paper-with-me

홈 › Papers

Improving Conditioning in Context-Aware Sequence to Sequence Models

2019-11-21 · Xinyi Wang, Jason Weston, Michael Auli, Yacine Jernite

Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on cases where generation is conditioned on both a short query and a long context, such as abstractive question answering or document-level translation. We modify the standard sequence-to-sequence approach to make better use of both the query and the context by expanding the conditioning mechanism to intertwine query and context attention. We also introduce a simple and efficient data augmentation method for the proposed model. Experiments on three different tasks show that both changes lead to consistent improvements.

📄 PDF Abstract BibTeX arXiv:1911.09728

Code (0)

등록된 구현이 없습니다.

Tasks

abstractive question answeringData AugmentationOpen-Domain Question AnsweringQuestion AnsweringTranslation

Similar Papers 제목 키워드 기반

Diverse Pretrained Context Encodings Improve Document Translation

2021-06-07 · ACL 2021 5 · Domenic Donato, Lei Yu, Chris Dyer

We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different…

Document TranslationSentenceTranslation

MIMIC: A Generative Multimodal Foundation Model for Biomolecules

2026-04-27 · Siavash Golkar, Jake Kovalic, Irina Espejo Morales, Samuel Sledzieski 외 arxiv

Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models in biology are trained within one modality or for a fixed forward t…

Representation Learning

Purposer: Putting Human Motion Generation in Context

2024-04-19 · Nicolas Ugrinovic, Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel 외

We present a novel method to generate human motion to populate 3D indoor scenes. It can be controlled with various combinations of conditioning signals such as a path in a scene, target poses, past motions, and scenes re…

Motion GenerationRepresentation Learning

KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates

2026-04-14 · Yudong Li, Jiawei Cai, Linlin Shen arxiv

Standard Large Language Model (LLM) pre-training typically treats corpora as flattened token sequences, often overlooking the real-world context that humans naturally rely on to contextualize information. To bridge this …

SiDGen: Structure-informed Diffusion for Generative modeling of Ligands for Proteins

2025-11-12 · Samyak Sanghvi, Nishant Ranjan, Tarak Karmakar arxiv

Structure-based drug design (SBDD) faces a fundamental scaling fidelity dilemma: rich pocket-aware conditioning captures interaction geometry but can be costly, often scales quadratically ($O(L^2)$) or worse with protein…