Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text
Generation via Concentrating Attention

Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention

14 November 2022

Jinyi Hu

Maosong Sun

Xing Xie

Papers citing "Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention"

7 / 7 papers shown

Title
Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering Zhe-nan Lin Yitao Cai Xiaojun Wan 30 13 0 15 Sep 2021
Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems Potsawee Manakul Mark J. F. Gales 11 5 0 08 Sep 2021
ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation Qingxiu Dong Xiaojun Wan Yue Cao 89 35 0 21 Jan 2021
On-the-Fly Attention Modulation for Neural Generation Yue Dong Chandra Bhagavatula Ximing Lu Jena D. Hwang Antoine Bosselut Jackie C.K. Cheung Yejin Choi 35 11 0 02 Jan 2021
Big Bird: Transformers for Longer Sequences Manzil Zaheer Guru Guruganesh Kumar Avinava Dubey Joshua Ainslie Chris Alberti ... Philip Pham Anirudh Ravula Qifan Wang Li Yang Amr Ahmed VLM 249 1,982 0 28 Jul 2020
Efficient Content-Based Sparse Attention with Routing Transformers Aurko Roy M. Saffar Ashish Vaswani David Grangier MoE 228 578 0 12 Mar 2020
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 247 9,042 0 06 Jun 2015