Merge pull request #102 from lcy-seso/refine_ner

refine NER.

sequence_tagging_for_ner/.gitignore

+*.pyc
+*.tar.gz

sequence_tagging_for_ner/data/download.sh

 wget http://cs224d.stanford.edu/assignment2/assignment2.zip
-unzip assignment2.zip
-cp assignment2_release/data/ner/wordVectors.txt data/
-cp assignment2_release/data/ner/vocab.txt data/
-rm -rf assignment2.zip assignment2_release
+
+if [ $? -eq 0  ];then
+    unzip assignment2.zip
+    cp assignment2_release/data/ner/wordVectors.txt ./data
+    cp assignment2_release/data/ner/vocab.txt ./data
+    rm -rf assignment2.zip assignment2_release
+else
+  echo "download data error!" >> /dev/stderr
+  exit 1
+fi
 

sequence_tagging_for_ner/data/test

--DOCSTART- -X- O O
-
 CRICKET NNP I-NP O
 - : O O
 LEICESTERSHIRE NNP I-NP I-ORG

sequence_tagging_for_ner/data/train

--DOCSTART- -X- O O
-
 EU NNP I-NP I-ORG
 rejects VBZ I-VP O
 German JJ I-NP I-MISC

sequence_tagging_for_ner/infer.py

+import gzip
+
+import reader
+from network_conf import *
+from utils import *
+
+
+def infer(model_path, batch_size, test_data_file, vocab_file, target_file):
+    def _infer_a_batch(inferer, test_data, id_2_word, id_2_label):
+        probs = inferer.infer(input=test_data, field=["id"])
+        assert len(probs) == sum(len(x[0]) for x in test_data)
+
+        for idx, test_sample in enumerate(test_data):
+            start_id = 0
+            for w, tag in zip(test_sample[0],
+                              probs[start_id:start_id + len(test_sample[0])]):
+                print("%s\t%s" % (id_2_word[w], id_2_label[tag]))
+            print("\n")
+            start_id += len(test_sample[0])
+
+    word_dict = load_dict(vocab_file)
+    word_dict_len = len(word_dict)
+    word_reverse_dict = load_reverse_dict(vocab_file)
+
+    label_dict = load_dict(target_file)
+    label_reverse_dict = load_reverse_dict(target_file)
+    label_dict_len = len(label_dict)
+
+    # initialize PaddlePaddle
+    paddle.init(use_gpu=False, trainer_count=1)
+    parameters = paddle.parameters.Parameters.from_tar(
+        gzip.open(model_path, "r"))
+
+    predict = ner_net(
+        word_dict_len=word_dict_len,
+        label_dict_len=label_dict_len,
+        is_train=False)
+
+    inferer = paddle.inference.Inference(
+        output_layer=predict, parameters=parameters)
+
+    test_data = []
+    for i, item in enumerate(
+            reader.data_reader(test_data_file, word_dict, label_dict)()):
+        test_data.append([item[0], item[1]])
+        if len(test_data) == batch_size:
+            _infer_a_batch(inferer, test_data, word_reverse_dict,
+                           label_reverse_dict)
+            test_data = []
+
+    _infer_a_batch(inferer, test_data, word_reverse_dict, label_reverse_dict)
+    test_data = []
+
+
+if __name__ == "__main__":
+    infer(
+        model_path="models/params_pass_0.tar.gz",
+        batch_size=2,
+        test_data_file="data/test",
+        vocab_file="data/vocab.txt",
+        target_file="data/target.txt")

sequence_tagging_for_ner/ner.py

-import math
-import gzip
-import paddle.v2 as paddle
-import paddle.v2.evaluator as evaluator
-import conll03
-import itertools
-
-# init dataset
-train_data_file = 'data/train'
-test_data_file = 'data/test'
-vocab_file = 'data/vocab.txt'
-target_file = 'data/target.txt'
-emb_file = 'data/wordVectors.txt'
-
-train_data_reader = conll03.train(train_data_file, vocab_file, target_file)
-test_data_reader = conll03.test(test_data_file, vocab_file, target_file)
-word_dict, label_dict = conll03.get_dict(vocab_file, target_file)
-word_vector_values = conll03.get_embedding(emb_file)
-
-# init hyper-params
-word_dict_len = len(word_dict)
-label_dict_len = len(label_dict)
-mark_dict_len = 2
-word_dim = 50
-mark_dim = 5
-hidden_dim = 300
-
-mix_hidden_lr = 1e-3
-default_std = 1 / math.sqrt(hidden_dim) / 3.0
-emb_para = paddle.attr.Param(
-    name='emb', initial_std=math.sqrt(1. / word_dim), is_static=True)
-std_0 = paddle.attr.Param(initial_std=0.)
-std_default = paddle.attr.Param(initial_std=default_std)
-
-
-def d_type(size):
-    return paddle.data_type.integer_value_sequence(size)
-
-
-def ner_net(is_train):
-    word = paddle.layer.data(name='word', type=d_type(word_dict_len))
-    mark = paddle.layer.data(name='mark', type=d_type(mark_dict_len))
-
-    word_embedding = paddle.layer.mixed(
-        name='word_embedding',
-        size=word_dim,
-        input=paddle.layer.table_projection(input=word, param_attr=emb_para))
-    mark_embedding = paddle.layer.mixed(
-        name='mark_embedding',
-        size=mark_dim,
-        input=paddle.layer.table_projection(input=mark, param_attr=std_0))
-    emb_layers = [word_embedding, mark_embedding]
-
-    word_caps_vector = paddle.layer.concat(
-        name='word_caps_vector', input=emb_layers)
-    hidden_1 = paddle.layer.mixed(
-        name='hidden1',
-        size=hidden_dim,
-        act=paddle.activation.Tanh(),
-        bias_attr=std_default,
-        input=[
-            paddle.layer.full_matrix_projection(
-                input=word_caps_vector, param_attr=std_default)
-        ])
-
-    rnn_para_attr = paddle.attr.Param(initial_std=0.0, learning_rate=0.1)
-    hidden_para_attr = paddle.attr.Param(
-        initial_std=default_std, learning_rate=mix_hidden_lr)
-
-    rnn_1_1 = paddle.layer.recurrent(
-        name='rnn1-1',
-        input=hidden_1,
-        act=paddle.activation.Relu(),
-        bias_attr=std_0,
-        param_attr=rnn_para_attr)
-    rnn_1_2 = paddle.layer.recurrent(
-        name='rnn1-2',
-        input=hidden_1,
-        act=paddle.activation.Relu(),
-        reverse=1,
-        bias_attr=std_0,
-        param_attr=rnn_para_attr)
-
-    hidden_2_1 = paddle.layer.mixed(
-        name='hidden2-1',
-        size=hidden_dim,
-        bias_attr=std_default,
-        act=paddle.activation.STanh(),
-        input=[
-            paddle.layer.full_matrix_projection(
-                input=hidden_1, param_attr=hidden_para_attr),
-            paddle.layer.full_matrix_projection(
-                input=rnn_1_1, param_attr=rnn_para_attr)
-        ])
-    hidden_2_2 = paddle.layer.mixed(
-        name='hidden2-2',
-        size=hidden_dim,
-        bias_attr=std_default,
-        act=paddle.activation.STanh(),
-        input=[
-            paddle.layer.full_matrix_projection(
-                input=hidden_1, param_attr=hidden_para_attr),
-            paddle.layer.full_matrix_projection(
-                input=rnn_1_2, param_attr=rnn_para_attr)
-        ])
-
-    rnn_2_1 = paddle.layer.recurrent(
-        name='rnn2-1',
-        input=hidden_2_1,
-        act=paddle.activation.Relu(),
-        reverse=1,
-        bias_attr=std_0,
-        param_attr=rnn_para_attr)
-    rnn_2_2 = paddle.layer.recurrent(
-        name='rnn2-2',
-        input=hidden_2_2,
-        act=paddle.activation.Relu(),
-        bias_attr=std_0,
-        param_attr=rnn_para_attr)
-
-    hidden_3 = paddle.layer.mixed(
-        name='hidden3',
-        size=hidden_dim,
-        bias_attr=std_default,
-        act=paddle.activation.STanh(),
-        input=[
-            paddle.layer.full_matrix_projection(
-                input=hidden_2_1, param_attr=hidden_para_attr),
-            paddle.layer.full_matrix_projection(
-                input=rnn_2_1,
-                param_attr=rnn_para_attr), paddle.layer.full_matrix_projection(
-                    input=hidden_2_2, param_attr=hidden_para_attr),
-            paddle.layer.full_matrix_projection(
-                input=rnn_2_2, param_attr=rnn_para_attr)
-        ])
-
-    output = paddle.layer.mixed(
-        name='output',
-        size=label_dict_len,
-        bias_attr=False,
-        input=[
-            paddle.layer.full_matrix_projection(
-                input=hidden_3, param_attr=std_default)
-        ])
-
-    if is_train:
-        target = paddle.layer.data(name='target', type=d_type(label_dict_len))
-
-        crf_cost = paddle.layer.crf(
-            size=label_dict_len,
-            input=output,
-            label=target,
-            param_attr=paddle.attr.Param(
-                name='crfw',
-                initial_std=default_std,
-                learning_rate=mix_hidden_lr))
-
-        crf_dec = paddle.layer.crf_decoding(
-            size=label_dict_len,
-            input=output,
-            label=target,
-            param_attr=paddle.attr.Param(name='crfw'))
-
-        return crf_cost, crf_dec, target
-    else:
-        predict = paddle.layer.crf_decoding(
-            size=label_dict_len,
-            input=output,
-            param_attr=paddle.attr.Param(name='crfw'))
-
-        return predict
-
-
-def ner_net_train(data_reader=train_data_reader, num_passes=1):
-    # define network topology
-    crf_cost, crf_dec, target = ner_net(is_train=True)
-    evaluator.sum(name='error', input=crf_dec)
-    evaluator.chunk(
-        name='ner_chunk',
-        input=crf_dec,
-        label=target,
-        chunk_scheme='IOB',
-        num_chunk_types=(label_dict_len - 1) / 2)
-
-    # create parameters
-    parameters = paddle.parameters.create(crf_cost)
-    parameters.set('emb', word_vector_values)
-
-    # create optimizer
-    optimizer = paddle.optimizer.Momentum(
-        momentum=0,
-        learning_rate=2e-4,
-        regularization=paddle.optimizer.L2Regularization(rate=8e-4),
-        gradient_clipping_threshold=25,
-        model_average=paddle.optimizer.ModelAverage(
-            average_window=0.5, max_average_window=10000), )
-
-    trainer = paddle.trainer.SGD(
-        cost=crf_cost,
-        parameters=parameters,
-        update_equation=optimizer,
-        extra_layers=crf_dec)
-
-    reader = paddle.batch(
-        paddle.reader.shuffle(data_reader, buf_size=8192), batch_size=64)
-
-    feeding = {'word': 0, 'mark': 1, 'target': 2}
-
-    def event_handler(event):
-        if isinstance(event, paddle.event.EndIteration):
-            if event.batch_id % 100 == 0:
-                print "Pass %d, Batch %d, Cost %f, %s" % (
-                    event.pass_id, event.batch_id, event.cost, event.metrics)
-            if event.batch_id % 1000 == 0:
-                result = trainer.test(reader=reader, feeding=feeding)
-                print "\nTest with Pass %d, Batch %d, %s" % (
-                    event.pass_id, event.batch_id, result.metrics)
-
-        if isinstance(event, paddle.event.EndPass):
-            # save parameters
-            with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
-                parameters.to_tar(f)
-            result = trainer.test(reader=reader, feeding=feeding)
-            print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
-
-    trainer.train(
-        reader=reader,
-        event_handler=event_handler,
-        num_passes=num_passes,
-        feeding=feeding)
-
-    return parameters
-
-
-def ner_net_infer(data_reader=test_data_reader, model_file='ner_model.tar.gz'):
-    test_data = []
-    test_sentences = []
-    for item in data_reader():
-        test_data.append([item[0], item[1]])
-        test_sentences.append(item[-1])
-        if len(test_data) == 10:
-            break
-
-    predict = ner_net(is_train=False)
-
-    lab_ids = paddle.infer(
-        output_layer=predict,
-        parameters=paddle.parameters.Parameters.from_tar(gzip.open(model_file)),
-        input=test_data,
-        field='id')
-
-    flat_data = [word for word in itertools.chain.from_iterable(test_sentences)]
-
-    labels_reverse = {}
-    for (k, v) in label_dict.items():
-        labels_reverse[v] = k
-    pre_lab = [labels_reverse[lab_id] for lab_id in lab_ids]
-
-    for word, label in zip(flat_data, pre_lab):
-        print word, label
-
-
-if __name__ == '__main__':
-    paddle.init(use_gpu=False, trainer_count=1)
-    ner_net_train(data_reader=train_data_reader, num_passes=1)
-    ner_net_infer(
-        data_reader=test_data_reader, model_file='params_pass_0.tar.gz')

sequence_tagging_for_ner/network_conf.py

+import math
+
+import paddle.v2 as paddle
+import paddle.v2.evaluator as evaluator
+
+
+def ner_net(word_dict_len, label_dict_len, stack_num=2, is_train=True):
+    mark_dict_len = 2
+    word_dim = 50
+    mark_dim = 5
+    hidden_dim = 128
+
+    word = paddle.layer.data(
+        name='word',
+        type=paddle.data_type.integer_value_sequence(word_dict_len))
+    word_embedding = paddle.layer.embedding(
+        input=word,
+        size=word_dim,
+        param_attr=paddle.attr.Param(
+            name='emb', initial_std=math.sqrt(1. / word_dim), is_static=True))
+
+    mark = paddle.layer.data(
+        name='mark',
+        type=paddle.data_type.integer_value_sequence(mark_dict_len))
+    mark_embedding = paddle.layer.embedding(
+        input=mark,
+        size=mark_dim,
+        param_attr=paddle.attr.Param(initial_std=math.sqrt(1. / word_dim)))
+
+    word_caps_vector = paddle.layer.concat(
+        input=[word_embedding, mark_embedding])
+
+    mix_hidden_lr = 1e-3
+    rnn_para_attr = paddle.attr.Param(initial_std=0.0, learning_rate=0.1)
+    hidden_para_attr = paddle.attr.Param(
+        initial_std=1 / math.sqrt(hidden_dim), learning_rate=mix_hidden_lr)
+
+    # the first rnn layer shares the input-to-hidden mappings.
+    hidden = paddle.layer.fc(
+        name="__hidden00__",
+        size=hidden_dim,
+        act=paddle.activation.Tanh(),
+        bias_attr=paddle.attr.Param(initial_std=1.),
+        input=word_caps_vector,
+        param_attr=hidden_para_attr)
+
+    fea = []
+    for direction in ["fwd", "bwd"]:
+        for i in range(stack_num):
+            if i:
+                hidden = paddle.layer.fc(
+                    name="__hidden%02d_%s__" % (i, direction),
+                    size=hidden_dim,
+                    act=paddle.activation.STanh(),
+                    bias_attr=paddle.attr.Param(initial_std=1.),
+                    input=[hidden, rnn],
+                    param_attr=[hidden_para_attr, rnn_para_attr])
+
+            rnn = paddle.layer.recurrent(
+                name="__rnn%02d_%s__" % (i, direction),
+                input=hidden,
+                act=paddle.activation.Relu(),
+                bias_attr=paddle.attr.Param(initial_std=1.),
+                reverse=i % 2 if direction == "fwd" else not i % 2,
+                param_attr=rnn_para_attr)
+        fea += [hidden, rnn]
+
+    rnn_fea = paddle.layer.fc(
+        size=hidden_dim,
+        bias_attr=paddle.attr.Param(initial_std=1.),
+        act=paddle.activation.STanh(),
+        input=fea,
+        param_attr=[hidden_para_attr, rnn_para_attr] * 2)
+
+    emission = paddle.layer.fc(
+        size=label_dict_len,
+        bias_attr=False,
+        input=rnn_fea,
+        param_attr=rnn_para_attr)
+
+    if is_train:
+        target = paddle.layer.data(
+            name='target',
+            type=paddle.data_type.integer_value_sequence(label_dict_len))
+
+        crf = paddle.layer.crf(
+            size=label_dict_len,
+            input=emission,
+            label=target,
+            param_attr=paddle.attr.Param(name='crfw', initial_std=1e-3))
+
+        crf_dec = paddle.layer.crf_decoding(
+            size=label_dict_len,
+            input=emission,
+            label=target,
+            param_attr=paddle.attr.Param(name='crfw'))
+        return crf, crf_dec, target
+    else:
+        predict = paddle.layer.crf_decoding(
+            size=label_dict_len,
+            input=emission,
+            param_attr=paddle.attr.Param(name='crfw'))
+        return predict

sequence_tagging_for_ner/conll03.py → sequence_tagging_for_ner/reader.py

@@ -2,16 +2,9 @@
 Conll03 dataset.
 """
 
-import tarfile
-import gzip
-import itertools
-import collections
-import re
-import numpy as np
+from utils import *
 
-__all__ = ['train', 'test', 'get_dict', 'get_embedding']
-
-UNK_IDX = 0
+__all__ = ["data_reader"]
 
 
 def canonicalize_digits(word):
@@ -28,96 +21,46 @@ def canonicalize_word(word, wordset=None, digits=True):
         if (wordset != None) and (word in wordset): return word
         word = canonicalize_digits(word)  # try to canonicalize numbers
     if (wordset == None) or (word in wordset): return word
-    else: return "UUUNKKK"  # unknown token
-
-
-def load_dict(filename):
-    d = dict()
-    with open(filename, 'r') as f:
-        for i, line in enumerate(f):
-            d[line.strip()] = i
-    return d
+    else: return "<UNK>"  # unknown token
 
 
-def get_dict(vocab_file='data/vocab.txt', target_file='data/target.txt'):
+def data_reader(data_file, word_dict, label_dict):
     """
-    Get the word and label dictionary.
-    """
-    word_dict = load_dict(vocab_file)
-    label_dict = load_dict(target_file)
-    return word_dict, label_dict
-
+    The dataset can be obtained according to http://www.clips.uantwerpen.be/conll2003/ner/.
+    It returns a reader creator, each sample in the reader includes:
+    word id sequence, label id sequence and raw sentence.
 
-def get_embedding(emb_file='data/wordVectors.txt'):
-    """
-    Get the trained word vector.
+    :return: reader creator
+    :rtype: callable
     """
-    return np.loadtxt(emb_file, dtype=float)
-
 
-def corpus_reader(filename='data/train'):
     def reader():
+        UNK_IDX = word_dict["<UNK>"]
+
         sentence = []
         labels = []
-        with open(filename) as f:
+        with open(data_file, "r") as f:
             for line in f:
-                if re.match(r"-DOCSTART-.+", line) or (len(line.strip()) == 0):
+                if len(line.strip()) == 0:
                     if len(sentence) > 0:
-                        yield sentence, labels
+                        word_idx = [
+                            word_dict.get(
+                                canonicalize_word(w, word_dict), UNK_IDX)
+                            for w in sentence
+                        ]
+                        mark = [1 if w[0].isupper() else 0 for w in sentence]
+                        label_idx = [label_dict[l] for l in labels]
+                        yield word_idx, mark, label_idx
                     sentence = []
                     labels = []
                 else:
                     segs = line.strip().split()
                     sentence.append(segs[0])
-                    # transform from I-TYPE to BIO schema
-                    if segs[-1] != 'O' and (len(labels) == 0 or
+                    # transform I-TYPE to BIO schema
+                    if segs[-1] != "O" and (len(labels) == 0 or
                                             labels[-1][1:] != segs[-1][1:]):
-                        labels.append('B' + segs[-1][1:])
+                        labels.append("B" + segs[-1][1:])
                     else:
                         labels.append(segs[-1])
 
-        f.close()
-
     return reader
-
-
-def reader_creator(corpus_reader, word_dict, label_dict):
-    """
-    Conll03 train set creator.
-
-    The dataset can be obtained according to http://www.clips.uantwerpen.be/conll2003/ner/.
-    It returns a reader creator, each sample in the reader includes word id sequence, label id sequence and raw sentence for purpose of print.
-
-    :return: Training reader creator
-    :rtype: callable
-    """
-
-    def reader():
-        for sentence, labels in corpus_reader():
-            word_idx = [
-                word_dict.get(canonicalize_word(w, word_dict), UNK_IDX)
-                for w in sentence
-            ]
-            mark = [1 if w[0].isupper() else 0 for w in sentence]
-            label_idx = [label_dict.get(w) for w in labels]
-            yield word_idx, mark, label_idx, sentence
-
-    return reader
-
-
-def train(data_file='data/train',
-          vocab_file='data/vocab.txt',
-          target_file='data/target.txt'):
-    return reader_creator(
-        corpus_reader(data_file),
-        word_dict=load_dict(vocab_file),
-        label_dict=load_dict(target_file))
-
-
-def test(data_file='data/test',
-         vocab_file='data/vocab.txt',
-         target_file='data/target.txt'):
-    return reader_creator(
-        corpus_reader(data_file),
-        word_dict=load_dict(vocab_file),
-        label_dict=load_dict(target_file))

sequence_tagging_for_ner/train.py

+import gzip
+import numpy as np
+
+import reader
+from utils import *
+from network_conf import *
+
+
+def main(train_data_file,
+         test_data_file,
+         vocab_file,
+         target_file,
+         emb_file,
+         num_passes=10,
+         batch_size=32):
+    word_dict = load_dict(vocab_file)
+    label_dict = load_dict(target_file)
+
+    word_vector_values = get_embedding(emb_file)
+
+    word_dict_len = len(word_dict)
+    label_dict_len = len(label_dict)
+
+    paddle.init(use_gpu=False, trainer_count=1)
+
+    # define network topology
+    crf_cost, crf_dec, target = ner_net(word_dict_len, label_dict_len)
+    evaluator.sum(name="error", input=crf_dec)
+    evaluator.chunk(
+        name="ner_chunk",
+        input=crf_dec,
+        label=target,
+        chunk_scheme="IOB",
+        num_chunk_types=(label_dict_len - 1) / 2)
+
+    # create parameters
+    parameters = paddle.parameters.create(crf_cost)
+    parameters.set("emb", word_vector_values)
+
+    # create optimizer
+    optimizer = paddle.optimizer.Momentum(
+        momentum=0,
+        learning_rate=2e-4,
+        regularization=paddle.optimizer.L2Regularization(rate=8e-4),
+        gradient_clipping_threshold=25,
+        model_average=paddle.optimizer.ModelAverage(
+            average_window=0.5, max_average_window=10000), )
+
+    trainer = paddle.trainer.SGD(
+        cost=crf_cost,
+        parameters=parameters,
+        update_equation=optimizer,
+        extra_layers=crf_dec)
+
+    train_reader = paddle.batch(
+        paddle.reader.shuffle(
+            reader.data_reader(train_data_file, word_dict, label_dict),
+            buf_size=1000),
+        batch_size=batch_size)
+    test_reader = paddle.batch(
+        paddle.reader.shuffle(
+            reader.data_reader(test_data_file, word_dict, label_dict),
+            buf_size=1000),
+        batch_size=batch_size)
+
+    feeding = {"word": 0, "mark": 1, "target": 2}
+
+    def event_handler(event):
+        if isinstance(event, paddle.event.EndIteration):
+            if event.batch_id % 1 == 0:
+                logger.info("Pass %d, Batch %d, Cost %f, %s" % (
+                    event.pass_id, event.batch_id, event.cost, event.metrics))
+            if event.batch_id % 1 == 0:
+                result = trainer.test(reader=test_reader, feeding=feeding)
+                logger.info("\nTest with Pass %d, Batch %d, %s" %
+                            (event.pass_id, event.batch_id, result.metrics))
+
+        if isinstance(event, paddle.event.EndPass):
+            # save parameters
+            with gzip.open("models/params_pass_%d.tar.gz" % event.pass_id,
+                           "w") as f:
+                parameters.to_tar(f)
+
+            result = trainer.test(reader=test_reader, feeding=feeding)
+            logger.info("\nTest with Pass %d, %s" % (event.pass_id,
+                                                     result.metrics))
+
+    trainer.train(
+        reader=train_reader,
+        event_handler=event_handler,
+        num_passes=num_passes,
+        feeding=feeding)
+
+
+if __name__ == "__main__":
+    main(
+        train_data_file='data/train',
+        test_data_file='data/test',
+        vocab_file='data/vocab.txt',
+        target_file='data/target.txt',
+        emb_file='data/wordVectors.txt')

sequence_tagging_for_ner/utils.py

+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+import logging
+import os
+import re
+import argparse
+import numpy as np
+from collections import defaultdict
+
+logger = logging.getLogger("logger")
+logger.setLevel(logging.INFO)
+
+
+def get_embedding(emb_file='data/wordVectors.txt'):
+    """
+    Get the trained word vector.
+    """
+    return np.loadtxt(emb_file, dtype=float)
+
+
+def load_dict(dict_path):
+    """
+    Load the word dictionary from the given file.
+    Each line of the given file is a word, which can include multiple columns
+    seperated by tab.
+
+    This function takes the first column (columns in a line are seperated by
+    tab) as key and takes line number of a line as the key (index of the word
+    in the dictionary).
+    """
+
+    return dict((line.strip().split("\t")[0], idx)
+                for idx, line in enumerate(open(dict_path, "r").readlines()))
+
+
+def load_reverse_dict(dict_path):
+    """
+    Load the word dictionary from the given file.
+    Each line of the given file is a word, which can include multiple columns
+    seperated by tab.
+
+    This function takes line number of a line as the key (index of the word in
+    the dictionary) and the first column (columns in a line are seperated by
+    tab) as the value.
+    """
+    return dict((idx, line.strip().split("\t")[0])
+                for idx, line in enumerate(open(dict_path, "r").readlines()))