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 5160 of 551 papers

TitleStatusHype
Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings0
Correspondence Matters for Video Referring Expression ComprehensionCode1
GERNERMED++: Transfer Learning in German Medical NLPCode0
Atril: an XML Visualization System for Corpus Texts0
Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word AlignmentCode0
Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine TranslationCode0
Structural Supervision for Word Alignment and Machine Translation0
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?0
Graph Neural Networks for Multiparallel Word Alignment0
Improving Word Translation via Two-Stage Contrastive LearningCode1
Show:102550
← PrevPage 6 of 56Next →

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