# Transductive Learning for Abstractive News Summarization

arXiv: https://arxiv.org/abs/2104.09500 · HTML: https://mlsanity.com/paper/2104.09500/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Bottom-Up Abstractive Summarization](https://mlsanity.com/paper/1808.10792/) (2018)
- [Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting](https://mlsanity.com/paper/2004.12651/) (2020)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [Ranking Sentences for Extractive Summarization with Reinforcement Learning](https://mlsanity.com/paper/1802.08636/) (2018)
- [Unsupervised Opinion Summarization as Copycat-Review Generation](https://mlsanity.com/paper/1911.02247/) (2019)
- [Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation](https://mlsanity.com/paper/2010.12836/) (2020)
- [A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss](https://mlsanity.com/paper/1805.06266/) (2018)
- [Neural Extractive Text Summarization with Syntactic Compression](https://mlsanity.com/paper/1902.00863/) (2019)
- [Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints](https://mlsanity.com/paper/1603.08887/) (2016)

## Built on by (most cited first, 1 of 1)

- [Efficient Few-Shot Fine-Tuning for Opinion Summarization](https://mlsanity.com/paper/2205.02170/) (2022)

## Abstract (arXiv)

Pre-trained and fine-tuned news summarizers are expected to generalize to news articles unseen in the fine-tuning (training) phase. However, these articles often contain specifics, such as new events and people, a summarizer could not learn about in training. This applies to scenarios such as a news publisher training a summarizer on dated news and summarizing incoming recent news. In this work, we explore the first application of transductive learning to summarization where we further fine-tune models on test set inputs. Specifically, we construct pseudo summaries from salient article sentences and input randomly masked articles. Moreover, this approach is also beneficial in the fine-tuning phase, where we jointly predict extractive pseudo references and abstractive gold summaries in the training set. We show that our approach yields state-of-the-art results on CNN/DM and NYT datasets, improving ROUGE-L by 1.05 and 0.74, respectively. Importantly, our approach does not require any changes of the original architecture. Moreover, we show the benefits of transduction from dated to more recent CNN news. Finally, through human and automatic evaluation, we demonstrate improvements in summary abstractiveness and coherence.