paper-with-me

Papers

DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer

2021-10-12 · EMNLP 2021 11 · Haozhe Ji, Minlie Huang

Despite the recent advances in applying pre-trained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models. In this paper, we propose DiscoDVT, a discourse-aware discrete variational Transformer to tackle the incoherence issue. DiscoDVT learns a discrete variable sequence that summarizes the global structure of the text and then applies it to guide the generation process at each decoding step. To further embed discourse-aware information into the discrete latent representations, we introduce an auxiliary objective to model the discourse relations within the text. We conduct extensive experiments on two open story generation datasets and demonstrate that the latent codes learn meaningful correspondence to the discourse structures that guide the model to generate long texts with better long-range coherence.

📄 PDF Abstract BibTeX arXiv:2110.05999

Code (1)

cdjhz/discodvt 공식 구현 pytorch

Tasks

Story GenerationText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Adam 설명 없음
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 $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension

2019-08-28 · IJCNLP 2019 11 · Todor Mihaylov, Anette Frank

In this work, we propose to use linguistic annotations as a basis for a \textit{Discourse-Aware Semantic Self-Attention} encoder that we employ for reading comprehension on long narrative texts. We extract relations betw…

Reading ComprehensionSentence

Discourse-Aware Neural Rewards for Coherent Text Generation

2018-05-10 · NAACL 2018 6 · Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao 외

In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ord…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Sentence+2

Paragraph-level Commonsense Transformers with Recurrent Memory

2020-10-04 · Saadia Gabriel, Chandra Bhagavatula, Vered Shwartz, Ronan Le Bras 외

Human understanding of narrative texts requires making commonsense inferences beyond what is stated explicitly in the text. A recent model, COMET, can generate such implicit commonsense inferences along several dimension…

SentenceWorld Knowledge

Discourse-Aware Neural Extractive Text Summarization

2019-10-30 · ACL 2020 6 · Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu

Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries.…

Extractive Text SummarizationSentenceText Summarization

Align to Structure: Aligning Large Language Models with Structural Information

2025-04-04 · Zae Myung Kim, Anand Ramachandran, Farideh Tavazoee, Joo-Kyung Kim 외

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel meth…

Document SummarizationText Generation