python - 训练现有 Spacy Ner 管道会忘记之前的示例

Question

我正在为命名实体识别创建一个新模型。我有一个训练数据集，如下所示：

[[
"world leading global energy trading company has an exciting 
opportunity for a senior csharp application platform developer to 
join its systematic trading division developing new trading 
applications tools and solutions for its successful front office 
trading team", 
{"entities": [[80, 86, "RNK"]]}
]]

所以我运行以下函数来训练模型。

@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", 
str),
new_model_name=("New model name for model meta.", "option", "nm", 
str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int), 
entity=("Name of the entity to be trained", "option", "e", str),
label=("The label to be given to the trained entity", "option", "l", 
str),
)
def main(model = None, new_model_name=("ner%s" % str(datetime.now)), 
output_dir= None, n_iter=20, entity=None, label=None):

if entity is None or label is None:
    log.info("Entity and Label must both be supplied")
    log.info("Bailing out as nothing to do ...... :-(")
    return

log.info("Fetching training data for entity [%s] to be trained with 
label [%s]" % (entity, label))

log.info("Training data retrieved and the first row is : ")
log.info(TRAIN_DATA[0])
log.info("There are %d rows to be trained" % len(TRAIN_DATA))

if model is not None:
    nlp = spacy.load(output_dir)  # load existing spaCy model
    print("Loaded model '%s'" % model)
else:
    nlp = spacy.blank("en")  # create blank Language class
    print("Created blank 'en' model")

if "ner" not in nlp.pipe_names:
    log.info("ner not in pipe names, adding it in now ....")
    ner = nlp.create_pipe("ner")
    nlp.add_pipe(ner)
# otherwise, get it, so we can add labels to it
else:
    log.info("retrieving previous ner pipe now ....")
    ner = nlp.get_pipe("ner")

# add labels
for _, annotations in TRAIN_DATA:
     for ent in annotations.get('entities'):
        ner.add_label(ent[2])

move_names = list(ner.move_names)

# get names of other pipes to disable them during training
pipe_exceptions = ["ner", "trf_wordpiecer", "trf_tok2vec"]
other_pipes = [pipe for pipe in nlp.pipe_names if pipe not in 
pipe_exceptions]
with nlp.disable_pipes(*other_pipes):  # only train NER
    # reset and initialize the weights randomly – but only if we're
    # training a new model
    if model is None:
        optimizer=nlp.begin_training()
    else:
        optimizer=nlp.resume_training()
    for itn in range(n_iter):
        random.shuffle(TRAIN_DATA)
        losses = {}
        # batch up the examples using spaCy's minibatch
        batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 

1.001)) for batch in batchs: texts, annotations = zip(*batch) nlp.update( texts, # batch of texts annotations, # batch of annotations drop=0.5, # dropout - 让记忆数据更难 sgd=optimizer,损失=损失，）打印（“损失”，损失）

# test the trained model
for text, _ in TRAIN_DATA:
    doc = nlp(text)
    print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
    print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])

if output_dir is not None:
    output_dir = Path(output_dir)
    if not output_dir.exists():
        output_dir.mkdir()
    nlp.meta["name"] = new_model_name  # rename model
    nlp.to_disk(output_dir)
    print("Saved model to", output_dir)

    # test the saved model
    print("Loading from", output_dir)
    nlp2 = spacy.load(output_dir)
    # Check the classes have loaded back consistently
    assert nlp2.get_pipe("ner").move_names == move_names

return

if __name__ == "__main__":
    log = logging.getLogger(__name__)
    log.setLevel(logging.DEBUG)

    consoleHandler = logging.StreamHandler()
    consoleHandler.setLevel(logging.DEBUG)

    log.addHandler(consoleHandler)
    plac.call(main)

这很好用，然后我可以使用以下函数成功测试模型

@plac.annotations(
model_dir=("Optional output directory", "option", "o", Path),
test_text=("The test text to be used to test the model","option", 
"t", str),
entity=("Name of the entity to be trained", "option", "e", str),
label=("The label to be given to the trained entity", "option", "l", 
str),
)
def main(model_dir= None,test_text=None, entity=None, label=None):

if entity is None or label is None:
    log.info("Entity and Label must both be supplied")
    log.info("Bailing out as nothing to do ...... :-(")
    return

if test_text is None:
    test_text = ("Using default test string which is not optimal to 
look for %s" % entity)

nlp = spacy.load(model_dir)
log.info("Loaded model %s" % nlp.meta["name"])
log.info("Testing the string %s" % test_text)

ner = nlp.get_pipe("ner")
for label in ner.labels:
    log.info("NER Label : %s found in model" % label)

doc = nlp(test_text)
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])

if __name__ == "__main__":
log = logging.getLogger(__name__)
log.setLevel(logging.DEBUG)

consoleHandler = logging.StreamHandler()
consoleHandler.setLevel(logging.DEBUG)

log.addHandler(consoleHandler)
plac.call(main)

但是，如果我再次运行代码以针对新标签进行训练，例如说“技能”并提供新的训练数据，它会成功加载旧模型，检索 Ner 管道并将优化器设置为恢复，但是当我再次对其进行测试时已经忘记了所有关于 RNK 标签的培训。

我假设简历会以某种方式获取先前的模型状态并保留先前学习的注释。它当然保留了 NER 标签。

为什么会这样？

认为这可能与灾难性遗忘问题有关，我创建了一大组训练数据，其中包含两个类别的示例，因此：

'TOKEN'  >>> 'NER Annotation'
-----------------------------
'senior' >>> 'RNK'
'csharp' >>> 'SKILL'
'sql'    >>> 'SKILL'

这些是损失

Losses {'ner': 721.8737016180717}
Losses {'ner': 5.999976082008388}
Losses {'ner': 5.970323057037423}
Losses {'ner': 5.996330579093365}
Losses {'ner': 6.028536462566022}
Losses {'ner': 12.043830573641666}
Losses {'ner': 10.001897952651317}
Losses {'ner': 6.016950026187274}
Losses {'ner': 6.624311646328313} 
Losses {'ner': 10.602919933949224}
Losses {'ner': 6.1062697231067995}
Losses {'ner': 8.792055106010444}
Losses {'ner': 13.302123281119345}
Losses {'ner': 6.068028368915684}
Losses {'ner': 8.026694430880903}
Losses {'ner': 8.961434860193798}
Losses {'ner': 6.02721516249698}
Losses {'ner': 9.714660156853073}
Losses {'ner': 4.108544494319015}
Losses {'ner': 6.023105974059858}
Losses {'ner': 7.357760648981275}
Losses {'ner': 6.295292869532734}
Losses {'ner': 3.8088561052881995}
Losses {'ner': 6.059279332644757}
Losses {'ner': 7.024559462190113}
Losses {'ner': 4.784358718788942}
Losses {'ner': 5.935101364429172}
Losses {'ner': 4.027772727507415}
Losses {'ner': 2.1748163004265884}
Losses {'ner': 5.993975825343896}

我在 pastebin 中包含了我的训练数据，可以在这里找到：

https://pastebin.com/JmQv7HRS

标签： pythonspacynamed-entity-recognition