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.

Similar Papers

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.
Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on aspect-based abstractive summarization assume a small set of aspects and do not consider other diverse aspects.
Approach: They propose a weak supervision construction method and an aspect modeling scheme to solve this problem.
Outcome: The proposed method significantly expands the application of the task in practice.
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.
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.
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents (2021.acl-short)

Copied to clipboard

Challenge: Faceted summarization provides briefings of a document from different perspectives.
Approach: They propose a faceted summarization benchmark built on Emerald journal articles . they propose faceted models that bring structure into faceted documents .
Outcome: The proposed benchmark is based on Emerald journal articles and covers a diverse range of domains.
Aspect-Controllable Opinion Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work on opinion summarization produces general summaries based on reviews and popularity of opinions expressed in them.
Approach: They propose an approach that generates customized opinion summaries based on aspect queries.
Outcome: The proposed model outperforms the current state of the art and generates personalized summaries by controlling the number of aspects discussed in them.
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.
ASPECTNEWS: Aspect-Oriented Summarization of News Documents (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for generating generic summarizations can't be used to generalize to these domains without seeing in-domain training data.
Approach: They use a dataset of real-world aspect-oriented summaries to annotate articles from two different news sub-domains.
Outcome: The proposed approach produces better focused summaries than existing systems without seeing in-domain training data.
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.
End-to-End Segmentation-based News Summarization (2022.findings-acl)

Copied to clipboard

Challenge: Existing summarization systems only provide one genetic summary of the whole article, making it difficult for users to navigate the reading.
Approach: They propose a task of segmenting a news article into multiple sections and generating the corresponding summary to each section.
Outcome: The proposed model outperforms state-of-the-art models on a 27k news article dataset . it can jointly segment a document and produce the summary for each section .

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