MARC보기
LDR02376nmm uu200421 4500
001000000331527
00520240805164549
008181129s2018 |||||||||||||||||c||eng d
020 ▼a 9780438301184
035 ▼a (MiAaPQ)AAI10929557
035 ▼a (MiAaPQ)arizona:16521
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0820 ▼a 401
1001 ▼a Chen, Yuan-Lu.
24510 ▼a Improving Neural Net Machine Translation Systems with Linguistic Information.
260 ▼a [S.l.] : ▼b The University of Arizona., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 91 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: A.
500 ▼a Adviser: Michael Hammond.
5021 ▼a Thesis (Ph.D.)--The University of Arizona, 2018.
520 ▼a Interlinear Glossed Text (IGT) is widely used in linguistic studies. In a form of Interlinear Glossed Text, the first line is a sentence of the language of interest, the second line is a word-by-word translation, annotated with relevant grammati
520 ▼a The innovation of the current work is to incorporate the gloss information of Interlinear Glossed Text data into neural net machine translation systems.
520 ▼a Critically, if the Gaelic data and the gloss data are combined in a specific way as the training data, which is named as Parallel-Partial treatment, the performance of the systems is improved significantly. The systems with Parallel-Partial trea
520 ▼a Moreover, the boosting effect of the Parallel-Partial treatment is consistent across different languages and across neural net machine translation systems with different hyper-parameter settings.
520 ▼a How theoretical linguistics may work hand in hand with natural language processing, and how neural net machine learning may exploit linguistics are important questions (Pater 2017). The current work also exemplifies how theoretical linguistics m
590 ▼a School code: 0009.
650 4 ▼a Linguistics.
690 ▼a 0290
71020 ▼a The University of Arizona. ▼b Linguistics.
7730 ▼t Dissertation Abstracts International ▼g 80-01A(E).
773 ▼t Dissertation Abstract International
790 ▼a 0009
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T15000949 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자