https://github.com/OpenNMT/OpenNMT-tf
Guided Alignment Training for Topic-Aware Neural Machine Translation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Word Alignment is the task of finding the correspondence between source and target words in a pair of sentences that are translations of each other.
Source: Neural Network-based Word Alignment through Score Aggregation
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Guided Alignment Training for Topic-Aware Neural Machine Translation
PortaSpeech: Portable and High-Quality Generative Text-to-Speech
Unsupervised Multilingual Alignment using Wasserstein Barycenter
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
Addressing the Rare Word Problem in Neural Machine Translation
Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation
Aligning and Prompting Everything All at Once for Universal Visual Perception
Frustratingly Easy Label Projection for Cross-lingual Transfer
Addressing the Rare Word Problem in Neural Machine Translation
LRS3-TED: a large-scale dataset for visual speech recognition
Multilingual Distributed Representations without Word Alignment
PortaSpeech: Portable and High-Quality Generative Text-to-Speech
Conditional Random Field Autoencoders for Unsupervised Structured Prediction
Addressing the Rare Word Problem in Neural Machine Translation
Addressing the Rare Word Problem in Neural Machine Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.