Challenge: Recent studies indicated that neural methods are governed by the scaling law for the amount of training data.
Approach: They propose a low-cost strategy to augment training data for abstractive summarization tasks by extracting summarized text and paraphrasing it.
Outcome: The proposed strategy outperforms back-translation and self-training and is more cost-efficient when training data is small.

Similar Papers

Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization (2021.findings-emnlp)

Copied to clipboard

Challenge: a new study explores data manipulation techniques for improving abstractive summarization models without the need for any additional data.
Approach: They propose a method of data synthesis with paraphrasing, data augmentation with sample mixing and curriculum learning with new difficulty metrics based on specificity and abstractiveness.
Outcome: The proposed techniques improve abstractive summarization models without additional data . the proposed techniques can be applied in isolation and when combined .
Abstractive Document Summarization without Parallel Data (2020.lrec-1)

Copied to clipboard

Challenge: Abstractive summarization typically relies on large collections of paired articles and summaries.
Approach: They propose a system that relies only on example summaries and non-matching articles . they use an unsupervised sentence extractor that selects salient sentences .
Outcome: The proposed system performs well on CNN/DailyMail benchmark and automatic generating a press release from a scientific journal article.
Keyphrase Generation: A Text Summarization Struggle (N19-1)

Copied to clipboard

Challenge: Existing methods for keyphrase generation are unable to produce valuable terms that do not appear in the text.
Approach: They propose to consider the keyphrase string as an abstractive summary of the title and the abstract.
Outcome: The proposed method can generate better keyphrases than the existing methods or the unsupervised ones.
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models (2020.emnlp-main)

Copied to clipboard

Challenge: We present a method to produce abstractive summaries of documents that exceed several thousand words . we compare transformer based methods to extractive methods, but extractive models score higher .
Approach: They propose a method to generate abstractive summaries of documents that exceed several thousand words via neural abstractive summary.
Outcome: The proposed method produces abstractive summaries of documents that exceed several thousand words . it is compared with baseline methods, state-of-the-art models and variants of the proposed method .
Summary Level Training of Sentence Rewriting for Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing models rely on sentence-level rewards or suboptimal labels to achieve summary-level ROUGE scores.
Approach: They propose a model that extracts salient sentences from a document and paraphrases them to generate a summary.
Outcome: The proposed model improves on CNN/Daily Mail and New York Times datasets.
To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text (2021.findings-acl)

Copied to clipboard

Challenge: Abstractive summarization models have seen great improvements in recent years, but there is limited understanding of the strategies different models employ and how they relate their understanding of language.
Approach: They characterize how one popular abstractive model uses an explicit copy/generation switch to control its level of abstraction vs extraction . they find that abstractive summarization models lack the semantic understanding necessary to generate paraphrases that are both abstractive and faithful to the source document.
Outcome: The proposed model uses syntactic boundaries to truncate sentences that are often copied verbatim.
Parallel Data Augmentation for Formality Style Transfer (2020.acl-main)

Copied to clipboard

Challenge: Formality style transfer is a task of automatically transforming text in one particular formality style into another.
Approach: They propose to augment parallel data with three specific data augmentation methods to improve the model's generalization ability and reduce the overfitting risk.
Outcome: The proposed methods significantly improve performance when used to pre-train the model and lead to the state-of-the-art results in the GYAFC benchmark dataset.
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generating additional parallel sentences are aimed at expanding the support of the empirical data distribution by generating new sentence pairs that contain infrequent words.
Approach: They propose to use data augmentation techniques to generate additional parallel sentences by reversing the order of the target sentence to produce unfluent target sentences.
Outcome: The proposed approach improves on six low-resource translation tasks and the baseline and over DA methods.
Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation (2021.naacl-srw)

Copied to clipboard

Challenge: Neural machine translation is known to show poor performance at long sentence translations . however, when the sentence length exceeds a certain value, the quality of NMT becomes inferior to that of statistical machine translation.
Approach: They propose a method that uses given parallel corpora as train data to generate long sentences by concatenating two sentences at random.
Outcome: The proposed method improves translation quality more when combined with back-translation.
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches (2025.findings-naacl)

Copied to clipboard

Challenge: Existing approaches for low-resource text summarization use large language models (LLMs) but such models suffer from inconsistent outputs and are difficult to adapt to domain-specific data.
Approach: They propose two methods to effectively utilize large language models for low-resource text summarization.
Outcome: The proposed methods synthesize high-quality documents using LLaMA-3-70b-Instruct model . they achieve competitive ROUGE scores as a fully supervised method with 5% of the labeled data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations