paper-with-me

Papers

SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization

2021-06-03 · ACL 2021 5 · Yixin Liu, PengFei Liu

In this paper, we present a conceptually simple while empirically powerful framework for abstractive summarization, SimCLS, which can bridge the gap between the learning objective and evaluation metrics resulting from the currently dominated sequence-to-sequence learning framework by formulating text generation as a reference-free evaluation problem (i.e., quality estimation) assisted by contrastive learning. Experimental results show that, with minor modification over existing top-scoring systems, SimCLS can improve the performance of existing top-performing models by a large margin. Particularly, 2.51 absolute improvement against BART and 2.50 over PEGASUS w.r.t ROUGE-1 on the CNN/DailyMail dataset, driving the state-of-the-art performance to a new level. We have open-sourced our codes and results: https://github.com/yixinL7/SimCLS. Results of our proposed models have been deployed into ExplainaBoard platform, which allows researchers to understand our systems in a more fine-grained way.

📄 PDF Abstract BibTeX arXiv:2106.01890

Code (2)

yixinL7/SimCLS 공식 구현 pytorch
andrejmiscic/simcls-pytorch pytorch

Tasks

Abstractive Text SummarizationContrastive LearningText GenerationText Summarization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
PEGASUS PEGASUS proposes a transformer-based model for abstractive summarization. It uses a special self-supervised pre-training objective called gap-sentences generation (GSG) that's…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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…
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…

Similar Papers 제목 키워드 기반

Improving Factuality of Abstractive Summarization via Contrastive Reward Learning

2023-07-10 · I-Chun Chern, Zhiruo Wang, Sanjan Das, Bhavuk Sharma 외

Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates r…

Abstractive Text SummarizationContrastive Learning

Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization

2023-05-03 · ACL 2023 5 · Jiawen Xie, Qi Su, Shaoting Zhang, and Xiaofan Zhang

Most Transformer based abstractive summarization systems have a severe mismatch between training and inference, i.e., exposure bias. From diverse perspectives, we introduce a simple multi-level contrastive learning frame…

Abstractive Text SummarizationContrastive LearningDecoderFew-Shot Learning

A Unified and Efficient Contrastive Learning Framework for Text Summarization

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Both extractive and abstractive summarization systems share a common problem, i.e., there is a mismatch between the training object and evaluation metrics. To bridge this gap, we introduce a unified and efficient contra…

Abstractive Text SummarizationContrastive LearningText Summarization

Contrastive Attention Mechanism for Abstractive Sentence Summarization

2019-10-29 · IJCNLP 2019 11 · Xiangyu Duan, Hoongfei Yu, Mingming Yin, Min Zhang 외

We propose a contrastive attention mechanism to extend the sequence-to-sequence framework for abstractive sentence summarization task, which aims to generate a brief summary of a given source sentence. The proposed contr…

Abstractive Text SummarizationSentenceSentence SummarizationText Summarization

Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization

2021-08-26 · Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang, Ling Fan 외

In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization. Our model adopts a standard Transformer-based architecture with a multi-layer …

Abstractive Text SummarizationContrastive LearningDecoderDenoising+2