class TestBLEU(unittest.TestCase):
def setUp(self):
xnmt.events.clear()
self.hyp = ["the taro met the hanako".split()]
self.ref = ["taro met hanako".split()]
vocab = Vocab()
self.hyp_id = list(map(vocab.convert, self.hyp[0]))
self.ref_id = list(map(vocab.convert, self.ref[0]))
def test_bleu_1gram(self):
bleu = evaluator.BLEUEvaluator(ngram=1)
exp_bleu = 3.0 / 5.0
act_bleu = bleu.evaluate(self.ref, self.hyp).value()
self.assertEqual(act_bleu, exp_bleu)
@unittest.skipUnless(has_cython(), "requires cython to run")
def test_bleu_4gram_fast(self):
bleu = evaluator.FastBLEUEvaluator(ngram=4, smooth=1)
exp_bleu = math.exp(math.log((3.0/5.0) * (2.0/5.0) * (1.0/4.0) * (1.0/3.0))/4.0)
act_bleu = bleu.evaluate(self.ref_id, self.hyp_id)
self.assertEqual(act_bleu, exp_bleu)
class TestRunningConfig(unittest.TestCase):
def setUp(self):
xnmt.events.clear()
def test_assemble(self):
run.main(["test/config/assemble.yaml"])
def test_classifier(self):
run.main(["test/config/classifier.yaml"])
def test_component_sharing(self):
run.main(["test/config/component_sharing.yaml"])
def test_encoders(self):
run.main(["test/config/encoders.yaml"])
def test_ensembling(self):
run.main(["test/config/ensembling.yaml"])
def test_forced(self):
run.main(["test/config/forced.yaml"])
def test_lm(self):
run.main(["test/config/lm.yaml"])
def test_load_model(self):
run.main(["test/config/load_model.yaml"])
def test_multi_task(self):
run.main(["test/config/multi_task.yaml"])
def test_multi_task_speech(self):
run.main(["test/config/multi_task_speech.yaml"])
def test_preproc(self):
run.main(["test/config/preproc.yaml"])
def test_pretrained_emb(self):
run.main(["test/config/pretrained_embeddings.yaml"])
def test_random_search_test_params(self):
run.main(["test/config/random_search_test_params.yaml"])
def test_random_search_train_params(self):
run.main(["test/config/random_search_train_params.yaml"])
def test_reload(self):
run.main(["test/config/reload.yaml"])
def test_segmenting(self):
run.main(["test/config/seg_report.yaml"])
def test_reload_exception(self):
with self.assertRaises(ValueError) as context:
run.main(["test/config/reload_exception.yaml"])
self.assertEqual(str(context.exception), 'VanillaLSTMGates: x_t has inconsistent dimension')
def test_report(self):
run.main(["test/config/report.yaml"])
@unittest.expectedFailure # TODO: these tests need to be fixed
def test_retrieval(self):
run.main(["test/config/retrieval.yaml"])
def test_score(self):
run.main(["test/config/score.yaml"])
def test_self_attentional_am(self):
run.main(["test/config/self_attentional_am.yaml"])
def test_seq_labeler(self):
run.main(["test/config/seq_labeler.yaml"])
def test_speech(self):
run.main(["test/config/speech.yaml"])
@unittest.expectedFailure # TODO: these tests need to be fixed
def test_speech_retrieval(self):
run.main(["test/config/speech_retrieval.yaml"])
def test_standard(self):
run.main(["test/config/standard.yaml"])
@unittest.expectedFailure # TODO: these tests need to be fixed
def test_transformer(self):
run.main(["test/config/transformer.yaml"])
@unittest.skipUnless(has_cython(), "requires cython to run")
def test_search_strategy_reinforce(self):
run.main(["test/config/reinforce.yaml"])
@unittest.skipUnless(has_cython(), "requires cython to run")
def test_search_strategy_minrisk(self):
run.main(["test/config/minrisk.yaml"])
def tearDown(self):
try:
if os.path.isdir("test/tmp"):
shutil.rmtree("test/tmp")
except:
pass
class TestSegmentingEncoder(unittest.TestCase):
def setUp(self):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 64
xnmt.events.clear()
ParamManager.init_param_col()
self.segment_encoder_bilstm = BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim)
self.segment_composer = SumComposer()
self.src_reader = CharFromWordTextReader()
self.trg_reader = PlainTextReader()
self.loss_calculator = AutoRegressiveMLELoss()
baseline = Linear(input_dim=layer_dim, output_dim=1)
policy_network = Linear(input_dim=layer_dim, output_dim=2)
self.poisson_prior = PoissonPrior(mu=3.3)
self.eps_greedy = EpsilonGreedy(eps_prob=0.0, prior=self.poisson_prior)
self.conf_penalty = ConfidencePenalty()
self.policy_gradient = PolicyGradient(input_dim=layer_dim,
output_dim=2,
baseline=baseline,
policy_network=policy_network,
z_normalization=True,
conf_penalty=self.conf_penalty,
sample=5)
self.length_prior = PoissonLengthPrior(lmbd=3.3, weight=1)
self.segmenting_encoder = SegmentingSeqTransducer(
embed_encoder=self.segment_encoder_bilstm,
segment_composer=self.segment_composer,
final_transducer=BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
policy_learning=self.policy_gradient,
eps_greedy=self.eps_greedy,
length_prior=self.length_prior,
)
self.model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=self.segmenting_encoder,
attender=MlpAttender(input_dim=layer_dim,
state_dim=layer_dim,
hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(
input_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="decoder"),
transform=AuxNonLinear(input_dim=layer_dim,
output_dim=layer_dim,
aux_input_dim=layer_dim),
scorer=Softmax(vocab_size=100, input_dim=layer_dim),
trg_embed_dim=layer_dim,
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.model.set_train(True)
self.layer_dim = layer_dim
self.src_data = list(
self.model.src_reader.read_sents("examples/data/head.ja"))
self.trg_data = list(
self.model.trg_reader.read_sents("examples/data/head.en"))
my_batcher = xnmt.batcher.TrgBatcher(batch_size=3,
src_pad_token=1,
trg_pad_token=2)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)
def test_reinforce_loss(self):
self.model.global_fertility = 1.0
loss = self.model.calc_loss(self.src[0], self.trg[0],
AutoRegressiveMLELoss())
reinforce_loss = self.model.calc_additional_loss(
self.trg[0], self.model, loss)
pl = self.model.encoder.policy_learning
# Ensure correct length
src = self.src[0]
mask = src.mask.np_arr
outputs = self.segmenting_encoder.compose_output
actions = self.segmenting_encoder.segment_actions
# Ensure sample == outputs
self.assertEqual(len(outputs), pl.sample)
self.assertEqual(len(actions), pl.sample)
for sample_action in actions:
for i, sample_item in enumerate(sample_action):
# The last segmentation is 1
self.assertEqual(sample_item[-1], src[i].len_unpadded())
# Assert that all flagged actions are </s>
list(
self.assertEqual(pl.actions[j][0][i], 1)
for j in range(len(mask[i])) if mask[i][j] == 1)
self.assertTrue("mle" in loss.expr_factors)
self.assertTrue("fertility" in loss.expr_factors)
self.assertTrue("rl_reinf" in reinforce_loss.expr_factors)
self.assertTrue("rl_baseline" in reinforce_loss.expr_factors)
self.assertTrue("rl_confpen" in reinforce_loss.expr_factors)
# Ensure we are sampling from the policy learning
self.assertEqual(self.model.encoder.segmenting_action,
SegmentingSeqTransducer.SegmentingAction.POLICY)
def calc_loss_single_batch(self):
loss = self.model.calc_loss(self.src[0], self.trg[0],
AutoRegressiveMLELoss())
reinforce_loss = self.model.calc_additional_loss(
self.trg[0], self.model, loss)
return loss, reinforce_loss
def test_gold_input(self):
self.model.encoder.policy_learning = None
self.model.encoder.eps_greedy = None
self.calc_loss_single_batch()
self.assertEqual(self.model.encoder.segmenting_action,
SegmentingSeqTransducer.SegmentingAction.GOLD)
@unittest.skipUnless(has_cython(), "requires cython to run")
def test_sample_input(self):
self.model.encoder.eps_greedy.eps_prob = 1.0
self.calc_loss_single_batch()
self.assertEqual(
self.model.encoder.segmenting_action,
SegmentingSeqTransducer.SegmentingAction.POLICY_SAMPLE)
self.assertEqual(self.model.encoder.policy_learning.sampling_action,
PolicyGradient.SamplingAction.PREDEFINED)
def test_global_fertility(self):
# Test Global fertility weight
self.model.global_fertility = 1.0
self.segmenting_encoder.policy_learning = None
loss1, _ = self.calc_loss_single_batch()
self.assertTrue("fertility" in loss1.expr_factors)
def test_policy_train_test(self):
self.model.set_train(True)
self.calc_loss_single_batch()
self.assertEqual(self.model.encoder.policy_learning.sampling_action,
PolicyGradient.SamplingAction.POLICY_CLP)
self.model.set_train(False)
self.calc_loss_single_batch()
self.assertEqual(self.model.encoder.policy_learning.sampling_action,
PolicyGradient.SamplingAction.POLICY_AMAX)
def test_no_policy_train_test(self):
self.model.encoder.policy_learning = None
self.model.set_train(True)
self.calc_loss_single_batch()
self.assertEqual(self.model.encoder.segmenting_action,
SegmentingSeqTransducer.SegmentingAction.PURE_SAMPLE)
self.model.set_train(False)
self.calc_loss_single_batch()
self.assertEqual(self.model.encoder.segmenting_action,
SegmentingSeqTransducer.SegmentingAction.PURE_SAMPLE)
def test_sample_during_search(self):
self.model.set_train(False)
self.model.encoder.sample_during_search = True
self.calc_loss_single_batch()
self.assertEqual(self.model.encoder.segmenting_action,
SegmentingSeqTransducer.SegmentingAction.POLICY)
@unittest.skipUnless(has_cython(), "requires cython to run")
def test_policy_gold(self):
self.model.encoder.eps_greedy.prior = GoldInputPrior("segment")
self.model.encoder.eps_greedy.eps_prob = 1.0
self.calc_loss_single_batch()