table of contents
- unstable 1.3.2-3
NGRAMSHRINK(1) | User Commands | NGRAMSHRINK(1) |
NAME¶
ngramshrink - Shrink ngram model from input model file.
DESCRIPTION¶
Shrink ngram model from input model file.
SYNOPSIS¶
ngramshrink [--options] [in.fst [out.fst]]
OPTIONS¶
--backoff_label: type = int64, default = 0
- Backoff label
--check_consistency: type = bool, default = false
- Check model consistency
--context_pattern: type = string, default = ""
- Pattern of contexts to prune
--count_pattern: type = string, default = ""
- Pattern of counts to prune
--method: type = string, default = "seymore"
- One of: "context_prune", "count_prune", "relative_entropy", "seymore"
--norm_eps: type = double, default = 0.001
- Normalization check epsilon
--shrink_opt: type = int32, default = 0
- Optimization level: Range 0 (fastest) to 2 (most accurate)
--target_number_of_ngrams: type = int64, default = -1
- Maximum number of ngrams to leave in model after pruning. Value less than zero means no target number, just use theta.
--theta: type = double, default = 0
- Pruning threshold theta
--total_unigram_count: type = double, default = -1
- Total unigram count
--help: type = bool, default = false
- show usage information
--helpshort: type = bool, default = false
- show brief usage information
--tmpdir: type = string, default = "/tmp"
- temporary directory
--v: type = int32, default = 0
- verbosity level
--fst_align: type = bool, default = false
- Write FST data aligned where appropriate
--fst_default_cache_gc: type = bool, default = true
- Enable garbage collection of cache
--fst_default_cache_gc_limit: type = int64, default = 1048576
- Cache byte size that triggers garbage collection
--fst_read_mode: type = string, default = "read"
- Default file reading mode for mappable files
--fst_verify_properties: type = bool, default = false
- Verify FST properties queried by TestProperties
--save_relabel_ipairs: type = string, default = ""
- Save input relabel pairs to file
--save_relabel_opairs: type = string, default = ""
- Save output relabel pairs to file
--end_symbol: type = string, default = "</s>"
- Class label for sentence start
--start_symbol: type = string, default = "<s>"
- Class label for sentence start
--fst_compat_symbols: type = bool, default = true
- Require symbol tables to match when appropriate
--fst_field_separator: type = string, default = " "
- Set of characters used as a separator between printed fields
--fst_error_fatal: type = bool, default = true
- FST errors are fatal; o.w. return objects flagged as bad: e.g., FSTs: kError property set, FST weights: not a Member()
--ngram_error_fatal: type = bool, default = true
- NGram errors are fatal; o.w. return objects flagged as bad: e.g., NGramModel::Error() returns true.
--fst_weight_parentheses: type = string, default = ""
- 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)
--fst_weight_separator: type = string, default = ","
- Character separator between printed composite weights; must be a single character
August 2017 | OpenGrm NGram library 1.3.2 |