Hello, my name is Lee. I follow your step in Readme, but when I changed the training, test and raw embeddings data in the demo to my own data, the following error occurred.

Exception in thread "main" java.lang.IllegalStateException: Topic Inferencer: New topic not sampled.

The above problem arises when considering the words that exist in the testing documents but not in the training documents. The detailed error message is as follows:

Couldn't open cc.mallet.util.MalletLogger resources/logging.properties file.
Perhaps the 'resources' directories weren't copied into the 'class' directory.
Continuing.
java.lang.reflect.InaccessibleObjectException: Unable to make public jdk.internal.ref.Cleaner java.nio.DirectByteBuffer.cleaner() accessible: module java.base does not "opens java.nio" to unnamed module @2c6a3f77
at java.base/java.lang.reflect.AccessibleObject.checkCanSetAccessible(AccessibleObject.java:354)
at java.base/java.lang.reflect.AccessibleObject.checkCanSetAccessible(AccessibleObject.java:297)
at java.base/java.lang.reflect.Method.checkCanSetAccessible(Method.java:199)
at java.base/java.lang.reflect.Method.setAccessible(Method.java:193)
at com.jmatio.io.MatFileReader$1.run(MatFileReader.java:374)
at java.base/java.security.AccessController.doPrivileged(AccessController.java:318)
at com.jmatio.io.MatFileReader.clean(MatFileReader.java:366)
at com.jmatio.io.MatFileReader.read(MatFileReader.java:321)
at com.jmatio.io.MatFileReader.(MatFileReader.java:154)
at com.jmatio.io.MatFileReader.(MatFileReader.java:102)
at topicmodels.MetaLDAInferUnseen.main(MetaLDAInferUnseen.java:673)
Exception in thread "main" java.lang.IllegalStateException: Topic Inferencer: New topic not sampled.
at topicmodels.MetaLDAInferUnseen.getSampledDistribution(MetaLDAInferUnseen.java:266)
at topicmodels.MetaLDAInferUnseen.getInferredDistributions(MetaLDAInferUnseen.java:482)
at topicmodels.MetaLDAInferUnseen.main(MetaLDAInferUnseen.java:791)
inference with unseen words finished ...

when ignoring the words that exist in the testing documents but not in the training documents, it can run. But in the second inference mode, an error will be reported. Could you please help me?
Thanks very much!!!!!