Papers with sequence prediction
Sentiment Tagging with Partial Labels using Modular Architectures (P19-1)
Copied to clipboard
| Challenge: | Many NLP learning tasks can be decomposed into sub-tasks, each associated with a partial label. |
| Approach: | They propose a modular learning approach where sub-tasks are learned using functional modules . they propose 'learning with partial labels' approach that decomposes tasks into partial labels . |
| Outcome: | The proposed approach can simplify learning and reduce supervision efforts. |
From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction (P18-1)
Copied to clipboard
| Challenge: | equivalence between credit assignment problem and entropy regularized reinforcement learning is established . a wide range of successful sequence prediction algorithms have been developed . |
| Approach: | They propose to extend credit assignment in reward augmented maximum likelihood learning by credit assignment and entropy regularization. |
| Outcome: | The proposed algorithms outperform RAML and Actor-Critic on two benchmark datasets. |
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel (D19-1)
Copied to clipboard
| Challenge: | Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. |
| Approach: | They propose a new formulation of attention via the lens of the kernel which allows us to understand individual components of Transformer's attention. |
| Outcome: | The proposed model outperforms existing models on language understanding and sequence prediction tasks and is more efficient than existing models. |
Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | a novel generalization framework for visual temporal-aligned translation is proposed to transfer recognition skills to unseen performers . ambiguity in the visual sequence can hinder current methods for visual language translation . |
| Approach: | They propose a generalizable framework to transfer recognition skills to unseen performers . they use visual temporal-aligned translation to generate multiple words autoregressively . |
| Outcome: | The proposed framework is generalized to transfer recognition skills to unseen performers . it is compared with existing methods on lipreading and fingerspelling datasets . |
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on specialized DNA models trained for sequence prediction or evaluate biological knowledge using text-only questions. |
| Approach: | They propose a benchmark to evaluate general-purpose LLMs on sequence-based genome inference tasks. |
| Outcome: | The proposed benchmark outperforms baseline models on sequence-based genome inference tasks. |