MARC보기
LDR02042nmm uu200421 4500
001000000334202
00520240805175330
008181129s2018 |||||||||||||||||c||eng d
020 ▼a 9780438178175
035 ▼a (MiAaPQ)AAI10828817
035 ▼a (MiAaPQ)washington:18951
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0820 ▼a 004
1001 ▼a Jaech, Aaron.
24510 ▼a Low-Rank RNN Adaptation for Context-Aware Language Modeling.
260 ▼a [S.l.] : ▼b University of Washington., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 124 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
500 ▼a Adviser: Mari Ostendorf.
5021 ▼a Thesis (Ph.D.)--University of Washington, 2018.
520 ▼a A long-standing weakness of statistical language models is that their performance drastically degrades if they are used on data that varies even slightly from the data on which they were trained. In practice, applications require the use of adap
520 ▼a The current standard approach to recurrent neural network language model adaptation is to apply a simple linear shift to the recurrent and/or output layer bias vector. Although this is helpful, it does not go far enough. This thesis introduces a
520 ▼a In our experiments on several different datasets and multiple types of context, the increased adaptation of the recurrent layer is always helpful, as measured by perplexity, the standard for evaluating language models. We also demonstrate impact
590 ▼a School code: 0250.
650 4 ▼a Computer science.
650 4 ▼a Statistics.
690 ▼a 0984
690 ▼a 0463
71020 ▼a University of Washington. ▼b Electrical Engineering.
7730 ▼t Dissertation Abstracts International ▼g 79-12B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0250
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14999220 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자