使用复数训练的 CRF 模型，不适用于单数

Question

我已经制作了一个 CRF 模型。我的数据集有 24 个类，此时我刚刚开始，所以我的训练数据只有 1200 个标记/语料库。我已经训练了模型。在我的训练数据中，我使用了复数形式的标记，例如地址、照片、州、国家等。

现在在测试时，如果我给这个模型以句子形式的复数标记，那么它工作得很好，但是如果我以单数形式输入我的句子，比如照片、状态等，那么它不会给它分配任何标签。

crf 的这种行为看起来很奇怪。我已经探索了NER Feature Factory 并使用了一些引理功能，但它也没有用。分享我的austen.prop 用于模型形成。

# location of the training file
trainFile = training_data_for_ner.txt
# location where you would like to save (serialize) your
# classifier; adding .gz at the end automatically gzips the file,
# making it smaller, and faster to load
serializeTo = ner-model.ser.gz

# structure of your training file; this tells the classifier that
# the word is in column 0 and the correct answer is in column 1
map = word=0,answer=1,pos=2,lemma=3

# This specifies the order of the CRF: order 1 means that features
# apply at most to a class pair of previous class and current class
# or current class and next class.
maxLeft=1

# these are the features we'd like to train with
# some are discussed below, the rest can be
# understood by looking at NERFeatureFactory
useClassFeature=true
useWord=true
# word character ngrams will be included up to length 6 as prefixes
# and suffixes only 
useNGrams=true
noMidNGrams=true
maxNGramLeng=6
usePrev=true
useNext=true
useDisjunctive=true
useSequences=true
usePrevSequences=true
# the last 4 properties deal with word shape features
useTypeSeqs=true
useTypeSeqs2=true
useTypeySequences=true
wordShape=chris2useLC
# newly added features.
useLemmas=true
usePrevNextLemmas=true
useLemmaAsWord=true
useTags=true

通过阅读 NER Feature Factory 添加了最后四个功能。如果有人能帮我解决这个问题，我将不胜感激。

Answer 1

您应该使用词干标记重新训练它。以https://github.com/stanfordnlp/CoreNLP/blob/master/src/edu/stanford/nlp/process/Stemmer.java（main方法）为例。