From 891867ecd636eea06ba7550811e83888e672dccc Mon Sep 17 00:00:00 2001 From: zhangjinchao01 Date: Wed, 9 Nov 2016 13:44:54 +0800 Subject: [PATCH] update srl demo --- .../data/extract_dict_feature.py | 60 +++--- .../data/extract_pairs.py | 16 +- demo/semantic_role_labeling/data/get_data.sh | 6 +- demo/semantic_role_labeling/dataprovider.py | 38 ++-- demo/semantic_role_labeling/db_lstm.py | 180 +++++++++++++----- demo/semantic_role_labeling/predict.py | 63 ++++-- demo/semantic_role_labeling/predict.sh | 11 +- demo/semantic_role_labeling/train.sh | 18 +- .../semantic_role_labeling.md | 85 +++++---- 9 files changed, 314 insertions(+), 163 deletions(-) diff --git a/demo/semantic_role_labeling/data/extract_dict_feature.py b/demo/semantic_role_labeling/data/extract_dict_feature.py index 2982e54c665..daca5f01cf2 100644 --- a/demo/semantic_role_labeling/data/extract_dict_feature.py +++ b/demo/semantic_role_labeling/data/extract_dict_feature.py @@ -17,24 +17,15 @@ import os from optparse import OptionParser -def extract_dict_features(pair_file, feature_file, src_dict_file, - tgt_dict_file): - src_dict = set() - tgt_dict = set() - - with open(pair_file) as fin, open(feature_file, 'w') as feature_out, open( - src_dict_file, 'w') as src_dict_out, open(tgt_dict_file, - 'w') as tgt_dict_out: +def extract_dict_features(pair_file, feature_file): + + with open(pair_file) as fin, open(feature_file, 'w') as feature_out: for line in fin: - sentence, labels = line.strip().split('\t') + sentence, predicate, labels = line.strip().split('\t') sentence_list = sentence.split() labels_list = labels.split() - src_dict.update(sentence_list) - tgt_dict.update(labels_list) - verb_index = labels_list.index('B-V') - verb_feature = sentence_list[verb_index] mark = [0] * len(labels_list) if verb_index > 0: @@ -42,47 +33,50 @@ def extract_dict_features(pair_file, feature_file, src_dict_file, ctx_n1 = sentence_list[verb_index - 1] else: ctx_n1 = 'bos' - ctx_n1_feature = ctx_n1 + + if verb_index > 1: + mark[verb_index - 2] = 1 + ctx_n2 = sentence_list[verb_index - 2] + else: + ctx_n2 = 'bos' mark[verb_index] = 1 - ctx_0_feature = sentence_list[verb_index] + ctx_0 = sentence_list[verb_index] if verb_index < len(labels_list) - 2: mark[verb_index + 1] = 1 ctx_p1 = sentence_list[verb_index + 1] else: ctx_p1 = 'eos' - ctx_p1_feature = ctx_p1 + + if verb_index < len(labels_list) - 3: + mark[verb_index + 2] = 1 + ctx_p2 = sentence_list[verb_index + 2] + else: + ctx_p2 = 'eos' + feature_str = sentence + '\t' \ - + verb_feature + '\t' \ - + ctx_n1_feature + '\t' \ - + ctx_0_feature + '\t' \ - + ctx_p1_feature + '\t' \ + + predicate + '\t' \ + + ctx_n2 + '\t' \ + + ctx_n1 + '\t' \ + + ctx_0 + '\t' \ + + ctx_p1 + '\t' \ + + ctx_p2 + '\t' \ + ' '.join([str(i) for i in mark]) + '\t' \ + labels feature_out.write(feature_str + '\n') - src_dict_out.write('\n') - src_dict_out.write('\n'.join(list(src_dict))) - - tgt_dict_out.write('\n'.join(list(tgt_dict))) if __name__ == '__main__': - usage = '-p pair_file -f feature_file -s source dictionary -t target dictionary ' + usage = '-p pair_file -f feature_file' parser = OptionParser(usage) parser.add_option('-p', dest='pair_file', help='the pair file') - parser.add_option( - '-f', dest='feature_file', help='the file to store feature') - parser.add_option( - '-s', dest='src_dict', help='the file to store source dictionary') - parser.add_option( - '-t', dest='tgt_dict', help='the file to store target dictionary') + parser.add_option('-f', dest='feature_file', help='the feature file') (options, args) = parser.parse_args() - extract_dict_features(options.pair_file, options.feature_file, - options.src_dict, options.tgt_dict) + extract_dict_features(options.pair_file, options.feature_file) diff --git a/demo/semantic_role_labeling/data/extract_pairs.py b/demo/semantic_role_labeling/data/extract_pairs.py index 4d1bef8f958..86ab00ce417 100644 --- a/demo/semantic_role_labeling/data/extract_pairs.py +++ b/demo/semantic_role_labeling/data/extract_pairs.py @@ -51,7 +51,7 @@ def read_sentences(words_file): for line in fin: line = line.strip() if line == '': - sentences.append(s.lower()) + sentences.append(s) s = '' else: s += line + ' ' @@ -64,6 +64,11 @@ def transform_labels(sentences, labels): if len(labels[i]) == 1: continue else: + verb_list = [] + for x in labels[i][0]: + if x !='-': + verb_list.append(x) + for j in xrange(1, len(labels[i])): label_list = labels[i][j] current_tag = 'O' @@ -88,8 +93,7 @@ def transform_labels(sentences, labels): is_in_bracket = True else: print 'error:', ll - - sen_lab_pair.append((sentences[i], label_seq)) + sen_lab_pair.append((sentences[i], verb_list[j-1], label_seq)) return sen_lab_pair @@ -97,9 +101,9 @@ def write_file(sen_lab_pair, output_file): with open(output_file, 'w') as fout: for x in sen_lab_pair: sentence = x[0] - label_seq = ' '.join(x[1]) - assert len(sentence.split()) == len(x[1]) - fout.write(sentence + '\t' + label_seq + '\n') + label_seq = ' '.join(x[2]) + assert len(sentence.split()) == len(x[2]) + fout.write(sentence + '\t' + x[1]+'\t' +label_seq + '\n') if __name__ == '__main__': diff --git a/demo/semantic_role_labeling/data/get_data.sh b/demo/semantic_role_labeling/data/get_data.sh index 268c0995e27..55e33f46856 100644 --- a/demo/semantic_role_labeling/data/get_data.sh +++ b/demo/semantic_role_labeling/data/get_data.sh @@ -14,6 +14,10 @@ # limitations under the License. set -e wget http://www.cs.upc.edu/~srlconll/conll05st-tests.tar.gz +wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/verbDict.txt --no-check-certificate +wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/targetDict.txt --no-check-certificate +wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/wordDict.txt --no-check-certificate +wget https://www.googledrive.com/host/0B7Q8d52jqeI9ejh6Q1RpMTFQT1k/semantic_role_labeling/emb --no-check-certificate tar -xzvf conll05st-tests.tar.gz rm conll05st-tests.tar.gz cp ./conll05st-release/test.wsj/words/test.wsj.words.gz . @@ -22,4 +26,4 @@ gunzip test.wsj.words.gz gunzip test.wsj.props.gz python extract_pairs.py -w test.wsj.words -p test.wsj.props -o test.wsj.seq_pair -python extract_dict_feature.py -p test.wsj.seq_pair -f feature -s src.dict -t tgt.dict +python extract_dict_feature.py -p test.wsj.seq_pair -f feature diff --git a/demo/semantic_role_labeling/dataprovider.py b/demo/semantic_role_labeling/dataprovider.py index 2ef25c42c17..c1c6eeca517 100644 --- a/demo/semantic_role_labeling/dataprovider.py +++ b/demo/semantic_role_labeling/dataprovider.py @@ -17,11 +17,15 @@ from paddle.trainer.PyDataProvider2 import * UNK_IDX = 0 -def hook(settings, word_dict, label_dict, **kwargs): +def hook(settings, word_dict, label_dict, predicate_dict, **kwargs): settings.word_dict = word_dict settings.label_dict = label_dict + settings.predicate_dict = predicate_dict + #all inputs are integral and sequential type settings.slots = [ + integer_value_sequence(len(word_dict)), + integer_value_sequence(len(predicate_dict)), integer_value_sequence(len(word_dict)), integer_value_sequence(len(word_dict)), integer_value_sequence(len(word_dict)), @@ -31,27 +35,33 @@ def hook(settings, word_dict, label_dict, **kwargs): integer_value_sequence(len(label_dict))] -@provider(init_hook=hook) -def process(obj, file_name): +def get_batch_size(yeild_data): + return len(yeild_data[0]) + + +@provider(init_hook=hook, should_shuffle=True, calc_batch_size=get_batch_size, + can_over_batch_size=False, cache=CacheType.CACHE_PASS_IN_MEM) +def process(settings, file_name): with open(file_name, 'r') as fdata: for line in fdata: - sentence, predicate, ctx_n1, ctx_0, ctx_p1, mark, label = \ + sentence, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark, label = \ line.strip().split('\t') - + words = sentence.split() sen_len = len(words) - word_slot = [obj.word_dict.get(w, UNK_IDX) for w in words] + word_slot = [settings.word_dict.get(w, UNK_IDX) for w in words] - predicate_slot = [obj.word_dict.get(predicate, UNK_IDX)] * sen_len - ctx_n1_slot = [obj.word_dict.get(ctx_n1, UNK_IDX)] * sen_len - ctx_0_slot = [obj.word_dict.get(ctx_0, UNK_IDX)] * sen_len - ctx_p1_slot = [obj.word_dict.get(ctx_p1, UNK_IDX)] * sen_len + predicate_slot = [settings.predicate_dict.get(predicate)] * sen_len + ctx_n2_slot = [settings.word_dict.get(ctx_n2, UNK_IDX)] * sen_len + ctx_n1_slot = [settings.word_dict.get(ctx_n1, UNK_IDX)] * sen_len + ctx_0_slot = [settings.word_dict.get(ctx_0, UNK_IDX)] * sen_len + ctx_p1_slot = [settings.word_dict.get(ctx_p1, UNK_IDX)] * sen_len + ctx_p2_slot = [settings.word_dict.get(ctx_p2, UNK_IDX)] * sen_len marks = mark.split() mark_slot = [int(w) for w in marks] label_list = label.split() - label_slot = [obj.label_dict.get(w) for w in label_list] - - yield word_slot, predicate_slot, ctx_n1_slot, \ - ctx_0_slot, ctx_p1_slot, mark_slot, label_slot + label_slot = [settings.label_dict.get(w) for w in label_list] + yield word_slot, predicate_slot, ctx_n2_slot, ctx_n1_slot, \ + ctx_0_slot, ctx_p1_slot, ctx_p2_slot, mark_slot, label_slot diff --git a/demo/semantic_role_labeling/db_lstm.py b/demo/semantic_role_labeling/db_lstm.py index 364460afbe3..68feb9c4a77 100644 --- a/demo/semantic_role_labeling/db_lstm.py +++ b/demo/semantic_role_labeling/db_lstm.py @@ -19,8 +19,9 @@ import sys from paddle.trainer_config_helpers import * #file paths -word_dict_file = './data/src.dict' -label_dict_file = './data/tgt.dict' +word_dict_file = './data/wordDict.txt' +label_dict_file = './data/targetDict.txt' +predicate_file= './data/verbDict.txt' train_list_file = './data/train.list' test_list_file = './data/test.list' @@ -31,8 +32,10 @@ if not is_predict: #load dictionaries word_dict = dict() label_dict = dict() + predicate_dict = dict() with open(word_dict_file, 'r') as f_word, \ - open(label_dict_file, 'r') as f_label: + open(label_dict_file, 'r') as f_label, \ + open(predicate_file, 'r') as f_pre: for i, line in enumerate(f_word): w = line.strip() word_dict[w] = i @@ -41,6 +44,11 @@ if not is_predict: w = line.strip() label_dict[w] = i + for i, line in enumerate(f_pre): + w = line.strip() + predicate_dict[w] = i + + if is_test: train_list_file = None @@ -51,91 +59,169 @@ if not is_predict: module='dataprovider', obj='process', args={'word_dict': word_dict, - 'label_dict': label_dict}) + 'label_dict': label_dict, + 'predicate_dict': predicate_dict }) word_dict_len = len(word_dict) label_dict_len = len(label_dict) + pred_len = len(predicate_dict) else: word_dict_len = get_config_arg('dict_len', int) label_dict_len = get_config_arg('label_len', int) + pred_len = get_config_arg('pred_len', int) +############################## Hyper-parameters ################################## mark_dict_len = 2 word_dim = 32 mark_dim = 5 -hidden_dim = 128 +hidden_dim = 512 depth = 8 -emb_lr = 1e-2 -fc_lr = 1e-2 -lstm_lr = 2e-2 + + + +########################### Optimizer ####################################### + settings( batch_size=150, - learning_method=AdamOptimizer(), - learning_rate=1e-3, + learning_method=MomentumOptimizer(momentum=0), + learning_rate=2e-2, regularization=L2Regularization(8e-4), - gradient_clipping_threshold=25) + is_async=False, + model_average=ModelAverage(average_window=0.5, + max_average_window=10000), + +) -#6 features + + + +####################################### network ############################## +#8 features and 1 target word = data_layer(name='word_data', size=word_dict_len) -predicate = data_layer(name='verb_data', size=word_dict_len) +predicate = data_layer(name='verb_data', size=pred_len) + +ctx_n2 = data_layer(name='ctx_n2_data', size=word_dict_len) ctx_n1 = data_layer(name='ctx_n1_data', size=word_dict_len) ctx_0 = data_layer(name='ctx_0_data', size=word_dict_len) ctx_p1 = data_layer(name='ctx_p1_data', size=word_dict_len) +ctx_p2 = data_layer(name='ctx_p2_data', size=word_dict_len) mark = data_layer(name='mark_data', size=mark_dict_len) + if not is_predict: target = data_layer(name='target', size=label_dict_len) -ptt = ParameterAttribute(name='src_emb', learning_rate=emb_lr) -layer_attr = ExtraLayerAttribute(drop_rate=0.5) -fc_para_attr = ParameterAttribute(learning_rate=fc_lr) -lstm_para_attr = ParameterAttribute(initial_std=0., learning_rate=lstm_lr) -para_attr = [fc_para_attr, lstm_para_attr] -word_embedding = embedding_layer(size=word_dim, input=word, param_attr=ptt) -predicate_embedding = embedding_layer( - size=word_dim, input=predicate, param_attr=ptt) -ctx_n1_embedding = embedding_layer(size=word_dim, input=ctx_n1, param_attr=ptt) -ctx_0_embedding = embedding_layer(size=word_dim, input=ctx_0, param_attr=ptt) -ctx_p1_embedding = embedding_layer(size=word_dim, input=ctx_p1, param_attr=ptt) -mark_embedding = embedding_layer(size=mark_dim, input=mark) +default_std=1/math.sqrt(hidden_dim)/3.0 + +emb_para = ParameterAttribute(name='emb', initial_std=0., learning_rate=0.) +std_0 = ParameterAttribute(initial_std=0.) +std_default = ParameterAttribute(initial_std=default_std) + +word_embedding = embedding_layer(size=word_dim, input=word, param_attr=emb_para) +predicate_embedding = embedding_layer(size=word_dim, input=predicate, param_attr=ParameterAttribute(name='vemb',initial_std=default_std)) +ctx_n2_embedding = embedding_layer(size=word_dim, input=ctx_n2, param_attr=emb_para) +ctx_n2_embedding = embedding_layer(size=word_dim, input=ctx_n2, param_attr=emb_para) +ctx_n1_embedding = embedding_layer(size=word_dim, input=ctx_n1, param_attr=emb_para) +ctx_0_embedding = embedding_layer(size=word_dim, input=ctx_0, param_attr=emb_para) +ctx_p1_embedding = embedding_layer(size=word_dim, input=ctx_p1, param_attr=emb_para) +ctx_p2_embedding = embedding_layer(size=word_dim, input=ctx_p2, param_attr=emb_para) +mark_embedding = embedding_layer(name='word_ctx-in_embedding', size=mark_dim, input=mark, param_attr=std_0) + hidden_0 = mixed_layer( + name='hidden0', size=hidden_dim, + bias_attr=std_default, input=[ - full_matrix_projection(input=word_embedding), - full_matrix_projection(input=predicate_embedding), - full_matrix_projection(input=ctx_n1_embedding), - full_matrix_projection(input=ctx_0_embedding), - full_matrix_projection(input=ctx_p1_embedding), - full_matrix_projection(input=mark_embedding), + full_matrix_projection(input=word_embedding, param_attr=std_default), + full_matrix_projection(input=predicate_embedding, param_attr=std_default), + full_matrix_projection(input=ctx_n2_embedding, param_attr=std_default), + full_matrix_projection(input=ctx_n1_embedding, param_attr=std_default), + full_matrix_projection(input=ctx_0_embedding, param_attr=std_default), + full_matrix_projection(input=ctx_p1_embedding, param_attr=std_default), + full_matrix_projection(input=ctx_p2_embedding, param_attr=std_default), + full_matrix_projection(input=mark_embedding, param_attr=std_default) ]) -lstm_0 = lstmemory(input=hidden_0, layer_attr=layer_attr) + +mix_hidden_lr = 1e-3 +lstm_para_attr = ParameterAttribute(initial_std=0.0, learning_rate=1.0) +hidden_para_attr = ParameterAttribute(initial_std=default_std, learning_rate=mix_hidden_lr) + +lstm_0 = lstmemory(name='lstm0', + input=hidden_0, + act=ReluActivation(), + gate_act=SigmoidActivation(), + state_act=SigmoidActivation(), + bias_attr=std_0, + param_attr=lstm_para_attr) #stack L-LSTM and R-LSTM with direct edges input_tmp = [hidden_0, lstm_0] + for i in range(1, depth): - fc = fc_layer(input=input_tmp, size=hidden_dim, param_attr=para_attr) + mix_hidden = mixed_layer(name='hidden'+str(i), + size=hidden_dim, + bias_attr=std_default, + input=[full_matrix_projection(input=input_tmp[0], param_attr=hidden_para_attr), + full_matrix_projection(input=input_tmp[1], param_attr=lstm_para_attr) + ] + ) + + lstm = lstmemory(name='lstm'+str(i), + input=mix_hidden, + act=ReluActivation(), + gate_act=SigmoidActivation(), + state_act=SigmoidActivation(), + reverse=((i % 2)==1), + bias_attr=std_0, + param_attr=lstm_para_attr) + + input_tmp = [mix_hidden, lstm] + +feature_out = mixed_layer(name='output', + size=label_dict_len, + bias_attr=std_default, + input=[full_matrix_projection(input=input_tmp[0], param_attr=hidden_para_attr), + full_matrix_projection(input=input_tmp[1], param_attr=lstm_para_attr) + ], + ) - lstm = lstmemory( - input=fc, - act=ReluActivation(), - reverse=(i % 2) == 1, - layer_attr=layer_attr) - input_tmp = [fc, lstm] -prob = fc_layer( - input=input_tmp, - size=label_dict_len, - act=SoftmaxActivation(), - param_attr=para_attr) if not is_predict: - cls = classification_cost(input=prob, label=target) - outputs(cls) + crf_l = crf_layer( name = 'crf', + size = label_dict_len, + input = feature_out, + label = target, + param_attr=ParameterAttribute(name='crfw',initial_std=default_std, learning_rate=mix_hidden_lr) + + ) + + + crf_dec_l = crf_decoding_layer(name = 'crf_dec_l', + size = label_dict_len, + input = feature_out, + label = target, + param_attr=ParameterAttribute(name='crfw') + ) + + + eval = sum_evaluator(input=crf_dec_l) + + outputs(crf_l) + else: - outputs(prob) + crf_dec_l = crf_decoding_layer(name = 'crf_dec_l', + size = label_dict_len, + input = feature_out, + param_attr=ParameterAttribute(name='crfw') + ) + + outputs(crf_dec_l) + diff --git a/demo/semantic_role_labeling/predict.py b/demo/semantic_role_labeling/predict.py index 9a27112828e..80183300f2a 100644 --- a/demo/semantic_role_labeling/predict.py +++ b/demo/semantic_role_labeling/predict.py @@ -26,7 +26,7 @@ UNK_IDX = 0 class Prediction(): - def __init__(self, train_conf, dict_file, model_dir, label_file): + def __init__(self, train_conf, dict_file, model_dir, label_file, predicate_dict_file): """ train_conf: trainer configure. dict_file: word dictionary file name. @@ -35,16 +35,19 @@ class Prediction(): self.dict = {} self.labels = {} + self.predicate_dict={} self.labels_reverse = {} - self.load_dict_label(dict_file, label_file) + self.load_dict_label(dict_file, label_file, predicate_dict_file) len_dict = len(self.dict) len_label = len(self.labels) + len_pred = len(self.predicate_dict) conf = parse_config( train_conf, - 'dict_len=' + str(len_dict) + + 'dict_len=' + str(len_dict) + ',label_len=' + str(len_label) + + ',pred_len=' + str(len_pred) + ',is_predict=True') self.network = swig_paddle.GradientMachine.createFromConfigProto( conf.model_config) @@ -52,15 +55,17 @@ class Prediction(): slots = [ integer_value_sequence(len_dict), + integer_value_sequence(len_pred), integer_value_sequence(len_dict), integer_value_sequence(len_dict), integer_value_sequence(len_dict), integer_value_sequence(len_dict), + integer_value_sequence(len_dict), integer_value_sequence(2) - ] + ] self.converter = DataProviderConverter(slots) - def load_dict_label(self, dict_file, label_file): + def load_dict_label(self, dict_file, label_file, predicate_dict_file): """ Load dictionary from self.dict_file. """ @@ -71,39 +76,42 @@ class Prediction(): self.labels[line.strip()] = line_count self.labels_reverse[line_count] = line.strip() + for line_count, line in enumerate(open(predicate_dict_file, 'r')): + self.predicate_dict[line.strip()] = line_count def get_data(self, data_file): """ Get input data of paddle format. """ with open(data_file, 'r') as fdata: for line in fdata: - sentence, predicate, ctx_n1, ctx_0, ctx_p1, mark, label = line.strip( + sentence, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark, label = line.strip( ).split('\t') words = sentence.split() sen_len = len(words) - + word_slot = [self.dict.get(w, UNK_IDX) for w in words] - predicate_slot = [self.dict.get(predicate, UNK_IDX)] * sen_len + predicate_slot = [self.predicate_dict.get(predicate, UNK_IDX)] * sen_len + ctx_n2_slot = [self.dict.get(ctx_n2, UNK_IDX)] * sen_len ctx_n1_slot = [self.dict.get(ctx_n1, UNK_IDX)] * sen_len ctx_0_slot = [self.dict.get(ctx_0, UNK_IDX)] * sen_len ctx_p1_slot = [self.dict.get(ctx_p1, UNK_IDX)] * sen_len + ctx_p2_slot = [self.dict.get(ctx_p2, UNK_IDX)] * sen_len marks = mark.split() mark_slot = [int(w) for w in marks] + + yield word_slot, predicate_slot, ctx_n2_slot, ctx_n1_slot, \ + ctx_0_slot, ctx_p1_slot, ctx_p2_slot, mark_slot - yield word_slot, predicate_slot, ctx_n1_slot, \ - ctx_0_slot, ctx_p1_slot, mark_slot - - def predict(self, data_file): + def predict(self, data_file, output_file): """ data_file: file name of input data. """ input = self.converter(self.get_data(data_file)) output = self.network.forwardTest(input) - prob = output[0]["value"] - lab = list(np.argsort(-prob)[:, 0]) + lab = output[0]["id"].tolist() - with open(data_file, 'r') as fin, open('predict.res', 'w') as fout: + with open(data_file, 'r') as fin, open(output_file, 'w') as fout: index = 0 for line in fin: sen = line.split('\t')[0] @@ -115,8 +123,8 @@ class Prediction(): def option_parser(): - usage = ("python predict.py -c config -w model_dir " - "-d word dictionary -l label_file -i input_file") + usage = ("python predict.py -c config -w model_dir " + "-d word dictionary -l label_file -i input_file -p pred_dict_file") parser = OptionParser(usage="usage: %s [options]" % usage) parser.add_option( "-c", @@ -137,6 +145,13 @@ def option_parser(): dest="label_file", default=None, help="label file") + parser.add_option( + "-p", + "--predict_dict_file", + action="store", + dest="predict_dict_file", + default=None, + help="predict_dict_file") parser.add_option( "-i", "--data", @@ -150,6 +165,14 @@ def option_parser(): dest="model_path", default=None, help="model path") + + parser.add_option( + "-o", + "--output_file", + action="store", + dest="output_file", + default=None, + help="output file") return parser.parse_args() @@ -160,10 +183,12 @@ def main(): dict_file = options.dict_file model_path = options.model_path label_file = options.label_file + predict_dict_file = options.predict_dict_file + output_file = options.output_file swig_paddle.initPaddle("--use_gpu=0") - predict = Prediction(train_conf, dict_file, model_path, label_file) - predict.predict(data_file) + predict = Prediction(train_conf, dict_file, model_path, label_file, predict_dict_file) + predict.predict(data_file,output_file) if __name__ == '__main__': diff --git a/demo/semantic_role_labeling/predict.sh b/demo/semantic_role_labeling/predict.sh index a545b9a5d59..d0acdb0bd09 100644 --- a/demo/semantic_role_labeling/predict.sh +++ b/demo/semantic_role_labeling/predict.sh @@ -26,15 +26,18 @@ LOG=`get_best_pass $log` LOG=(${LOG}) best_model_path="output/pass-${LOG[1]}" - config_file=db_lstm.py -dict_file=./data/src.dict -label_file=./data/tgt.dict +dict_file=./data/wordDict.txt +label_file=./data/targetDict.txt +predicate_dict_file=./data/verbDict.txt input_file=./data/feature +output_file=predict.res python predict.py \ -c $config_file \ -w $best_model_path \ -l $label_file \ + -p $predicate_dict_file \ -d $dict_file \ - -i $input_file + -i $input_file \ + -o $output_file diff --git a/demo/semantic_role_labeling/train.sh b/demo/semantic_role_labeling/train.sh index 94c7b6f31df..b566931db0f 100644 --- a/demo/semantic_role_labeling/train.sh +++ b/demo/semantic_role_labeling/train.sh @@ -16,12 +16,18 @@ set -e paddle train \ --config=./db_lstm.py \ + --use_gpu=0 \ + --log_period=5000 \ + --trainer_count=1 \ + --show_parameter_stats_period=5000 \ + --saving_period=1 \ --save_dir=./output \ - --trainer_count=4 \ - --log_period=10 \ - --num_passes=500 \ - --use_gpu=false \ - --show_parameter_stats_period=10 \ - --test_all_data_in_one_period=1 \ + --local=1 \ + --num_passes=10000 \ + --test_period=0 \ + --average_test_period=10000000 \ + --init_model_path=./data \ + --load_missing_parameter_strategy=rand \ + --dot_period=100 \ 2>&1 | tee 'train.log' diff --git a/doc/demo/semantic_role_labeling/semantic_role_labeling.md b/doc/demo/semantic_role_labeling/semantic_role_labeling.md index 05fbc8278da..c6b9813f6a6 100644 --- a/doc/demo/semantic_role_labeling/semantic_role_labeling.md +++ b/doc/demo/semantic_role_labeling/semantic_role_labeling.md @@ -30,8 +30,6 @@ Several new files appear in the `data `directory as follows. conll05st-release：the test data set of CoNll-2005 shared task test.wsj.words：the Wall Street Journal data sentences test.wsj.props: the propositional arguments -src.dict：the dictionary of words in sentences -tgt.dict：the labels dictionary feature: the extracted features from data set ``` @@ -67,6 +65,8 @@ def hook(settings, word_dict, label_dict, **kwargs): settings.label_dict = label_dict #all inputs are integral and sequential type settings.slots = [ + integer_value_sequence(len(word_dict)), + integer_value_sequence(len(predicate_dict)), integer_value_sequence(len(word_dict)), integer_value_sequence(len(word_dict)), integer_value_sequence(len(word_dict)), @@ -77,34 +77,39 @@ def hook(settings, word_dict, label_dict, **kwargs): ``` The corresponding data iterator is as following: ``` -@provider(use_seq=True, init_hook=hook) -def process(obj, file_name): +@provider(init_hook=hook, should_shuffle=True, calc_batch_size=get_batch_size, + can_over_batch_size=False, cache=CacheType.CACHE_PASS_IN_MEM) +def process(settings, file_name): with open(file_name, 'r') as fdata: for line in fdata: - sentence, predicate, ctx_n1, ctx_0, ctx_p1, mark, label = line.strip().split('\t') + sentence, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2, mark, label = \ + line.strip().split('\t') + words = sentence.split() sen_len = len(words) - word_slot = [obj.word_dict.get(w, UNK_IDX) for w in words] + word_slot = [settings.word_dict.get(w, UNK_IDX) for w in words] - predicate_slot = [obj.word_dict.get(predicate, UNK_IDX)] * sen_len - ctx_n1_slot = [obj.word_dict.get(ctx_n1, UNK_IDX) ] * sen_len - ctx_0_slot = [obj.word_dict.get(ctx_0, UNK_IDX) ] * sen_len - ctx_p1_slot = [obj.word_dict.get(ctx_p1, UNK_IDX) ] * sen_len + predicate_slot = [settings.predicate_dict.get(predicate)] * sen_len + ctx_n2_slot = [settings.word_dict.get(ctx_n2, UNK_IDX)] * sen_len + ctx_n1_slot = [settings.word_dict.get(ctx_n1, UNK_IDX)] * sen_len + ctx_0_slot = [settings.word_dict.get(ctx_0, UNK_IDX)] * sen_len + ctx_p1_slot = [settings.word_dict.get(ctx_p1, UNK_IDX)] * sen_len + ctx_p2_slot = [settings.word_dict.get(ctx_p2, UNK_IDX)] * sen_len marks = mark.split() mark_slot = [int(w) for w in marks] label_list = label.split() - label_slot = [obj.label_dict.get(w) for w in label_list] - - yield word_slot, predicate_slot, ctx_n1_slot, ctx_0_slot, ctx_p1_slot, mark_slot, label_slot + label_slot = [settings.label_dict.get(w) for w in label_list] + yield word_slot, predicate_slot, ctx_n2_slot, ctx_n1_slot, \ + ctx_0_slot, ctx_p1_slot, ctx_p2_slot, mark_slot, label_slot ``` -The `process`function yield 7 lists which are six features and labels. +The `process`function yield 9 lists which are 8 features and label. ### Neural Network Config `db_lstm.py` is the neural network config file to load the dictionaries and define the data provider module and network architecture during the training procedure. -Seven `data_layer` load instances from data provider. Six features are transformed into embedddings respectively, and mixed by `mixed_layer` . Deep bidirectional LSTM layers extract features for the softmax layer. The objective function is cross entropy of labels. +Nine `data_layer` load instances from data provider. Eight features are transformed into embedddings respectively, and mixed by `mixed_layer` . Deep bidirectional LSTM layers extract features for the softmax layer. The objective function is cross entropy of labels. ### Run Training The script for training is `train.sh`, user just need to execute: @@ -115,24 +120,36 @@ The content in `train.sh`: ``` paddle train \ --config=./db_lstm.py \ + --use_gpu=0 \ + --log_period=5000 \ + --trainer_count=1 \ + --show_parameter_stats_period=5000 \ + --saving_period=1 \ --save_dir=./output \ - --trainer_count=4 \ - --log_period=10 \ - --num_passes=500 \ - --use_gpu=false \ - --show_parameter_stats_period=10 \ - --test_all_data_in_one_period=1 \ + --local=1 \ + --num_passes=10000 \ + --test_period=0 \ + --average_test_period=10000000 \ + --init_model_path=./data \ + --load_missing_parameter_strategy=rand \ + --dot_period=100 \ 2>&1 | tee 'train.log' ``` - \--config=./db_lstm.py : network config file. -- \--save_di=./output: output path to save models. -- \--trainer_count=4 : set thread number (or GPU count). -- \--log_period=10 : print log every 20 batches. -- \--num_passes=500: set pass number, one pass in PaddlePaddle means training all samples in dataset one time. -- \--use_gpu=false: use CPU to train, set true, if you install GPU version of PaddlePaddle and want to use GPU to train. -- \--show_parameter_stats_period=10: show parameter statistic every 100 batches. -- \--test_all_data_in_one_period=1: test all data in every testing. +- \--use_gpu=false: use CPU to train, set true, if you install GPU version of PaddlePaddle and want to use GPU to train, until now crf_layer do not support GPU +- \--log_period=500: print log every 20 batches. +- \--trainer_count=1: set thread number (or GPU count). +- \--show_parameter_stats_period=5000: show parameter statistic every 100 batches. +- \--saving_period=1: save model per pass +- \--save_dir=./output: output path to save models. +- \--local=1: traing in local mode +- \--num_passes=10000: set pass number, one pass in PaddlePaddle means training all samples in dataset one time. +- \--test_period=0: run testing each pass +- \--average_test_period=10000000: do test on average parameter every average_test_period batches +- \--init_model_path=./data: parameter initialization path +- \--load_missing_parameter_strategy=rand: random initialization unexisted parameters +- \--dot_period=100: print a dot per 100 batches After training, the models will be saved in directory `output`. @@ -166,11 +183,13 @@ The script for prediction is `predict.sh`, user just need to execute: In `predict.sh`, user should offer the network config file, model path, label file, word dictionary file, feature file ``` python predict.py - -c $config_file - -w $model_path - -l $label_file - -d $dict_file - -i $input_file + -c $config_file \ + -w $best_model_path \ + -l $label_file \ + -p $predicate_dict_file \ + -d $dict_file \ + -i $input_file \ + -o $output_file ``` `predict.py` is the main executable python script, which includes functions: load model, load data, data prediction. The network model will output the probability distribution of labels. In the demo, we take the label with maximum probability as result. User can also implement the beam search or viterbi decoding upon the probability distribution matrix. -- GitLab