Bioinformatics: the machine learning approach
Bioinformatics: the machine learning approach
Statistical Language Learning
Zipf and Heaps Laws' Coefficients Depend on Language
CICLing '01 Proceedings of the Second International Conference on Computational Linguistics and Intelligent Text Processing
Increasing our ignorance of language: identifying language structure in an unknown 'signal'
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
| Hi-index | 0.00 |
This paper describes algorithms and software developed to characterise and detect generic intelligent language-like features in an input signal, using Natural Language Learning techniques: looking for characteristic statistical "language-signatures" in test corpora. As a first step towards such species-independent language-detection, we present a suite of programs to analyse digital representations of a range of data, and use the results to extrapolate whether or not there are language-like structures which distinguish this data from other sources, such as music, images, and white noise. We assume that generic species-independent communication can be detected by concentrating on localised patterns and rhythms, identifying segments at the level of characters, words and phrases, without necessarily having to "understand" the content.We assume that a language-like signal will be encoded symbolically, i.e. some kind of character-stream. Our language-detection algorithm for symbolic input uses a number of statistical clues: data compression ratio, "chunking" to find character bit-length and boundaries, and matching against a Zipfian type-token distribution for "letters" and "words". We do not claim extensive (let alone exhaustive) empirical evidence that our language-detection clues are "correct"; the only real test will come when the Search for Extra-Terrestrial Intelligence finds true alien signals. If and when true SETI signals are found, the first step to interpretation is to identify the language-like features, using techniques like the above. Our current research goal is to apply Natural Language Learning techniques to the identification of "higher-level" grammatical and semantic structure in a linguistic signal.