Challenge: Existing approaches to abstractive summarization suffer from exposure bias . Existing solutions bridge this gap through un- or semi-supervised holistic learning .
Approach: They propose to reformat abstractive summarization to sequential generation and revision (SeGRe) this allows the model to assess the flawed summary from a global perspective and modify inappropriate expressions.
Outcome: The proposed model can assess the flawed summary from a global view and modify inappropriate expressions.

Similar Papers

Pre-training for Abstractive Document Summarization by Reinstating Source Text (2020.emnlp-main)

Copied to clipboard

Challenge: Abstractive document summarization models are often trained on limited supervised data . authors present three objectives for pretraining abstractive summarizing models .
Approach: They propose to pre-train a SEQ2SEQ based abstractive summarization model on unlabeled text.
Outcome: The proposed method improves on two benchmark summarization datasets with 19GB of text . the goal is sentence reordering, next sentence generation and masked document generation .
Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution (2021.acl-long)

Copied to clipboard

Challenge: Abstractive summarization models have made great strides in recent years, but little is known about how they actually form summaries and how to understand where their decisions come from.
Approach: They propose a two-step method to interpret summarization model decisions by categorizing each decoder decision into one of several generation modes.
Outcome: The proposed method can identify phrases the summarization model has memorized and determine where in the training pipeline this memorization happened, and study complex generation phenomena on a per-instance basis.
A New Approach to Overgenerating and Scoring Abstractive Summaries (2021.naacl-main)

Copied to clipboard

Challenge: Abstractive summarization is a learning objective to produce system outputs that resemble reference summaries on a word-to-word basis.
Approach: They propose a two-staged strategy to generate multiple variants of the target summary and score and select admissible ones according to users’ needs.
Outcome: The proposed approach can achieve state-of-the-art on benchmark summarization datasets.
The Summary Loop: Learning to Write Abstractive Summaries Without Examples (2020.acl-main)

Copied to clipboard

Challenge: Unsupervised abstractive summarization is important for news headlines and research papers . a novel method that encourages the inclusion of key terms from the original document into the summary is presented .
Approach: They propose a method that encourages the inclusion of key terms from the original document into the summary by a coverage model along with a fluency model.
Outcome: The proposed method outperforms existing methods on news summarization datasets and is competitive with existing methods.
GECSum: Generative Evaluation-Driven Sequence Level Contrastive Learning for Abstractive Summarization (2024.lrec-main)

Copied to clipboard

Challenge: Abstractive summarization is a technique in natural language processing that involves generating a summary of a source document by creating new sentences and phrases.
Approach: They propose a sequence-level contrastive learning framework that leverages the semantic understanding capabilities of the abstractive model itself to evaluate summary in reference-based settings.
Outcome: The proposed framework outperforms the state-of-the-art in four summarization datasets.
Balancing Lexical and Semantic Quality in Abstractive Summarization (2023.acl-short)

Copied to clipboard

Challenge: Existing methods to reduce exposure bias in sequence-to-sequence models are underexplored.
Approach: They propose a method to re-rank sequence-to-sequence neural models to reduce exposure bias.
Outcome: The proposed method achieves an 89.67 BERTScore on the CNN/DailyMail and XSum datasets.
Global Encoding for Abstractive Summarization (P18-2)

Copied to clipboard

Challenge: Existing models for abstractive summarization suffer from repetition and semantic irrelevance.
Approach: They propose a global encoding framework which controls the information flow from the encoder to the decoder based on the global information of the source context.
Outcome: The proposed model outperforms baseline models on the LCSTS and English Gigaword and can generate summary of higher quality and reduce repetition.
Extractive Summarization with Text Generator (2024.naacl-long)

Copied to clipboard

Challenge: Existing extractive systems lack gold training signals, thereby hindering learning of extractive models.
Approach: They propose to use text generators to train extractive summarizers by approximating outputs of abstractive summaries.
Outcome: The proposed method can be used to train extractive summarizers without training . it is shown that the approximated summaries correlate positively with the auxiliary summary outputs.
Learning From the Source Document: Unsupervised Abstractive Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for abstractive summarization are under supervised training, but obtaining high-quality and large-scale datasets for supervised learning is laboriously difficult.
Approach: They propose an unsupervised method that leverages contrastive learning to generate summaries by rewriting and paraphrasing the source documents to generate good summary.
Outcome: The proposed method outperforms baseline methods on extensive experiments on source documents and fake documents.
Generalization in Generation: A closer look at Exposure Bias (D19-56)

Copied to clipboard

Challenge: Autoregressive generative models are often criticized for using ground-truth contexts at training time but generated ones at test time.
Approach: They propose that generalization is the underlying property to address and propose unconditional generation as its fundamental benchmark.
Outcome: The proposed model is generalized and can handle true and generated contexts.

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