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 71–80 of 551 papers

TitleStatusHype
An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation—0
Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement—0
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings—0
PortaSpeech: Portable and High-Quality Generative Text-to-SpeechCode2
Graph Algorithms for Multiparallel Word AlignmentCode1
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions—0
Mitigating Language-Dependent Ethnic Bias in BERTCode0
English-Arabic Cross-language Plagiarism Detection—0
Optimizing Word Alignments with Better Subword Tokenization—0
Machine Translation with Pre-specified Target-side Words Using a Semi-autoregressive Model—0
Show:102550
← PrevPage 8 of 56Next →

Benchmark Results

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