])
pairs = zip(feats_list, true)
check_tensor_correctness(pairs)
def test_predict_after_train_d3_1():
""" 1 point(s) """
global test_sent, gold, word_to_ix, vocab
torch.manual_seed(1)
feat_extract = SimpleFeatureExtractor()
word_embed = VanillaWordEmbeddingLookup(word_to_ix, TEST_EMBEDDING_DIM)
act_chooser = ActionChooserNetwork(TEST_EMBEDDING_DIM * NUM_FEATURES)
combiner = MLPCombinerNetwork(TEST_EMBEDDING_DIM)
parser = TransitionParser(feat_extract, word_embed, act_chooser, combiner)
# Train
for i in xrange(75):
train([ (test_sent[:-1], gold) ], parser, optim.SGD(parser.parameters(), lr=0.01), verbose=False)
# predict
pred = parser.predict(test_sent[:-1])
gold_graph = dependency_graph_from_oracle(test_sent[:-1], gold)
assert pred == gold_graph
def test_parse_logic_d3_1():
global test_sent, gold, word_to_ix, vocab
torch.manual_seed(1)
feat_extract = SimpleFeatureExtractor()
word_embed = VanillaWordEmbedding(word_to_ix, TEST_EMBEDDING_DIM)
act_chooser = FFActionChooser(TEST_EMBEDDING_DIM * NUM_FEATURES)
combiner = FFCombiner(TEST_EMBEDDING_DIM)
parser = TransitionParser(feat_extract, word_embed, act_chooser, combiner)
output, dep_graph, actions_done = parser(test_sent[:-1], gold)
assert len(output) == 16 # Made the right number of decisions
# check one of the outputs
checked_out = output[9].view(-1).data.tolist()
true_out = [-1.2444578409194946, -1.3128550052642822, -0.8145193457603455]
check_tensor_correctness([(true_out, checked_out)])
true_dep_graph = dependency_graph_from_oracle(test_sent, gold)
assert true_dep_graph == dep_graph
assert actions_done == [0, 1, 0, 1, 0, 0, 1, 2, 0, 0, 0, 1, 2, 2, 2, 0]
def test_parse_logic_d3_1():
""" 0.5 point(s) """
global test_sent, gold, word_to_ix, vocab
torch.manual_seed(1)
feat_extract = SimpleFeatureExtractor()
word_embed = VanillaWordEmbeddingLookup(word_to_ix, TEST_EMBEDDING_DIM)
act_chooser = ActionChooserNetwork(TEST_EMBEDDING_DIM * NUM_FEATURES)
combiner = MLPCombinerNetwork(TEST_EMBEDDING_DIM)
parser = TransitionParser(feat_extract, word_embed, act_chooser, combiner)
output, dep_graph, actions_done = parser(test_sent[:-1], gold)
assert len(output) == 15 # Made the right number of decisions
# check one of the outputs
checked_out = output[10].view(-1).data.tolist()
true_out = [-1.4737, -1.0875, -0.8350]
check_tensor_correctness([(true_out, checked_out)])
true_dep_graph = dependency_graph_from_oracle(test_sent, gold)
assert true_dep_graph == dep_graph
assert actions_done == [0, 0, 1, 0, 1, 0, 0, 1, 2, 0, 0, 0, 1, 1, 2]