- Average Sentence Length: computes the average number of words per sentence.
- Common Lines: returns the common lines between two files.
- Levenshtein Filtering: filters sentences from a parallel file whose normalized edit distance is greater than 0.07.
- Parallel Shuffling: shuffles two parallel files.
- Repeated Lines: removes repeated lines from a file.
- TMX Reader: reads a file in tmx format.
- Vocabulary: returns a document's vocabulary.
- Translation Error Rate: computes TER.
- Word Error Rate: computes WER.
- Moses Scripts: a copy of the scripts included with Moses.
- Scatter Plotting: a tool for plotting BLEU values of different systems.
- Quality Estimation Tagger: generates word-level/phrase-level QE tags for a given translated text and its post-edited version.
- Statistical Dictionary: translates a text using an statistical dictionary.
- Approximate Randomization Testing: assesses the statistical significance of the difference in performance between two systems.
- Bootstrap Resampling: computes several metrics with their confidence interval using bootstrap resampling.
- Tokenizer: this tool provides several methods for de/tokenizing a sentence.