| Challenge: | Existing methods to generate summaries of different styles without training separate models are lacking parallel data and expensive (re)training. |
| Approach: | They propose two methods that can be deployed during summary decoding on any pre-trained Transformer-based summarization model. |
| Outcome: | The proposed methods generate news headlines with various ideological leanings while still informative. |
Similar Papers
HydraSum: Disentangling Style Features in Text Summarization with Multi-Decoder Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive summarization systems implicitly encode “decisions” about summary properties, but these are not enforced. |
| Approach: | They propose a new summarization architecture that extends existing models to a mixture-of-experts version with multiple decoders. |
| Outcome: | The proposed architecture outperforms baseline models in obtaining stylistically-diverse summaries by sampling from individual decoders or their mixtures. |
Attention Head Masking for Inference Time Content Selection in Abstractive Summarization (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies show that multi-heads attentions at the same layer collectively guide the summarization. |
| Approach: | They propose an inference-time attention head masking mechanism that works on encoder-decoder attentions to pinpoint salient content at inference time. |
| Outcome: | The proposed technique outperforms state-of-the-art models on CNN/DailyMail and New York Times datasets and is data-efficient. |
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. |
Training Dynamics for Text Summarization Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models have shown impressive results when fine-tuned on large summarization datasets. |
| Approach: | They analyze the training dynamics for generation models, focusing on summarization . they find that a propensity to copy the input is learned early in the training process . |
| Outcome: | The proposed model learns at different stages of fine-tuning, the authors show . they show that factual errors are learnt in later stages, but not at high-loss tokens . |
Boosting Summarization with Normalizing Flows and Aggressive Training (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that FlowSUM improves the quality of generated summaries with minimal impact on inference time. |
| Approach: | They propose a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization. |
| Outcome: | The proposed model improves the quality of generated summaries and reduces inference time. |
Abstractive Document Summarization with Summary-length Prediction (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing abstractive summarization models do not consider summarizing-specific information such as the target summary length. |
| Approach: | They propose a method for enabling a model to understand summarization-specific information by predicting the summary length in the encoder and generating a summary of the predicted length in fine-tuning. |
| Outcome: | The proposed method improves ROUGE scores on the WikiHow, NYT, and CNN/DM datasets. |
Generating Summaries with Topic Templates and Structured Convolutional Decoders (P19-1)
Copied to clipboard
| Challenge: | Existing neural generation approaches create multi-sentence text as a single sequence . Existing approaches create multiple sentences as if they were a sequence based on content structure . |
| Approach: | They propose a structured convolutional decoder that is guided by the content structure of target summaries. |
| Outcome: | The proposed model outperforms existing decoders on three datasets representing different domains. |
Inducing Document Structure for Aspect-based Summarization (P19-1)
Copied to clipboard
| Challenge: | Abstractive summarization systems treat documents as unstructured and generate a single generic summary per document. |
| Approach: | They propose to incorporate document structure into automatic summarization systems . they induce latent document structure and abstractive summarizing objective . |
| Outcome: | The proposed model improves on topic-agnostic baselines and can produce abstractive and extractive aspect-based summaries. |
Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation (2020.lrec-1)
Copied to clipboard
| Challenge: | Summarizing text is not a straightforward task. |
| Approach: | They propose to use automated transcriptions to generate reports from automatic transcriptions as a dataset for neural summarization. |
| Outcome: | The proposed model improves on publicmeetings corpus on a dataset of aligned public meetings. |
Summarization Beyond News: The Automatically Acquired Fandom Corpora (2020.lrec-1)
Copied to clipboard
| Challenge: | Abstractive summarization methods require large corpora to train neural architectures. |
| Approach: | They propose a novel automatic corpus construction approach that automatically constructs large open-licensed summarization corpora from existing large text collections and an evaluation process with human annotators. |
| Outcome: | The proposed approach can be used to train abstractive summarization models on large corpora and through a manual evaluation with human annotators. |