LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization (N19-4)
Copied to clipboard
| Challenge: | Neural abstractive text summarization (NATS) has gained a lot of attention in the past few years from both industry and academia. |
| Approach: | They propose an open-source toolkit for training and evaluation of different sequence-to-sequence based models for the NATS task and for deploying the pre-trained models to real-world applications. |
| Outcome: | The proposed model can be used to generate high-quality summaries that are verbally innovative and can easily incorporate external knowledge. |
Similar Papers
A Survey of Automatic Text Summarization Using Graph Neural Networks (2022.coling-1)
Copied to clipboard
| Challenge: | Abstractive ATS involves generating factually correct and fluent sentences. |
| Approach: | They provide an overview of the use of graph neural networks (GNNs) for automatic text summarization. |
| Outcome: | The proposed model is based on a set of graph neural networks (GNNs) that are used to generate a concise, correct and fluent summary of a given text. |
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization (2021.acl-short)
Copied to clipboard
| Challenge: | Experimental results show that SimCLS can improve existing top-performing models by a large margin. |
| Approach: | They propose a framework for abstractive summarization that is conceptually simple and empirically powerful. |
| Outcome: | The proposed framework improves the performance of top-performing models by a large margin against existing top-scoring systems. |
Searching for Effective Neural Extractive Summarization: What Works and What’s Next (P19-1)
Copied to clipboard
| Challenge: | Recent years have seen success in the use of deep neural networks on text summarization, but there is no clear understanding of why they perform so well or how they might be improved. |
| Approach: | They propose to use different types of model architectures to improve extractive summarization systems. |
| Outcome: | The proposed framework achieves state-of-the-art on CNN/DailyMail by a large margin based on observations and analysis. |
NEWTS: A Corpus for News Topic-Focused Summarization (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarking corpora provide concordant pairs of full and abridged versions of Web, news or professional content. |
| Approach: | They propose a topical summarization corpus called NEWTS that is annotated via crowd-sourcing. |
| Outcome: | The proposed model can condition summaries on a desired range of themes . the proposed model outperforms Lead-3 baselines on most benchmark datasets . |
Neural Text Summarization: A Critical Evaluation (D19-1)
Copied to clipboard
| Challenge: | Current approaches to text summarization use advanced attention and copying mechanisms, multi-task and multi-reward training techniques. |
| Approach: | They evaluate datasets, evaluation metrics, and models for text summarization . they highlight three primary shortcomings: 1) datasets leave task underconstrained; 2) models overfit layout biases . |
| Outcome: | The current evaluation protocol is weakly correlated with human judgment and does not account for factual correctness. |
On the Abstractiveness of Neural Document Summarization (D18-1)
Copied to clipboard
| Challenge: | Recent studies show that document summarization systems are abstractive . authors suggest that automated summarizing systems could be improved . |
| Approach: | They propose to use a pure copy system to verify abstractiveness of document summarization systems. |
| Outcome: | The proposed system produces abstractive summaries while being far more efficient. |
Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to summarize documents are not extractive and require an abstractive approach. |
| Approach: | They propose a novel abstractive model which is conditioned on the article’s topics and based entirely on convolutional neural networks. |
| Outcome: | The proposed model outperforms an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans. |
IceSum: An Icelandic Text Summarization Corpus (2021.naacl-srw)
Copied to clipboard
| Challenge: | Automatic Text Summarization (ATS) is the task of generating concise and fluent summaries from one or more documents. |
| Approach: | They present a corpus of 1,000 Icelandic news articles and extractive summaries . they train several neural network-based models on the corpus and evaluate them . |
| Outcome: | The proposed model outperforms baseline methods in the evaluation of the dataset and the models with an open license. |
SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization (2021.acl-demo)
Copied to clipboard
| Challenge: | despite advances in abstractive text summarization, the true performance and failure modes of modern neural models are not yet fully understood due to the black-box nature of neural models and unmanageable scale of recent datasets for manual analysis. |
| Approach: | They propose an open-source tool for visualizing abstractive summaries that enables fine-grained analysis of models, data, and evaluation metrics associated with text summarization. |
| Outcome: | The proposed tool can identify the shortcomings and failure modes of state-of-the-art summarization models. |
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. |