FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W7883548> ?p ?o ?g. }

• W7883548 abstract "Language modeling plays a critical role in natural language processing and understanding. Starting from a general structure, language models are able to learn natural language patterns from rich input data. However, the state-of-the-art language models only take advantage of words themselves, which are not sufficient to characterize the language. In this thesis, we improve recurrent neural network language models (RNNLM) by training them with additional information. Different methods of integrating the different types of additional information into RNNLMs are proposed in this thesis. All the potential information beyond the word itself that can be used to characterize the language is called meta-information. In this thesis, we propose to use different types of meta-information to represent languages such as discourse level information, which is reflected from the whole discourse, sentence level information which characterize the patterns of sentences and morphological information which represents the word from different perspectives. For example, we consider the following Dutch paragraph. represents sentence beginning. stands for the sentence ending. kan allemaal nog natuurlijk maar ze ontlopen dan de groepswinnaar in elk geval in de kwartfinale en vooral Nederland wil graag in Rotterdam die kwartfinale spelen en dan moet er groepswinst behaald worden anders verhuizen ze naar Brugge en krijgt het Jan Breydelstadion Oranje dus op bezoek we gaan er even uit slotfase zit eraan te komen twee minuten nog tot het einde plus de toegevoegde tijd dat is uh toch nog ook wel een paar minuten denk ik maar de wedstrijd is gespeeld On the discourse level, this paragraph is labeled as “Live commentaries (broadcast)” from the socio-situational setting (SSS) perspective and “sport” from the topic perspective. On the sentence level, each word except for the beginning word and ending word , is annotated with its preceding word information and succeeding word information. For example, we consider word “slotfase” in the following sentence. slotfase zit eraan te komen . This word has preceding information “ ” and succeeding information “zit eraan te komen ”. On the word level, the word “slotfase” is annotated by a vector containing some of the proposed meta-information. On the discourse level, we investigate classification methods for socio-situational settings and topics. On the sentence level, in this thesis, we focus on information such as succeeding words information and whole sentence information. In this thesis, each word is annotated by a vector containing the meta-information collected. Different methods are proposed in this thesis to integrate the meta-information into language models. On the discourse level, a curriculum learning method has been used to combine the socio-situational settings and topics. On the sentence level, forward-backward recurrent neural network language models have been proposed to integrate the succeeding word information and whole sentence information into language models. On the word level, each word has been conditioned on its preceding words as well as on preceding meta-information. The results reported in this thesis show that meta-information can be used to improve the effectiveness of language models at the cost of increasing training time. In this thesis, we address this problem by applying parallel processing techniques. A subsampling stochastic gradient descent algorithm has been proposed to accelerate the training of recurrent neural network language models." @default.
• W7883548 created "2016-06-24" @default.
• W7883548 creator A5085953379 @default.
• W7883548 date "2014-03-11" @default.
• W7883548 modified "2023-10-03" @default.
• W7883548 title "Language Models With Meta-information" @default.
• W7883548 cites W109703299 @default.
• W7883548 cites W115367774 @default.
• W7883548 cites W1269315465 @default.
• W7883548 cites W143396524 @default.
• W7883548 cites W1494910745 @default.
• W7883548 cites W1497703589 @default.
• W7883548 cites W1520968739 @default.
• W7883548 cites W1528470941 @default.
• W7883548 cites W1531910480 @default.
• W7883548 cites W153786144 @default.
• W7883548 cites W1540578583 @default.
• W7883548 cites W1551447917 @default.
• W7883548 cites W15592790 @default.
• W7883548 cites W1574901103 @default.
• W7883548 cites W1575384945 @default.
• W7883548 cites W1576169408 @default.
• W7883548 cites W1590952807 @default.
• W7883548 cites W1597533204 @default.
• W7883548 cites W1614298861 @default.
• W7883548 cites W1625504505 @default.
• W7883548 cites W1644652583 @default.
• W7883548 cites W1660390307 @default.
• W7883548 cites W170853248 @default.
• W7883548 cites W1790062158 @default.
• W7883548 cites W1798551699 @default.
• W7883548 cites W179875071 @default.
• W7883548 cites W180685247 @default.
• W7883548 cites W1850668662 @default.
• W7883548 cites W1880262756 @default.
• W7883548 cites W1923581016 @default.
• W7883548 cites W1934041838 @default.
• W7883548 cites W1956203405 @default.
• W7883548 cites W1965154800 @default.
• W7883548 cites W1970655904 @default.
• W7883548 cites W1970689298 @default.
• W7883548 cites W1972099155 @default.
• W7883548 cites W1983578042 @default.
• W7883548 cites W1983774533 @default.
• W7883548 cites W1984635093 @default.
• W7883548 cites W1985384830 @default.
• W7883548 cites W1985676901 @default.
• W7883548 cites W1989705153 @default.
• W7883548 cites W1990387894 @default.
• W7883548 cites W1992300521 @default.
• W7883548 cites W1993191067 @default.
• W7883548 cites W1996903695 @default.
• W7883548 cites W1999965501 @default.
• W7883548 cites W2016871293 @default.
• W7883548 cites W2018616927 @default.
• W7883548 cites W2020073413 @default.
• W7883548 cites W2020294948 @default.
• W7883548 cites W2020382207 @default.
• W7883548 cites W2022564164 @default.
• W7883548 cites W2026577970 @default.
• W7883548 cites W2027582570 @default.
• W7883548 cites W2030335114 @default.
• W7883548 cites W2032558547 @default.
• W7883548 cites W2038201841 @default.
• W7883548 cites W2040711288 @default.
• W7883548 cites W2044340178 @default.
• W7883548 cites W2046224275 @default.
• W7883548 cites W2049469158 @default.
• W7883548 cites W2049901611 @default.
• W7883548 cites W2050971845 @default.
• W7883548 cites W2056250865 @default.
• W7883548 cites W2056424040 @default.
• W7883548 cites W2061271742 @default.
• W7883548 cites W2066243589 @default.
• W7883548 cites W2072223048 @default.
• W7883548 cites W2074216031 @default.
• W7883548 cites W2074459654 @default.
• W7883548 cites W2075201173 @default.
• W7883548 cites W2079145130 @default.
• W7883548 cites W2079656678 @default.
• W7883548 cites W2084084380 @default.
• W7883548 cites W2084168002 @default.
• W7883548 cites W2092286949 @default.
• W7883548 cites W2096072088 @default.
• W7883548 cites W2096175520 @default.
• W7883548 cites W2096375461 @default.
• W7883548 cites W2097333193 @default.
• W7883548 cites W2099345940 @default.
• W7883548 cites W2100506586 @default.
• W7883548 cites W2100714283 @default.
• W7883548 cites W2102439588 @default.
• W7883548 cites W2109722477 @default.
• W7883548 cites W2110485445 @default.
• W7883548 cites W2110575115 @default.
• W7883548 cites W2111305191 @default.
• W7883548 cites W2112874453 @default.
• W7883548 cites W2116353118 @default.
• W7883548 cites W2118585731 @default.
• W7883548 cites W2118792877 @default.
• W7883548 cites W2119821739 @default.

• next