No article text was recorded for this version.
attention-alignment discrepancy
Version 2 of 265 papers76 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Saliency-driven Word Alignment Interpretation for Neural Machine Translation
- Blog: On the Word Alignment from Neural Machine Translation
- Blog: An Operation Sequence Model for Explainable Neural Machine Translation
- Blog: Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation
- Blog: Alignment-Enhanced Transformer for Constraining NMT with Pre-Specified Translations
- Blog: Neural Machine Translation with Supervised Attention
- Blog: Investigation of Transformer-based Latent Attention Models for Neural Machine Translation
- Blog: Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models
- Blog: Better Explain Transformers by Illuminating Important Information
- Blog: A Discriminative Neural Model for Cross-Lingual Word Alignment
- Blog: What does Attention in Neural Machine Translation Pay Attention to?
- Blog: Accurate Word Alignment Induction from Neural Machine Translation
- Blog: Weakly-Supervised Generation and Grounding of Visual Descriptions with Conditional Generative Models
- Blog: Hard Non-Monotonic Attention for Character-Level Transduction
- Blog: Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
- Blog: Silver Data for Coreference Resolution in Ukrainian: Translation, Alignment, and Projection
- Blog: Towards Enhancing Faithfulness for Neural Machine Translation
- Blog: Multilingual Neural Machine Translation with Task-Specific Attention
- Blog: Neural Machine Translation with Explicit Phrase Alignment
- Blog: Supervising Model Attention with Human Explanations for Robust Natural Language Inference
- Blog: An Operation Sequence Model for Explainable Neural Machine Translation
- Blog: INMT: Interactive Neural Machine Translation Prediction
- Blog: Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models
- Blog: Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
- Blog: Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
- Blog: Global Encoding for Abstractive Summarization
- Blog: Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning
- Blog: Latent Alignment and Variational Attention
- Blog: Supervised Attention for Sequence-to-Sequence Constituency Parsing
- Blog: Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
- Blog: Towards Neural Machine Translation with Partially Aligned Corpora
- Blog: Improving Sequence-to-Sequence Constituency Parsing
- Blog: Visual Agreement Regularized Training for Multi-Modal Machine Translation
- Blog: Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension
- Blog: Generating Alignments Using Target Foresight in Attention-Based Neural Machine Translation
- Blog: Neural Machine Translation Decoding with Terminology Constraints
- Blog: Saliency-driven Word Alignment Interpretation for Neural Machine Translation
- Blog: A Convolutional Encoder Model for Neural Machine Translation
- Blog: Neural Machine Translation with Adequacy-Oriented Learning
- Blog: Explicit Alignment Objectives for Multilingual Bidirectional Encoders
- Blog: Addressing the Under-Translation Problem from the Entropy Perspective
- Blog: Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator
- Blog: Entropy- and Distance-Regularized Attention Improves Low-Resource Neural Machine Translation
- Blog: On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation
- Blog: Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
- Blog: Six Challenges for Neural Machine Translation
- Blog: Neural Machine Translation with Supervised Attention
- Blog: Do Context-Aware Translation Models Pay the Right Attention?
- Blog: Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions
- Blog: P-Transformer: Towards Better Document-to-Document Neural Machine Translation
- Blog: Supervised Attentions for Neural Machine Translation
- Blog: LIG-CRIStAL Submission for the WMT 2017 Automatic Post-Editing Task
- Blog: Transformer-Based Direct Hidden Markov Model for Machine Translation
- Blog: A Dynamic Head Importance Computation Mechanism for Neural Machine Translation
- Blog: Explicit Alignment Learning for Neural Machine Translation
- Blog: Attention Calibration for Transformer in Neural Machine Translation
- Blog: A Convolutional Encoder Model for Neural Machine Translation
- Blog: Incorporating Discrete Translation Lexicons into Neural Machine Translation
- Blog: Compositional Generalization via Semantic Tagging
- Blog: Visual Agreement Regularized Training for Multi-Modal Machine Translation
Showing 60 of 65 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_attention_alignment_discrepancy_a6698418,
title = {attention-alignment discrepancy},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/attention-alignment-discrepancy/rdr_a6698418c53d4864a7402ce4158f03d0},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_attention_alignment_discrepancy_a6698418_v2,
title = {attention-alignment discrepancy},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/attention-alignment-discrepancy/rdr_a6698418c53d4864a7402ce4158f03d0/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}