Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100794635> ?p ?o ?g. }
- W3100794635 abstract "Two popular types of machine translation are phrase-based (PBMT) and neural machine translation (NMT) systems. Both of these types of machine translation systems are composed of multiple complex models or layers. Due to their complexity, it is difficult to explain why a system makes certain mistakes during translation or how it is capable of regenerating complex syntactic or semantic phenomena in the target language. Each of these models and layers learns different linguistic aspects of the source language. However, for some of these models and layers, it is not clear which linguistic phenomena are learned or how this information is learned. To shed light on what linguistic phenomena are captured by these systems, we analyze the behavior of important models in both systems. We consider phrase reordering models from PBMT to investigate which words from inside of a phrase have the biggest impact on the reordering behavior. Additionally, to contribute to the interpretability of NMT systems we study the behavior of the attention model, which is a key component in NMT systems and the closest model in functionality to phrase reordering models in phrase-based systems. The attention model together with the encoder hidden state representations form the main components to encode source side linguistic information in NMT. To this end, we also analyze the information captured in the encoder hidden state representations of an NMT system. We investigate the extent to which syntactic and lexical-semantic information from the source side is captured by hidden state representations of different NMT architectures." @default.
- W3100794635 created "2020-11-23" @default.
- W3100794635 creator A5046152715 @default.
- W3100794635 date "2020-01-01" @default.
- W3100794635 modified "2023-09-27" @default.
- W3100794635 title "An empirical analysis of phrase-based and neural machine translation." @default.
- W3100794635 cites W1481113913 @default.
- W3100794635 cites W1517947178 @default.
- W3100794635 cites W1597533204 @default.
- W3100794635 cites W1753482797 @default.
- W3100794635 cites W1787224781 @default.
- W3100794635 cites W179875071 @default.
- W3100794635 cites W179935507 @default.
- W3100794635 cites W1800356822 @default.
- W3100794635 cites W1902237438 @default.
- W3100794635 cites W1916559533 @default.
- W3100794635 cites W1969974515 @default.
- W3100794635 cites W1989705153 @default.
- W3100794635 cites W1996430422 @default.
- W3100794635 cites W2006969979 @default.
- W3100794635 cites W2018156128 @default.
- W3100794635 cites W2038721957 @default.
- W3100794635 cites W2049633694 @default.
- W3100794635 cites W2064675550 @default.
- W3100794635 cites W2081580037 @default.
- W3100794635 cites W2086202918 @default.
- W3100794635 cites W2095755718 @default.
- W3100794635 cites W2100664567 @default.
- W3100794635 cites W2101105183 @default.
- W3100794635 cites W2103318667 @default.
- W3100794635 cites W2106595396 @default.
- W3100794635 cites W2110168585 @default.
- W3100794635 cites W2116792345 @default.
- W3100794635 cites W2118090838 @default.
- W3100794635 cites W2119168550 @default.
- W3100794635 cites W2124807415 @default.
- W3100794635 cites W2126433015 @default.
- W3100794635 cites W2131367528 @default.
- W3100794635 cites W2132339004 @default.
- W3100794635 cites W2134237567 @default.
- W3100794635 cites W2136812632 @default.
- W3100794635 cites W2137463156 @default.
- W3100794635 cites W2141599568 @default.
- W3100794635 cites W2143995218 @default.
- W3100794635 cites W2146574666 @default.
- W3100794635 cites W2153508793 @default.
- W3100794635 cites W2153653739 @default.
- W3100794635 cites W2154124206 @default.
- W3100794635 cites W2156985047 @default.
- W3100794635 cites W2157331557 @default.
- W3100794635 cites W2158195707 @default.
- W3100794635 cites W2158953777 @default.
- W3100794635 cites W2159755860 @default.
- W3100794635 cites W2163561955 @default.
- W3100794635 cites W2171421863 @default.
- W3100794635 cites W2180952760 @default.
- W3100794635 cites W2194775991 @default.
- W3100794635 cites W2250418535 @default.
- W3100794635 cites W2250539671 @default.
- W3100794635 cites W2250861254 @default.
- W3100794635 cites W2250907725 @default.
- W3100794635 cites W2251369387 @default.
- W3100794635 cites W2251762107 @default.
- W3100794635 cites W2251994258 @default.
- W3100794635 cites W2292919134 @default.
- W3100794635 cites W2296283641 @default.
- W3100794635 cites W2398041834 @default.
- W3100794635 cites W2401082558 @default.
- W3100794635 cites W2413794162 @default.
- W3100794635 cites W2437005631 @default.
- W3100794635 cites W2508661145 @default.
- W3100794635 cites W2516649778 @default.
- W3100794635 cites W2525778437 @default.
- W3100794635 cites W2576713500 @default.
- W3100794635 cites W2594990650 @default.
- W3100794635 cites W2757291580 @default.
- W3100794635 cites W2760656271 @default.
- W3100794635 cites W2793165286 @default.
- W3100794635 cites W2888010645 @default.
- W3100794635 cites W2889326796 @default.
- W3100794635 cites W2892205701 @default.
- W3100794635 cites W2897507397 @default.
- W3100794635 cites W2906987001 @default.
- W3100794635 cites W2946232455 @default.
- W3100794635 cites W2946794439 @default.
- W3100794635 cites W2962777840 @default.
- W3100794635 cites W2962834107 @default.
- W3100794635 cites W2962911926 @default.
- W3100794635 cites W2963333747 @default.
- W3100794635 cites W2963403868 @default.
- W3100794635 cites W2963430224 @default.
- W3100794635 cites W2963499433 @default.
- W3100794635 cites W2963506925 @default.
- W3100794635 cites W2963598809 @default.
- W3100794635 cites W2963641561 @default.
- W3100794635 cites W2963807318 @default.
- W3100794635 cites W2963991316 @default.
- W3100794635 cites W2964045208 @default.
- W3100794635 cites W2964085268 @default.
- W3100794635 cites W2964121744 @default.