ngrammake man page

ngrammake — make n-gram model from FST with raw counts

Synopsis

ngrammake [Options] [in.fst [out.fst]]

Description

Make a normalized n-gram model from an input FST with raw counts.

Options

Boolean options accept either true or false as a value, or the default value if neither value is specified.

--backoff[=BOOLEAN]

Use backoff smoothing instead of mixture.  Default: method-dependent.

--backoff_label=INT64

Backoff label.  Default: 0.

--bins=INT64

Number of bins for katz or absolute discounting.  Default: -1.

--check_consistency[=BOOLEAN]

Check model consistency.  Default: false.

--count_of_counts=FILENAME

Read count-of-counts from a file.  Default: do not read.

--discount_D=FLOAT

Absolute discount value D to use.  Default: -1.0.

--end_symbol=STRING

Class label for sentence end.  Default: "</s>".

--fst_align[=BOOLEAN]

Write FST data aligned where appropriate.  Default: false.

--fst_compat_symbols[=BOOLEAN]

Require symbol tables to match when appropriate.  Default: true.

--fst_default_cache_gc[=BOOLEAN]

Enable garbage collection of cache.  Default: true.

--fst_default_cache_gc_limit=INT64

Set the cache byte size that triggers garbage collection.  Default: 1048576.

--fst_error_fatal[=BOOLEAN]

If true, FST errors are fatal.  Otherwise, returned objects are flagged as bad. For example, FSTs are returned with the kError property set to true, and FST weights set so that Member() returns false.  Default: true.

--fst_field_separator=STRING

Set the characters used as a separator between printed fields.  Default: " ".

--fst_read_mode=STRING

Default file reading mode for mappable files, "read" to use read(2) or "map" to use mmap(2).  Default: "read".

--fst_verify_properties[=BOOLEAN]

Verify fst properties queried by TestProperties.  Default: false.

--fst_weight_parentheses=STRING

Set the characters enclosing the first weight of a printed composite weight (e.g., pair weight, tuple weight, and derived classes) to ensure proper I/O of nested composite weights.  Must have size 0 (none) or 2 (open and close parenthesis).  Default: no parentheses.

--fst_weight_separator=CHARACTER

Set the character separator between printed composite weights.  Default: comma.

--help[=BOOLEAN]

Show usage information.  Default: false.

--helpshort[=BOOLEAN]

Show brief usage information.  Default: false.

--interpolate[=BOOLEAN]

Use interpolated smoothing.  Default: method-dependent.

--method=STRING

One of "absolute", "katz", "kneser_ney", "presmoothed", "unsmoothed", "katz_frac", and "witten_bell".  Default: "katz".

--ngram_error_fatal[=BOOLEAN]

If true, NGram errors are fatal.  Otherwise, returned objects are flagged as bad; i.e., NGramModel::Error() returns true.  Default: true.

--norm_eps=FLOAT

Normalization check epsilon.  Default: 0.001.

--save_relabel_ipairs=FILENAME

Save input relabel pairs to file.  Default: do not save.

--save_relabel_opairs=FILENAME

Save output relabel pairs to file.  Default: do not save.

--start_symbol=STRING

Class label for sentence start.  Default: "<s>".

--tmpdir=PATHNAME

Set the temporary directory to use.  Default: /tmp.

--v[=INT32]

Set the verbosity level.  Default: 0.

--witten_bell_k=FLOAT

Witten-Bell hyperparameter K.  Default: 1.0.

See Also

ngramapply(1), ngramcontext(1), ngramcount(1), ngramhisttest(1), ngraminfo(1), ngrammarginalize(1), ngrammerge(1), ngramperplexity(1), ngramprint(1), ngramrandgen(1), ngramrandtest(1), ngramread(1), ngramshrink(1), ngramsort(1), ngramsplit(1), ngramsymbols(1), ngramtransfer(1)

Referenced By

ngramapply(1), ngramcontext(1), ngramcount(1), ngramhisttest(1), ngraminfo(1), ngrammarginalize(1), ngrammerge(1), ngramperplexity(1), ngramprint(1), ngramrandgen(1), ngramrandtest(1), ngramread(1), ngramshrink(1), ngramsort(1), ngramsplit(1), ngramsymbols(1), ngramtransfer(1).

1.3.2 OpenGrm NGram User Commands