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.

Similar Papers

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.
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (N18-2)

Copied to clipboard

Challenge: Existing abstractive summarization models focus on summarizing sentences and short documents.
Approach: They propose a hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary.
Outcome: The proposed model significantly outperforms state-of-the-art models on two large-scale datasets of scientific papers.
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Abstractive summarization is the task of generating a concise summary of input documents . a middle-aged man and a young girl died after they were unable to avoid the plane .
Approach: They propose a model that enriches the original Transformer with a Tensor Product Representation for abstractive summarization.
Outcome: The proposed model outperforms the Transformer and the original TP-Transformer significantly on several datasets.
Structure-Infused Copy Mechanisms for Abstractive Summarization (C18-1)

Copied to clipboard

Challenge: Experimental results show that system summaries struggle to preserve syntactic meaning of source texts.
Approach: They propose to incorporate syntactic information from source sentences into abstractive summaries by structure-infused copy mechanisms.
Outcome: The proposed approach compares favorably to state-of-the-art methods.
Improving Neural Abstractive Document Summarization with Structural Regularization (D18-1)

Copied to clipboard

Challenge: Recent advances in document summarization fail to capture long-term structure of documents and multi-sentence summaries, resulting in information loss and repetitions.
Approach: They propose to leverage structural information of documents and multi-sentence summaries to improve document summarization performance.
Outcome: The proposed model outperforms state-of-the-art models on document summarization tasks.
Abstractive Summarization Guided by Latent Hierarchical Document Structure (2022.emnlp-main)

Copied to clipboard

Challenge: Sequential abstractive summarizations often do not capture hierarchical and inter-sentential dependencies in the summmarized document.
Approach: They propose a hierarchy-aware graph neural network which captures hierarchical and inter-sentential dependencies in the summmarized document.
Outcome: The proposed model improves strong sequence models such as BART with a 0.55 and 0.75 margin in ROUGE-1/2/L for CNN/DM and XSum.
Document Summarization with Latent Queries (2022.tacl-1)

Copied to clipboard

Challenge: Existing benchmarks for query-focused summarization are small for training large neural models.
Approach: They propose a unified modeling framework for query-focused summarization . they model queries as discrete latent variables over document tokens .
Outcome: The proposed framework outperforms strong comparison systems across benchmarks, query types, document settings, and target domains.
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.
Long Document Summarization with Top-down and Bottom-up Inference (2023.findings-eacl)

Copied to clipboard

Challenge: Recent models infer latent representations of words or tokens with a transformer encoder, which is bottom-up and thus does not capture long-distance context well.
Approach: They propose a method to infer latent representations of words or tokens in documents . they assume a hierarchical structure of a document where top-level captures long range dependency .
Outcome: The proposed model can summarize an entire book and achieve competitive performance on a wide range of document summarization benchmarks.
Beyond Generic Summarization: A Multi-faceted Hierarchical Summarization Corpus of Large Heterogeneous Data (L18-1)

Copied to clipboard

Challenge: Automated summarization has focused on ten to twenty documents, typically news articles, but could in theory analyze hundreds of documents from a wide range of sources and provide an overview to the interested reader.
Approach: They propose a method for creating hierarchical summarization corpora from large, heterogeneous document collections by crowdsourcing relevant content and asking trained annotators to order the relevant information hierarchically.
Outcome: The proposed method can be used to develop and evaluate hierarchical summarization systems.

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