paper-with-me

홈 › Papers

Generative Bridging Network for Neural Sequence Prediction

2018-06-01 · NAACL 2018 6 · Wenhu Chen, Guanlin Li, Shuo Ren, Shujie Liu, Zhirui Zhang, Mu Li, Ming Zhou

In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE directly maximizing the conditional likelihood, the bridge extends the point-wise ground truth to a bridge distribution conditioned on it, and the generator is optimized to minimize their KL-divergence. Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN, are proposed to penalize confidence, enhance language smoothness and relieve learning burden. Experiments conducted on two recognized sequence prediction tasks (machine translation and abstractive text summarization) show that our proposed GBNs can yield significant improvements over strong baselines. Furthermore, by analyzing samples drawn from different bridges, expected influences on the generator are verified.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text SummarizationImage CaptioningLanguage ModelingLanguage ModellingMachine TranslationPredictionSpeech RecognitionSpelling CorrectionText SummarizationTranslation

Similar Papers 제목 키워드 기반

Generative Bridging Network in Neural Sequence Prediction

2017-06-28 · Wenhu Chen, Guanlin Li, Shuo Ren, Shujie Liu 외

In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is intro…

Abstractive Text SummarizationLanguage ModelingLanguage ModellingMachine Translation+3

A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches

2024-01-26 · Ruibo Ming, Zhewei Huang, Jingwei Wu, Zhuoxuan Ju 외

Future Frame Synthesis (FFS, aka Video Frame Prediction) focuses on generating future frame sequences conditioned on existing content. This survey provides a comprehensive review of existing research on FFS, covering com…

SurveyVideo Prediction

Electron flow matching for generative reaction mechanism prediction obeying conservation laws

2025-02-18 · Joonyoung F. Joung, Mun Hong Fong, Nicholas Casetti, Jordan P. Liles 외

Central to our understanding of chemical reactivity is the principle of mass conservation, which is fundamental for ensuring physical consistency, balancing equations, and guiding reaction design. However, data-driven co…

Prediction

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

2025-09-18 · Yuming Jiang, Siteng Huang, Shengke Xue, Yaxi Zhao 외 arxiv

This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pretraining methodology. The first stage, E…

Robot Manipulation

Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings

2017-11-15 · ACL 2018 7 · Shaohui Kuang, Junhui Li, António Branco, Weihua Luo 외

In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations betwe…

Machine TranslationSentenceTranslationWord Embeddings