Statistical machine translation (SMT) was a machine translation approach, that superseded the previous, rule-based approach because it required explicit description of each and every linguistic rule, which was costly, and which often did not generalize to other languages. Since 2003, the statistical approach itself has been gradually superseded by the deep learning-based neural network approach.
The first ideas of statistical machine translation were introduced by Warren Weaver in 1949, including the ideas of applying Claude Shannon's information theory. Statistical machine translation was re-introduced in the late 1980s and early 1990s by researchers at IBM's Thomas J. Watson Research Center
The idea behind statistical machine translation comes from information theory. A document is translated according to the probability distribution that a string in the target language (for example, English) is the translation of a string in the source language (for example, French).
The problem of modeling the probability distribution has been approached in a number of ways. One approach which lends itself well to computer implementation is to apply Bayes Theorem, that is , where the translation model is the probability that the source string is the translation of the target string, and the language model is the probability of seeing that target language string. This decomposition is attractive as it splits the problem into two subproblems. Finding the best translation is done by picking up the one that gives the highest probability:
For a rigorous implementation of this one would have to perform an exhaustive search by going through all strings in the native language. Performing the search efficiently is the work of a machine translation decoder that uses the foreign string, heuristics and other methods to limit the search space and at the same time keeping acceptable quality. This trade-off between quality and time usage can also be found in speech recognition.
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Translation is the communication of the meaning of a source-language text by means of an equivalent target-language text. The English language draws a terminological distinction (which does not exist in every language) between translating (a written text) and interpreting (oral or signed communication between users of different languages); under this distinction, translation can begin only after the appearance of writing within a language community.
A parallel text is a text placed alongside its translation or translations. Parallel text alignment is the identification of the corresponding sentences in both halves of the parallel text. The Loeb Classical Library and the Clay Sanskrit Library are two examples of dual-language series of texts. Reference Bibles may contain the original languages and a translation, or several translations by themselves, for ease of comparison and study; Origen's Hexapla (Greek for "sixfold") placed six versions of the Old Testament side by side.
A cache language model is a type of statistical language model. These occur in the natural language processing subfield of computer science and assign probabilities to given sequences of words by means of a probability distribution. Statistical language models are key components of speech recognition systems and of many machine translation systems: they tell such systems which possible output word sequences are probable and which are improbable.
The Human Language Technology (HLT) course introduces methods and applications for language processing and generation, using statistical learning and neural networks.
Le cours est une introduction à la théorie des valeurs extrêmes et son utilisation pour la gestion des risques hydrologiques (essentiellement crues). Une ouverture plus large sur la gestion des danger
The student has been exposed to the use of modelling, coding, and visualization as a means to understand a research problem more deeply.
The student will have experience in symbolic and numerical of M
Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...
The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...
The design and implementation of efficient concurrent data structures has seen significant attention. However, most of this work has focused on concurrent data structures providing good worst-case guarantees, although, in real workloads, objects are often ...