Language identification

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Language identification is the process of determining which natural language given content is in. Traditionally, identification of written language - as practiced, for instance, in library science - has relied on manually identifying frequent words and letters known to be characteristic of particular languages. More recently, computational approaches have been applied to the problem, by viewing language identification as a special case of text categorization, a Natural Language Processing approach that relies on statistical methods.

Non-computational approaches[edit]

In the field of library science, language identification is important for categorizing materials. As librarians often have to categorize materials which are in languages they are not familiar with, they sometimes rely on tables of frequent words and distinctive letters or characters to help them identify languages. While identifying a single such word or character may not suffice to distinguish a language from another with a similar orthography, identifying several is often highly reliable.

Statistical approaches[edit]

There are several statistical approaches to language identification using different techniques to classify the data. One technique is to compare the compressibility of the text to the compressibility of texts in a set of known languages. This approach is known as mutual information based distance measure. The same technique can also be used to empirically construct family trees of languages which closely correspond to the trees constructed using historical methods. Mutual information based distance measure is essentially equivalent to more conventional model-based methods and is not generally considered to be either novel or better than simpler techniques. Bennedetto, et al's work has largely been discredited as relatively naive and inaccurate.

Another technique, as described by Cavnar and Trenkle (1994) and Dunning (1994) is to create a language n-gram model from a "training text" for each of the languages. These models can be based on characters (Cavnar and Trenkle) or encoded bytes (Dunning); in the latter, language identification and character encoding detection are integrated. Then, for any piece of text needing to be identified, a similar model is made, and that model is compared to each stored language model. The most likely language is the one with the model that is most similar to the model from the text needing to be identified. This approach can be problematic when the input text is in a language for which there is no model. In that case, the method may return another, "most similar" language as its result. Also problematic for any approach are pieces of input text that are composed of several languages, as is common on the Web.

For a more recent method, see Řehůřek and Kolkus (2009). This method can detect multiple languages in an unstructured piece of text and works robustly on short texts of only a few words: something that the n-gram approaches struggle with.

An older statistical method by Grefenstette was based on the prevalence of certain function words (e.g., "the" in English).


See also[edit]

External links[edit]


Web services[edit]