Challenge: a popular approach to learning data representations involves the use of an auto-encoder that compresses data into a latent-space representation without supervision.
Approach: They propose to train an auto-encoder that encodes input text into human-readable sentences . they use comprehensible natural language as a latent representation of the input source text .
Outcome: The proposed auto-encoder can encode input text into human-readable sentences without document-summary pairs.

Similar Papers

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.
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 .
Adversarial Domain Adaptation Using Artificial Titles for Abstractive Title Generation (P19-1)

Copied to clipboard

Challenge: Obtaining good quality labeled data can be difficult and expensive for abstractive summarization models . authors propose the use of artificial titles for unlabeled target documents .
Approach: They propose to use artificial titles and sequential training to capture grammatical style of unlabeled target domains to adapt to/from news articles and Stack Exchange posts.
Outcome: The proposed techniques can boost performance for unsupervised adaptation and fine-tuning with limited target data.
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting (P18-1)

Copied to clipboard

Challenge: Empirically, we achieve the new state-of-the-art on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores.
Approach: They propose a sentence-level policy gradient method that bridges computation between two neural networks in a hierarchical way while maintaining language fluency.
Outcome: The proposed model achieves state-of-the-art on all metrics and higher abstractiveness scores on the CNN/Daily Mail dataset and faster training convergence than previous models.
Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods focus on attention mechanism, but they are not suitable for abstractive text summarization.
Approach: They propose a siamese generative adversarial net for abstractive text summarization which preserves the main semantics of the source text and the target summary.
Outcome: The proposed model can preserve the main semantics of the source text and target summary.
Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization (D18-1)

Copied to clipboard

Challenge: Existing methods to summarize short texts using a neural encoder-decoder are limited and expensive to obtain.
Approach: They propose to use a maximal marginal relevance method to select representative sentences from multi-document input and leverage an abstractive encoder-decoder model to fuse disparate sentences to an abstract.
Outcome: The proposed method compares favorably to state-of-the-art extractive and abstractive approaches judged by automatic metrics and human assessors.
Deep Communicating Agents for Abstractive Summarization (N18-1)

Copied to clipboard

Challenge: Empirical results show that multiple communicating agents produce a better summary than extractive summarization.
Approach: They propose an encoder-decoder architecture that uses deep communicating agents to represent a long document for abstractive summarization.
Outcome: Empirical results show that multiple communicating agents produce a better summary than baselines.
Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation (D18-1)

Copied to clipboard

Challenge: Recent work on abstractive summarization has made progress with neural encoder-decoder architectures, but these models lack explicit semantic modeling of the source document and its summary.
Approach: They extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which they guide using the source document.
Outcome: The proposed approach improves summarization performance by 7.4 and 10.5 points in ROUGE-2 using gold standard AMR parses and parses obtained from an off-the-shelf parser respectively.
StructSum: Summarization via Structured Representations (2021.eacl-main)

Copied to clipboard

Challenge: Abstractive summarization models overfit to training corpora, lack of transparency and layout bias . authors propose incorporating latent and explicit dependencies across sentences in source document .
Approach: They propose a framework based on document-level structure induction to address layout bias and lack of transparency in abstractive summarization models.
Outcome: The proposed framework improves coverage of content in the source documents and generates more abstractive summaries by generating more novel n-grams.
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling (2020.lrec-1)

Copied to clipboard

Challenge: Abstractive summarization is an NLP task with many real-world applications.
Approach: They propose to use a pre-trained language model to train a Transformer-based neural model . they propose a new method of BERT-windowing to allow chunk-wise processing of texts longer than the BERT window size .
Outcome: The proposed model outperforms baseline models on CNN/Daily Mail dataset and shows its superiority on German dataset.

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