"Finite state transducer"의 두 판 사이의 차이
둘러보기로 가기
검색하러 가기
Pythagoras0 (토론 | 기여) (→노트: 새 문단) |
Pythagoras0 (토론 | 기여) (→메타데이터: 새 문단) |
||
23번째 줄: | 23번째 줄: | ||
===소스=== | ===소스=== | ||
<references /> | <references /> | ||
+ | |||
+ | == 메타데이터 == | ||
+ | |||
+ | ===위키데이터=== | ||
+ | * ID : [https://www.wikidata.org/wiki/Q2166395 Q2166395] |
2020년 12월 26일 (토) 04:14 판
노트
위키데이터
- ID : Q2166395
말뭉치
- We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation.[1]
- The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor.[1]
- A finite state transducer essentially is a finite state automaton that works on two (or more) tapes.[2]
- A finite-state transducer (FST) is a finite-state machine with two memory tapes, following the terminology for Turing machines: an input tape and an output tape.[3]
- * that can be implemented as finite-state transducers are called rational relations.[3]
- Finite-state transducers are often used for phonological and morphological analysis in natural language processing research and applications.[3]
- Finite State Transducers can be weighted, where each transition is labelled with a weight in addition to the input and output labels.[3]
- In this article, we apply a hierarchical pipeline concept that composes Weighted Finite-State Transducers (WFST) together.[4]
- Weighted Finite-State Transducers WFST is good at modeling HMM and solving state machine problems.[4]
- A finite-state transducer (FST) has arcs labeling the input and output labels.[4]
- We can represent a rewrite rule as a regular relation and thus we can build a corresponding finite-state transducer.[5]
- So far we’ve learned that each rewrite rule is a binary regular string relation and that these relations can be represented by finite-state transducers.[5]
- We’ve seen how the rewrite rules can be represented as regular string relations which on the other hand have an equivalent formalism namely the finite-state transducers.[5]
- We introduce a framework for automatic differentiation with weighted finite-state transducers (WFSTs) allowing them to be used dynamically at training time.[6]
- One of the key ideas in this technology is to separate processing into several stages, in ``cascaded finite-state transducers.[7]
- In a finite-state transducer, an output entity is constructed when final states are reached, e.g., a representation of the information in a phrase.[7]
- In a cascaded finite-state transducer, there are different finite-state transducers at different stages.[7]
소스
- ↑ 1.0 1.1 A weighted finite state transducer translation template model for statistical machine translation
- ↑ 2.2 Finite State Transducers
- ↑ 3.0 3.1 3.2 3.3 Finite-state transducer
- ↑ 4.0 4.1 4.2 Speech Recognition — Weighted Finite-State Transducers (WFST)
- ↑ 5.0 5.1 5.2 Finite-State Transducers for Text Rewriting
- ↑ Differentiable Weighted Finite-State Transducers
- ↑ 7.0 7.1 7.2 Cascaded Finite-State Transducers
메타데이터
위키데이터
- ID : Q2166395