SOTAVerified

Word Alignment

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

Papers

Showing 125 of 551 papers

TitleStatusHype
PortaSpeech: Portable and High-Quality Generative Text-to-SpeechCode2
Aligning and Prompting Everything All at Once for Universal Visual PerceptionCode2
Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal AlignmentCode2
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style TransferCode1
Mask-Align: Self-Supervised Neural Word AlignmentCode1
Multilingual Sentence Transformer as A Multilingual Word AlignerCode1
Improving Word Translation via Two-Stage Contrastive LearningCode1
Frustratingly Easy Label Projection for Cross-lingual TransferCode1
Improving Bilingual Lexicon Induction with Cross-Encoder RerankingCode1
Improving Word Translation via Two-Stage Contrastive LearningCode1
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic SpaceCode1
Attention is Not Only a Weight: Analyzing Transformers with Vector NormsCode1
Correspondence Matters for Video Referring Expression ComprehensionCode1
Conversational Word Embedding for Retrieval-Based Dialog SystemCode1
ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective FeedbackCode1
Graph Algorithms for Multiparallel Word AlignmentCode1
Cross-Align: Modeling Deep Cross-lingual Interactions for Word AlignmentCode1
End-to-End Slot Alignment and Recognition for Cross-Lingual NLUCode1
BinaryAlign: Word Alignment as Binary Sequence LabelingCode1
Image-Text Co-Decomposition for Text-Supervised Semantic SegmentationCode1
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word AlignmentCode1
Improving Translation Faithfulness of Large Language Models via Augmenting InstructionsCode1
Counterfactual Variable Control for Robust and Interpretable Question AnsweringCode1
CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object DetectionCode1
Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel CorporaCode1
Show:102550
← PrevPage 1 of 23Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@184.26Unverified
2Adv - Refine - CSLSP@181.7Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@182.94Unverified
2Adv - Refine - CSLSP@182.3Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@183.5Unverified
2Adv - Refine - CSLSP@183.3Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@183.23Unverified
2Adv - Refine - CSLSP@182.1Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@181.45Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@174.08Unverified
#ModelMetricClaimedVerifiedStatus
1Barycenter AlignmentP@184.65Unverified