paper-with-me

홈 › Papers

Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness

2022-05-04 · NAACL 2022 7 · Yun-Zhu Song, Yi-Syuan Chen, Hong-Han Shuai

A notable challenge in Multi-Document Summarization (MDS) is the extremely-long length of the input. In this paper, we present an extract-then-abstract Transformer framework to overcome the problem. Specifically, we leverage pre-trained language models to construct a hierarchical extractor for salient sentence selection across documents and an abstractor for rewriting the selected contents as summaries. However, learning such a framework is challenging since the optimal contents for the abstractor are generally unknown. Previous works typically create pseudo extraction oracle to enable the supervised learning for both the extractor and the abstractor. Nevertheless, we argue that the performance of such methods could be restricted due to the insufficient information for prediction and inconsistent objectives between training and testing. To this end, we propose a loss weighting mechanism that makes the model aware of the unequal importance for the sentences not in the pseudo extraction oracle, and leverage the fine-tuned abstractor to generate summary references as auxiliary signals for learning the extractor. Moreover, we propose a reinforcement learning method that can efficiently apply to the extractor for harmonizing the optimization between training and testing. Experiment results show that our framework substantially outperforms strong baselines with comparable model sizes and achieves the best results on the Multi-News, Multi-XScience, and WikiCatSum corpora.

📄 PDF Abstract BibTeX arXiv:2205.01889

Code (1)

yunzhusong/NAACL2022-REFLECT 공식 구현 pytorch

Tasks

Document SummarizationMulti-Document SummarizationSentence

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Multi-Head Attention 설명 없음
Residual Connection 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 $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음

Similar Papers 제목 키워드 기반

A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance and Self-referenced Redundancy

2021-06-26 · ACL 2021 5 · Wang Chen, Piji Li, Irwin King

In recent years, reference-based and supervised summarization evaluation metrics have been widely explored. However, collecting human-annotated references and ratings are costly and time-consuming. To avoid these limitat…

Document SummarizationSentence

A Topic-aware Summarization Framework with Different Modal Side Information

2023-05-19 · Xiuying Chen, Mingzhe Li, Shen Gao, Xin Cheng 외

Automatic summarization plays an important role in the exponential document growth on the Web. On content websites such as CNN.com and WikiHow.com, there often exist various kinds of side information along with the main …

Contrastive LearningTriplet

Scientific Article Summarization Using Citation-Context and Article's Discourse Structure

2017-04-21 · EMNLP 2015 9 · Arman Cohan, Nazli Goharian

We propose a summarization approach for scientific articles which takes advantage of citation-context and the document discourse model. While citations have been previously used in generating scientific summaries, they l…

Articles

Heterogeneous Graph Neural Networks for Extractive Document Summarization

2020-04-26 · ACL 2020 6 · Danqing Wang, PengFei Liu, Yining Zheng, Xipeng Qiu 외

As a crucial step in extractive document summarization, learning cross-sentence relations has been explored by a plethora of approaches. An intuitive way is to put them in the graph-based neural network, which has a more…

Document SummarizationExtractive Document SummarizationExtractive SummarizationExtractive Text Summarization+1

Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

2021-10-16 · ACL 2022 5 · Yusen Zhang, Ansong Ni, Ziming Mao, Chen Henry Wu 외

Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unable to efficiently process long text for …

Abstractive Text SummarizationDocument SummarizationMeeting SummarizationText Summarization