paper-with-me

홈 › Papers

PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation

2022-03-17 · ACL 2022 5 · Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, Lifu Huang

Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent high-level logical flow. In this work, we propose PLANET, a novel generation framework leveraging autoregressive self-attention mechanism to conduct content planning and surface realization dynamically. To guide the generation of output sentences, our framework enriches the Transformer decoder with latent representations to maintain sentence-level semantic plans grounded by bag-of-words. Moreover, we introduce a new coherence-based contrastive learning objective to further improve the coherence of output. Extensive experiments are conducted on two challenging long-form text generation tasks including counterargument generation and opinion article generation. Both automatic and human evaluations show that our method significantly outperforms strong baselines and generates more coherent texts with richer contents.

📄 PDF Abstract BibTeX arXiv:2203.09100

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningDecoderFormSentenceText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Contrastive Learning 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning

2024-07-26 · Mostafa Kotb, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter

Inspired by the success of the Transformer architecture in natural language processing and computer vision, we investigate the use of Transformers in Reinforcement Learning (RL), specifically in modeling the environment'…

continuous-controlContinuous ControlModel Predictive ControlQ-Learning+1

PlaNet-ClothPick: Effective Fabric Flattening Based on Latent Dynamic Planning

2023-03-02 · Halid Abdulrahim Kadi, Kasim Terzic

Why do Recurrent State Space Models such as PlaNet fail at cloth manipulation tasks? Recent work has attributed this to the blurry prediction of the observation, which makes it difficult to plan directly in the latent sp…

State Space Models

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

2021-04-26 · Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jianxiong Pan 외

Image inpainting is an underdetermined inverse problem, which naturally allows diverse contents to fill up the missing or corrupted regions realistically. Prevalent approaches using convolutional neural networks (CNNs) c…

DiversityImage InpaintingLanguage ModelingLanguage Modelling

Learning Latent Dynamics for Planning from Pixels

2018-11-12 · Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas 외

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning…

continuous-controlContinuous ControlMotion PlanningVariational Inference

Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation

2026-04-19 · Vaibhavi Lokegaonkar, Aryan Vijay Bhosale, Vishnu Raj, Gouthaman KV 외 arxiv

Video-to-music (V2M) is the fundamental task of creating background music for an input video. Recent V2M models achieve audiovisual alignment by typically relying on visual conditioning alone and provide limited semantic…

Music Generation