paper-with-me

홈 › Papers

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 framework for abstractive summarization (SimMCS) and a tailored sparse decoder self-attention pattern (SDSA) to bridge the gap between training and inference to improve model performance. Compared with previous contrastive objectives focusing only on the relative order of probability mass assigned to non-gold summaries, SimMCS additionally takes their absolute positions into account, which guarantees that the relatively high-quality (positive) summaries among them could be properly assigned high probability mass, and further enhances the capability of discriminating summary quality beyond exploiting potential artifacts of specific metrics. SDSA simulates the possible inference scenarios of deviation in the training phase to get closer to the ideal paradigm. Our approaches outperform the previous state-of-the-art results on two summarization datasets while just adding fairly low overhead. Further empirical analysis shows our model preserves the advantages of prior contrastive methods and possesses strong few-shot learning ability.

📄 PDF Abstract BibTeX

Code (1)

xjw-nlp/SimMCS pytorch

Tasks

Abstractive Text SummarizationContrastive LearningDecoderFew-Shot Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization

2021-08-26 · Shichao Sun, Wenjie Li

Encoder-decoder models have achieved remarkable success in abstractive text summarization, which aims to compress one or more documents into a shorter version without the loss of the essential content. Unfortunately, the…

Abstractive Text SummarizationContrastive LearningDecoderText Summarization

Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems

2020-05-20 · Chang Zhou, Jianxin Ma, Jianwei Zhang, Jingren Zhou 외

Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems. Standard approaches approxi…

Contrastive LearningFairnessLanguage ModelingLanguage Modelling+2

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

2026-07-30 · Xingjian Wu, Junlin Liu, Xingchen Liu, Xuhang Zhu 외 arxiv

Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level super…

Reinforcement LearningContrastive Learning

Order-free Learning Alleviating Exposure Bias in Multi-label Classification

2019-09-08 · Che-Ping Tsai, Hung-Yi Lee

Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label de…

DecoderGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation

2025-11-27 · Difu Feng, Qianqian Xu, Zitai Wang, Cong Hua 외 arxiv

Nowadays, recommendation systems have become crucial to online platforms, shaping user exposure by accurate preference modeling. However, such an exposure strategy can also reinforce users' existing preferences, leading …

Recommendation Systems