Selecting suitable model for creating Language Identification tool

Question

I am working on developing a tool for language identification of a given text i.e. given a sample text, identify the language (for e.g. English, Swedish, German, etc.) it is written in.

Now the strategy I have decided to follow (based on a few references I have gathered) are as follows -

a) Create a character n-gram model (The value of n is decided based on certain heuristics and computations)

b) Use a machine learning classifier(such as naive bayes) to predict the language of the given text.

Now, the doubt I have is - Is creating a character N-gram model necessary. As in, what disadvantage does a simple bag of words strategy have i.e. if I use all the words possible in the respective language to create a prediction model, what could be the possible cases where it would fail.

The reason why this doubt arose was the fact that any reference document/research paper I've come across states that language identification is a very difficult task. However, just using this strategy of using the words in the language seems to be a simple task.

EDIT: One reason why N-gram should be preferred is to make the model robust even if there are typos as stated here. Can anyone point out more?

Pierre · Answer 1 · 2014-08-12T10:31:12.970

1

Cavnar and Trenkle proposed a very simple yet efficient approach using character n-grams of variable length. Maybe you should try to implement it first and move to a more complex ML approach if C&T approach doesn't meet your requirements.

Basically, the idea is to build a language model using only the X (e.g. X = 300) most frequent n-grams of variable length (e.g. 1 <= N <= 5). Doing so, you are very likely to capture most functional words/morphemes of the considered language... without any prior linguistic knowledge on that language!

Why would you choose character n-grams over a BoW approach? I think the notion of character n-gram is pretty straightforward and apply to every written language. Word, is a much much complex notion which greatly differ from one language to another (consider languages with almost no spacing marks).

Reference: http://odur.let.rug.nl/~vannoord/TextCat/textcat.pdf

edited Aug 12 '14 at 10:31

answered Aug 12 '14 at 09:24

Pierre

1,204
8
15

What if the test data is heavily filled with typos, for instance "hello brother" is entered as "ello bro ther". I mean it might sound ridiculous, but the BoW strategy wont help in this case i guess. – alphacentauri Aug 12 '14 at 09:31
Exactly, it won't help. In contrast, the n-gram approach should perform quiet well here. – Pierre Aug 12 '14 at 09:43
1

However, if the data is noisy the language identification tool shouldn't be blamed for... – Pierre Aug 12 '14 at 09:44
Also a good ML library can make a vanilla NB/SVM classifier easier to implement than C&T's old custom algorithm. – Fred Foo Aug 12 '14 at 09:51
8-grams is severe overkill, with X=300 you will barely be getting into 4-grams. – tripleee Aug 12 '14 at 10:18
@triplee oh. it's 5 not 8. – Pierre Aug 12 '14 at 10:30

score 1 · Answer 2 · answered Aug 12 '14 at 09:44

if I use all the words possible in the respective language to create a prediction model, what could be the possible cases where it would fail

Pretty much the same cases were a character n-gram model would fail. The problem is that you're not going to find appropriate statistics for all possible words.(*) Character n-gram statistics are easier to accumulate and more robust, even for text without typos: words in a language tend to follow the same spelling patterns. E.g. had you not found statistics for the Dutch word "uitbuiken" (a pretty rare word), then the occurrence of the n-grams "uit", "bui" and "uik" would still be strong indicators of this being Dutch.

(*) In agglutinative languages such as Turkish, new words can be formed by stringing morphemes together and the number of possible words is immense. Check the first few chapters of Jurafsky and Martin, or any undergraduate linguistics text, for interesting discussions on the possible number of words per language.

tripleee · Answer 3 · 2014-08-12T11:43:00.283

The performance really depends on your expected input. If you will be classifying multi-paragraph text all in one language, a functional words list (which your "bag of words" with pruning of hapaxes will quickly approximate) might well serve you perfectly, and could work better than n-grams.

There is significant overlap between individual words -- "of" could be Dutch or English; "and" is very common in English but also means "duck" in the Scandinavian languages, etc. But given enough input data, overlaps for individual stop words will not confuse your algorithm very often.

My anecdotal evidence is from using libtextcat on the Reuters multilingual newswire corpus. Many of the telegrams contain a lot of proper names, loan words etc. which throw off the n-gram classifier a lot of the time; whereas just examining the stop words would (in my humble estimation) produce much more stable results.

On the other hand, if you need to identify short, telegraphic utterances which might not be in your dictionary, a dictionary-based approach is obviously flawed. Note that many North European languages have very productive word formation by free compounding -- you see words like "tandborstställbrist" and "yhdyssanatauti" being coined left and right (and Finnish has agglutination on top -- "yhdyssanataudittomienkinkohan") which simply cannot be expected to be in a dictionary until somebody decides to use them.

Selecting suitable model for creating Language Identification tool

3 Answers3