https://github.com/072jiajia/image-text-co-decomposition
공식 코드Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
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.
Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
Counterfactual Variable Control for Robust and Interpretable Question Answering
Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models
SilverAlign: MT-Based Silver Data Algorithm For Evaluating Word Alignment
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
Bilingual Lexicon Induction through Unsupervised Machine Translation
Improving Bilingual Lexicon Induction with Cross-Encoder Reranking
Improving Word Translation via Two-Stage Contrastive Learning
Self-Augmented In-Context Learning for Unsupervised Word Translation
Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval
CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
Frustratingly Easy Label Projection for Cross-lingual Transfer
An Operation Sequence Model for Explainable Neural Machine Translation
Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.