From SpeechWiki

Revision as of 00:51, 27 July 2008

The design choices behind the various language models built on the Fisher Corpus are described below. The implementation uses the SRILM toolkit and some of the scripts are taken from this gigaword LM recipie. The main script is go_all.sh, and supporting scripts are here.

Source Text

The language model is built using only the repaired training data transcriptions, where each unique partial word is treated as a separate word.

N-gram order

2-gram, 3-gram and 4-gram models are built. 4-grams and more do not yield significant improvements and are not worth the extra computational resources they require in an ASR system, and essentially nothing is gained beyond 5-grams (.06 bits lower entropy, going from 4-grams to 5-grams<ref name="goodman2001abit"/>) .

Vocab Sizes

The LMs generated use only N most frequent words, mapping the rest to the UNK token. Where N is:

Which of these sizes will actually be used in the recognizer still remains to be seen.

Smoothing

Modified Kneser-Ney is used, since it performs best across a variety of n-gram counts, and training corpora sizes<ref name="chen1998empirical">Stanley Chen and Joshua Goodman. An empirical study of smoothing techniques for language modeling. Technical report TR-10-98, Harvard University, August 1998.</ref>.

Some experiments

Model Quality

The model quality is reported as the cross-entropy per word: The expected value with respect to the tests data of the log probablity estimated from the training data, divided by the number of tokens in the test corpus. See Perplexity for more details. The percentage of tokens in the test data that does not occur in the vocabulary (out of vocabulary %) is also reported.

The following table shows the cross entropy of models with no n-gram pruning at all: the only pruning that takes place is the vocabulary restriction

Pruning

To make the language model smaller, it is common to drop n-grams which occur less than k times,

Differences between ngram-count and make-big-lm

There is some subtle difference between ngram-count and make-big-lm, which I cannot track down.

make-big-lm -name .big -order 3 -sort -read ./LM/counts/ngrams -kndiscount -lm try -unk -debug 1

and

ngram-count -order 3 -read LM/counts/ngrams -kn1 LM/counts/kn1-3.txt -kn2 LM/counts/kn2-3.txt -kn3 LM/counts/kn3-3.txt -kn4 LM/counts/kn4-3.txt -kn5 LM/counts/kn5-3.txt -kn6 LM/counts/kn6-3.txt -kn7 LM/counts/kn7-3.txt -kn8 LM/counts/kn8-3.txt -kn9 LM/counts/kn9-3.txt -kndiscount1 -kndiscount2 -lm try -interpolate -debug 1

give different results, even though the KN discounts are identical in both case above.

ngram-count seems to do better on vocab sizes < 20k, and make-big-lm is slightly better on the full vocab.

I suspect it has something to do with make-big-lm allocating .05 of total probability to the unk token for some reason, while ngram-count allocates almost nothing to it.

Comparing the following table against the models in #Model Quality section.

Caching, Clustering and all that

Not worth trying due to trigrams being fairly space efficient (See 11.2 All hope abandon, ye who enter here in <ref name="goodman2001abit">Joshua Goodman. A Bit of Progress in Language Modeling, Extended Version Microsoft Research Technical Report MSR-TR-2001-72.</ref>).

In particular, they have this to say about the best smoothing strategy they themselves have developed:

"Kneser-Ney smoothing leads to improvements in theory, but in practice, most language models are built with high count cutoffs, to conserve space, and speed the search; with high count cutoffs, smoothing doesn’t matter."

<references/>