MALLET is a Java-based package for statistical natural language processing, document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.
I don't have domain knowledge about this algorithm, but it looks suspicious. I believe that either one of the nexTag is incorrect (maybe it should be nextStart?) or if it's not a bug, line 92 is dead code and should be removed to avoid confusion.
Hello, I noticed a potential bug in src/cc/mallet/pipe/SelectiveSGML2TokenSequence.java
On lines 92 and 93 of the file, we have:
I don't have domain knowledge about this algorithm, but it looks suspicious. I believe that either one of the nexTag is incorrect (maybe it should be nextStart?) or if it's not a bug, line 92 is dead code and should be removed to avoid confusion.