Class LmReaders
This software provides three main pieces of functionality:
(a) estimation of a language models from text inputs
(b) data structures for efficiently storing large collections of n-grams in
memory
(c) an API for efficient querying language models derived from n-gram
collections. Most of the techniques in the paper are described in
"Faster and Smaller N-gram Language Models" (Pauls and Klein 2011).
This software supports the estimation of two types of language models:
Kneser-Ney language models (Kneser and Ney, 1995) and Stupid Backoff language
models (Brants et al. 2007). Kneser-Ney language models can be estimated from
raw text by calling
createKneserNeyLmFromTextFiles(List, WordIndexer, int, File, ConfigOptions)
. This
can also be done from the command-line by calling main()
in
MakeKneserNeyArpaFromText
. See the examples
folder for a
script which demonstrates its use. A Stupid Backoff language model can be
read from a directory containing n-gram counts in the format used by Google's
Web1T corpus by calling readLmFromGoogleNgramDir(String, boolean, boolean)
.
Note that this software does not (yet) support building Google count
directories from raw text, though this can be done using SRILM.
Loading/estimating language models from text files can be very slow. This
software can use Java's built-in serialization to build language model
binaries which are both smaller and faster to load.
MakeLmBinaryFromArpa
and MakeLmBinaryFromGoogle
provide
main()
methods for doing this. See the examples
folder for scripts which demonstrate their use.
Language models can be read into memory from ARPA formats using
readArrayEncodedLmFromArpa(String, boolean)
and
readContextEncodedLmFromArpa(String)
. The "array encoding" versus
"context encoding" distinction is discussed in Section 4.2 of Pauls and Klein
(2011). Again, since loading language models from textual representations can
be very slow, they can be read from binaries using
readLmBinary(String)
. The interfaces for these language models can
be found in ArrayEncodedNgramLanguageModel
and
ContextEncodedNgramLanguageModel
. For examples of these interfaces in
action, you can have a look at PerplexityTest
.
We implement the HASH,HASH+SCROLL, and COMPRESSED language model
representations described in Pauls and Klein (2011) in this release. The
SORTED implementation may be added later. See HashNgramMap
and
CompressedNgramMap
for the implementations of the HASH and COMPRESSED
representations.
To speed up queries, you can wrap language models with caches (
ContextEncodedCachingLmWrapper
and
ArrayEncodedCachingLmWrapper
). These caches are described in section
4.1 of Pauls and Klein (2011). You should more or less always use these
caches, since they are faster and have modest memory requirements.
This software also support a java Map wrapper around an n-gram collection.
You can read a map wrapper using
readNgramMapFromGoogleNgramDir(String, boolean, WordIndexer)
.
ComputeLogProbabilityOfTextStream
provides a main()
method for computing the log probability of raw text.
Some example scripts can be found in the examples/
directory.
- Author:
- adampauls
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionstatic <W> void
createKneserNeyLmFromTextFiles
(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, File arpaOutputFile, ConfigOptions opts) Estimates a Kneser-Ney language model from raw text, and writes a file (in ARPA format).static <W> ArrayEncodedProbBackoffLm<W>
readArrayEncodedLmFromArpa
(LmReader<ProbBackoffPair, ArpaLmReaderCallback<ProbBackoffPair>> lmFile, boolean compress, WordIndexer<W> wordIndexer, ConfigOptions opts) Reads an array-encoded language model from an ARPA lm file.static ArrayEncodedProbBackoffLm<String>
readArrayEncodedLmFromArpa
(String lmFile, boolean compress) static <W> ArrayEncodedProbBackoffLm<W>
readArrayEncodedLmFromArpa
(String lmFile, boolean compress, WordIndexer<W> wordIndexer) static <W> ArrayEncodedProbBackoffLm<W>
readArrayEncodedLmFromArpa
(String lmFile, boolean compress, WordIndexer<W> wordIndexer, ConfigOptions opts, int lmOrder) static <W> ContextEncodedProbBackoffLm<W>
readContextEncodedKneserNeyLmFromTextFile
(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, ConfigOptions opts) Builds a context-encoded LM from raw text.static <W> ContextEncodedProbBackoffLm<W>
readContextEncodedKneserNeyLmFromTextFile
(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, ConfigOptions opts, File tmpFile) static <W> ContextEncodedProbBackoffLm<W>
readContextEncodedLmFromArpa
(LmReader<ProbBackoffPair, ArpaLmReaderCallback<ProbBackoffPair>> lmFile, WordIndexer<W> wordIndexer, ConfigOptions opts) static ContextEncodedProbBackoffLm<String>
readContextEncodedLmFromArpa
(String lmFile) static <W> ContextEncodedProbBackoffLm<W>
readContextEncodedLmFromArpa
(String lmFile, WordIndexer<W> wordIndexer) static <W> ContextEncodedProbBackoffLm<W>
readContextEncodedLmFromArpa
(String lmFile, WordIndexer<W> wordIndexer, ConfigOptions opts, int lmOrder) Reads a context-encoded language model from an ARPA lm file.static <W> StupidBackoffLm<W>
readGoogleLmBinary
(String file, WordIndexer<W> wordIndexer, String sortedVocabFile) Reads in a pre-built Google n-gram binary.static StupidBackoffLm<String>
readGoogleLmBinary
(String file, String sortedVocabFile) static <W> ArrayEncodedProbBackoffLm<W>
readKneserNeyLmFromTextFile
(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, boolean compress, ConfigOptions opts, File tmpFile) static <W> ArrayEncodedProbBackoffLm<W>
readKneserNeyLmFromTextFile
(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, ConfigOptions opts, boolean compress) Builds an array-encoded LM from raw text.static <W> NgramLanguageModel<W>
readLmBinary
(String file) Reads a binary file representing an LM.static ArrayEncodedNgramLanguageModel<String>
readLmFromGoogleNgramDir
(String dir, boolean compress, boolean kneserNey) static <W> ArrayEncodedNgramLanguageModel<W>
readLmFromGoogleNgramDir
(String dir, boolean compress, boolean kneserNey, WordIndexer<W> wordIndexer, ConfigOptions opts) Reads a stupid backoff lm from a directory with n-gram counts in the format used by Google n-grams.static NgramMapWrapper<String,
LongRef> readNgramMapFromBinary
(String binary, String vocabFile) static <W> NgramMapWrapper<W,
LongRef> readNgramMapFromBinary
(String binary, String sortedVocabFile, WordIndexer<W> wordIndexer) static NgramMapWrapper<String,
LongRef> readNgramMapFromGoogleNgramDir
(String dir, boolean compress) static <W> NgramMapWrapper<W,
LongRef> readNgramMapFromGoogleNgramDir
(String dir, boolean compress, WordIndexer<W> wordIndexer) static <W> void
writeLmBinary
(NgramLanguageModel<W> lm, String file) Writes a binary file representing the LM using the built-in serialization.
-
Constructor Details
-
LmReaders
public LmReaders()
-
-
Method Details
-
readContextEncodedLmFromArpa
-
readContextEncodedLmFromArpa
public static <W> ContextEncodedProbBackoffLm<W> readContextEncodedLmFromArpa(String lmFile, WordIndexer<W> wordIndexer) -
readContextEncodedLmFromArpa
public static <W> ContextEncodedProbBackoffLm<W> readContextEncodedLmFromArpa(String lmFile, WordIndexer<W> wordIndexer, ConfigOptions opts, int lmOrder) Reads a context-encoded language model from an ARPA lm file. Context-encoded language models allow faster queries, but require an extra 4-bytes of storage per n-gram for the suffix offsets (as compared to array-encoded language models).- Type Parameters:
W
-- Parameters:
lmFile
-compress
-wordIndexer
-opts
-lmOrder
-- Returns:
-
readContextEncodedLmFromArpa
public static <W> ContextEncodedProbBackoffLm<W> readContextEncodedLmFromArpa(LmReader<ProbBackoffPair, ArpaLmReaderCallback<ProbBackoffPair>> lmFile, WordIndexer<W> wordIndexer, ConfigOptions opts) -
readArrayEncodedLmFromArpa
public static ArrayEncodedProbBackoffLm<String> readArrayEncodedLmFromArpa(String lmFile, boolean compress) -
readArrayEncodedLmFromArpa
public static <W> ArrayEncodedProbBackoffLm<W> readArrayEncodedLmFromArpa(String lmFile, boolean compress, WordIndexer<W> wordIndexer) -
readArrayEncodedLmFromArpa
public static <W> ArrayEncodedProbBackoffLm<W> readArrayEncodedLmFromArpa(String lmFile, boolean compress, WordIndexer<W> wordIndexer, ConfigOptions opts, int lmOrder) -
readArrayEncodedLmFromArpa
public static <W> ArrayEncodedProbBackoffLm<W> readArrayEncodedLmFromArpa(LmReader<ProbBackoffPair, ArpaLmReaderCallback<ProbBackoffPair>> lmFile, boolean compress, WordIndexer<W> wordIndexer, ConfigOptions opts) Reads an array-encoded language model from an ARPA lm file.- Type Parameters:
W
-- Parameters:
lmFile
-compress
- Compress the LM using block compression. This LM should be smaller but slower.wordIndexer
-opts
-lmOrder
-- Returns:
-
readNgramMapFromGoogleNgramDir
public static NgramMapWrapper<String,LongRef> readNgramMapFromGoogleNgramDir(String dir, boolean compress) -
readNgramMapFromGoogleNgramDir
public static <W> NgramMapWrapper<W,LongRef> readNgramMapFromGoogleNgramDir(String dir, boolean compress, WordIndexer<W> wordIndexer) -
readNgramMapFromBinary
public static NgramMapWrapper<String,LongRef> readNgramMapFromBinary(String binary, String vocabFile) -
readNgramMapFromBinary
public static <W> NgramMapWrapper<W,LongRef> readNgramMapFromBinary(String binary, String sortedVocabFile, WordIndexer<W> wordIndexer) - Parameters:
sortedVocabFile
- should be the vocab_cs.gz file from the Google n-gram corpus.- Returns:
-
readLmFromGoogleNgramDir
public static ArrayEncodedNgramLanguageModel<String> readLmFromGoogleNgramDir(String dir, boolean compress, boolean kneserNey) -
readLmFromGoogleNgramDir
public static <W> ArrayEncodedNgramLanguageModel<W> readLmFromGoogleNgramDir(String dir, boolean compress, boolean kneserNey, WordIndexer<W> wordIndexer, ConfigOptions opts) Reads a stupid backoff lm from a directory with n-gram counts in the format used by Google n-grams.- Type Parameters:
W
-- Parameters:
dir
-compress
-wordIndexer
-opts
-- Returns:
-
readContextEncodedKneserNeyLmFromTextFile
public static <W> ContextEncodedProbBackoffLm<W> readContextEncodedKneserNeyLmFromTextFile(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, ConfigOptions opts) Builds a context-encoded LM from raw text. This call first builds and writes a (temporary) ARPA file by calling#createKneserNeyLmFromTextFiles(List, WordIndexer, int, File)
, and the reads the resulting file. Since the temp file can be quite large, it is important that the temp directory used by java (java.io.tmpdir
).- Type Parameters:
W
-- Parameters:
files
-wordIndexer
-lmOrder
-opts
-- Returns:
-
readKneserNeyLmFromTextFile
public static <W> ArrayEncodedProbBackoffLm<W> readKneserNeyLmFromTextFile(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, ConfigOptions opts, boolean compress) Builds an array-encoded LM from raw text. This call first builds and writes a (temporary) ARPA file by calling#createKneserNeyLmFromTextFiles(List, WordIndexer, int, File)
, and the reads the resulting file. Since the temp file can be quite large, it is important that the temp directory used by java (java.io.tmpdir
).- Type Parameters:
W
-- Parameters:
files
-wordIndexer
-lmOrder
-opts
-- Returns:
-
readContextEncodedKneserNeyLmFromTextFile
public static <W> ContextEncodedProbBackoffLm<W> readContextEncodedKneserNeyLmFromTextFile(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, ConfigOptions opts, File tmpFile) -
readKneserNeyLmFromTextFile
public static <W> ArrayEncodedProbBackoffLm<W> readKneserNeyLmFromTextFile(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, boolean compress, ConfigOptions opts, File tmpFile) -
createKneserNeyLmFromTextFiles
public static <W> void createKneserNeyLmFromTextFiles(List<String> files, WordIndexer<W> wordIndexer, int lmOrder, File arpaOutputFile, ConfigOptions opts) Estimates a Kneser-Ney language model from raw text, and writes a file (in ARPA format). Probabilities are in log base 10 to match SRILM.- Type Parameters:
W
-- Parameters:
files
- Files of raw text (new-line separated).wordIndexer
-lmOrder
-arpaOutputFile
-
-
readGoogleLmBinary
-
readGoogleLmBinary
public static <W> StupidBackoffLm<W> readGoogleLmBinary(String file, WordIndexer<W> wordIndexer, String sortedVocabFile) Reads in a pre-built Google n-gram binary. The user must supply thevocab_cs.gz
file (so that the corpus cannot be reproduced unless the user has the rights to do so).- Type Parameters:
W
-- Parameters:
file
- The binarywordIndexer
-sortedVocabFile
- thevocab_cs.gz
vocabulary file.- Returns:
-
readLmBinary
Reads a binary file representing an LM. These will need to be cast down to eitherContextEncodedNgramLanguageModel
orArrayEncodedNgramLanguageModel
to be useful. -
writeLmBinary
Writes a binary file representing the LM using the built-in serialization. These binaries should load much faster than ARPA files.- Type Parameters:
W
-- Parameters:
lm
-file
-
-