| | # Word Split: Text Segmentation Tool |
| | |
| | -Word Split is a Java application for Java software developers. The application |
| | -provides a way to split conjoined words that lack punctuation into separate |
| | -words. The software is intended to split database column names into their |
| | -human-readable equivalent text. |
| | +Word Split is a Java application for Java software developers. The application provides a way to split conjoined words that lack punctuation into separate words. The software is intended to split database column names into their human-readable equivalent text. |
| | |
| | Word Split takes the following input files: |
| | |
| | * a probability lexicon, one word and probability per line (CSV format) |
| | * a list of conjoined phrases, one per line |
| | |
| | -Word Split will use the lexicon to separate the list of conjoined phrases. |
| | -The resulting segmented phrases are written to standard out. |
| | +Word Split will use the lexicon to separate the list of conjoined phrases. The resulting segmented phrases are written to standard out. |
| | |
| | ## Contents |