Lune

EMNLP Findings2021

Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization

Lulu Zhao, Weihao Zeng, Weiran Xu, Jun Guo

Abstract

Abstractive dialogue summarization suffers from a lots of factual errors, which are due to scattered salient elements in the multi-speaker information interaction process.In this work, we design a heterogeneous semantic slot graph with a slot-level mask cross-attention to enhance the slot features for more correct summarization.We also propose a slot-driven beam search algorithm in the decoding process to give priority to generating salient elements in a limited length by "filling-in-the-blanks". Besides, an adversarial contrastive learning assisting the training process is introduced to alleviate the exposure bias.Experimental performance on different types of factual errors shows the effectiveness of our methods and human evaluation further verifies the results. (Mary) (Nick) It's OK ... It's OK ... Sorry , I didn't make it to your birthday party .Sorry , I didn't make it to your birthday party .But I just go so distracted

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Multi-Fact Correction in Abstractive Text Summarization cites Evaluating the Factual Consistency of Abstractive Text Summarization
  • Multi-Fact Correction in Abstractive Text Summarization cites FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization
  • Dialogue Summarization with Static-Dynamic Structure Fusion Graph cites Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Dialogue Summarization with Static-Dynamic Structure Fusion GraphShen Gao, Xin Cheng, Mingzhe Li, Xiuying Chen et al.ACL 2023 · 14 citations

Builds on7

  1. Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue SummarizationJiaao Chen, Diyi YangEMNLP 2020 · 121 citations
  2. Contrastive Learning with Adversarial Perturbations for Conditional Text GenerationSeanie Lee, Dong Bok Lee, Sung Ju HwangICLR 2021 · 117 citations
  3. Multi-Fact Correction in Abstractive Text SummarizationYue Dong, Shuohang Wang, Zhe Gan, Yu Cheng et al.EMNLP 2020 · 99 citations
  4. FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive SummarizationEsin Durmus, He He, Mona T. DiabACL 2020 · 90 citations
  5. Evaluating the Factual Consistency of Abstractive Text SummarizationWojciech Kryscinski, Bryan McCann, Caiming Xiong, Richard SocherEMNLP 2020 · 67 citations

Related papers

  1. Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive SummarizationJiawen Xie, Qi Su, Shaoting Zhang, Xiaofan ZhangACL Findings 2023 · 4 citations
  2. Factual Relation Discrimination for Factuality-oriented Abstractive SummarizationZhiguang Gao, Peifeng Li, Feng Jiang, Xiaomin Chu et al.EMNLP Findings 2023 · 1 citation
  3. Discriminative Adversarial Search for Abstractive SummarizationThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski et al.ICML 2020 · 37 citations
  4. Towards Understanding Consumer Healthcare Questions on the Web with Semantically Enhanced Contrastive LearningShweta Yadav, Stefan Cobeli, Cornelia CarageaWWW 2023 · 7 citations
  5. CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationShuyang Cao, Lu WangEMNLP 2021 · 130 citations
Dusk over the sea between two cliffs drawn in fine vertical lines