FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W636587922> ?p ?o ?g. }

• W636587922 abstract "The purpose of language models is in general to capture and to model regularities of language, thereby capturing morphological, syntactical and distributional properties of word sequences in a given language. They play an important role in many successful applications of Natural Language Processing, such as Automatic Speech Recognition, Machine Translation and Information Extraction. The most successful approaches to date are based on n-gram assumption and the adjustment of statistics from the training data by applying smoothing and back-off techniques, notably Kneser-Ney technique, introduced twenty years ago. In this way, language models predict a word based on its n-1 previous words. In spite of their prevalence, conventional n-gram based language models still suffer from several limitations that could be intuitively overcome by consulting human expert knowledge. One critical limitation is that, ignoring all linguistic properties, they treat each word as one discrete symbol with no relation with the others. Another point is that, even with a huge amount of data, the data sparsity issue always has an important impact, so the optimal value of n in the n-gram assumption is often 4 or 5 which is insufficient in practice. This kind of model is constructed based on the count of n-grams in training data. Therefore, the pertinence of these models is conditioned only on the characteristics of the training text (its quantity, its representation of the content in terms of theme, date). Recently, one of the most successful attempts that tries to directly learn word similarities is to use distributed word representations in language modeling, where distributionally words, which have semantic and syntactic similarities, are expected to be represented as neighbors in a continuous space. These representations and the associated objective function (the likelihood of the training data) are jointly learned using a multi-layer neural network architecture. In this way, word similarities are learned automatically. This approach has shown significant and consistent improvements when applied to automatic speech recognition and statistical machine translation tasks. A major difficulty with the continuous space neural network based approach remains the computational burden, which does not scale well to the massive corpora that are nowadays available. For this reason, the first contribution of this dissertation is the definition of a neural architecture based on a tree representation of the output vocabulary, namely Structured OUtput Layer (SOUL), which makes them well suited for large scale frameworks. The SOUL model combines the neural network approach with the class-based approach. It achieves significant improvements on both state-of-the-art large scale automatic speech recognition and statistical machine translations tasks. The second contribution is to provide several insightful analyses on their performances, their pros and cons, their induced word space representation. Finally, the third contribution is the successful adoption of the continuous space neural network into a machine translation framework. New translation models are proposed and reported to achieve significant improvements over state-of-the-art baseline systems." @default.
• W636587922 created "2016-06-24" @default.
• W636587922 creator A5031817060 @default.
• W636587922 date "2012-12-20" @default.
• W636587922 modified "2023-09-23" @default.
• W636587922 title "Continuous space models with neural networks in natural language processing" @default.
• W636587922 cites W122584218 @default.
• W636587922 cites W1423339008 @default.
• W636587922 cites W145476170 @default.
• W636587922 cites W1489525520 @default.
• W636587922 cites W1503441655 @default.
• W636587922 cites W1530801890 @default.
• W636587922 cites W1549680097 @default.
• W636587922 cites W1580585137 @default.
• W636587922 cites W1585876329 @default.
• W636587922 cites W1589170661 @default.
• W636587922 cites W1589987964 @default.
• W636587922 cites W1590952807 @default.
• W636587922 cites W1593239840 @default.
• W636587922 cites W1612003148 @default.
• W636587922 cites W1644652583 @default.
• W636587922 cites W1772447446 @default.
• W636587922 cites W180685247 @default.
• W636587922 cites W1880262756 @default.
• W636587922 cites W1916559533 @default.
• W636587922 cites W1934041838 @default.
• W636587922 cites W1969974515 @default.
• W636587922 cites W1970689298 @default.
• W636587922 cites W1974515274 @default.
• W636587922 cites W1984635093 @default.
• W636587922 cites W1989705153 @default.
• W636587922 cites W1992300521 @default.
• W636587922 cites W1993882792 @default.
• W636587922 cites W1995875735 @default.
• W636587922 cites W1996903695 @default.
• W636587922 cites W2006969979 @default.
• W636587922 cites W2013540053 @default.
• W636587922 cites W2020382207 @default.
• W636587922 cites W2024903555 @default.
• W636587922 cites W2026487812 @default.
• W636587922 cites W2031284124 @default.
• W636587922 cites W2050971845 @default.
• W636587922 cites W2051840895 @default.
• W636587922 cites W2056590938 @default.
• W636587922 cites W2056859949 @default.
• W636587922 cites W2066558940 @default.
• W636587922 cites W2067438047 @default.
• W636587922 cites W2071315630 @default.
• W636587922 cites W2075201173 @default.
• W636587922 cites W2076094076 @default.
• W636587922 cites W2079145130 @default.
• W636587922 cites W2080018251 @default.
• W636587922 cites W2080373976 @default.
• W636587922 cites W2087735403 @default.
• W636587922 cites W2095958485 @default.
• W636587922 cites W2096072088 @default.
• W636587922 cites W2096253869 @default.
• W636587922 cites W2100506586 @default.
• W636587922 cites W2101105183 @default.
• W636587922 cites W2103078213 @default.
• W636587922 cites W2104032746 @default.
• W636587922 cites W2105402874 @default.
• W636587922 cites W2105865683 @default.
• W636587922 cites W2106346128 @default.
• W636587922 cites W2106459246 @default.
• W636587922 cites W2109664771 @default.
• W636587922 cites W2110485445 @default.
• W636587922 cites W2111142112 @default.
• W636587922 cites W2111305191 @default.
• W636587922 cites W2111355378 @default.
• W636587922 cites W2111798208 @default.
• W636587922 cites W2113788796 @default.
• W636587922 cites W2114211285 @default.
• W636587922 cites W2114858359 @default.
• W636587922 cites W2117130368 @default.
• W636587922 cites W2117827367 @default.
• W636587922 cites W2118186095 @default.
• W636587922 cites W2119168550 @default.
• W636587922 cites W2120480077 @default.
• W636587922 cites W2120779048 @default.
• W636587922 cites W2121227244 @default.
• W636587922 cites W2122228338 @default.
• W636587922 cites W2124807415 @default.
• W636587922 cites W2126784811 @default.
• W636587922 cites W2128076038 @default.
• W636587922 cites W2128201184 @default.
• W636587922 cites W2130437494 @default.
• W636587922 cites W2130917146 @default.
• W636587922 cites W2131462252 @default.
• W636587922 cites W2132109814 @default.
• W636587922 cites W2136922672 @default.
• W636587922 cites W2140343992 @default.
• W636587922 cites W2142843952 @default.
• W636587922 cites W2143719855 @default.
• W636587922 cites W2144790469 @default.
• W636587922 cites W2144879357 @default.
• W636587922 cites W2145482038 @default.
• W636587922 cites W2146574666 @default.
• W636587922 cites W2147152072 @default.
• W636587922 cites W2147243662 @default.

• next